文章目录
一、YUV 简介
YUV
:是一种颜色编码方法,常使用在各个视频处理组件中
Y'UV(模拟), YCbCr(数字), YPbPr
等专有名词都可以称为 YUV,彼此有重叠Y
表示明亮度(单取此通道即可得灰度图),U
和V
则是描述图像的色彩饱和度,用于指定像素的颜色- 编解码:采集到的视频数据一般是 RGB24,为了节省带宽,一般需要经过 编码转换(RGB2YUV) 为 NV12 进行传输;应用时一般需要经过 解码转换(YUV2RGB) 为 RGB 用于显示或后续算法
- YUV 采样方式及原理:根据人眼的特点,将人眼相对不敏感的色彩信息进行压缩采样(亮度保持不变),得到相对小的文件进行播放和传输
YUV4:2:0
数据,每四个 Y 共用一组 UV 分量,在内存中的长度是h * w + h * w / 4 + h * w / 4 = h * w *1.5
,是RGB(h * w * 3)
格式视频数据内存的一半,每个像素的 Y 数据保留, 两个像素数据只保留一个 U 或者 V 数据YUV4:2:2
数据,每两个 Y 共用一组 UV 分量,在内存中的长度是h * w + h * w / 2 + h * w / 2 = h * w *2
,是RGB(h * w * 3)
格式视频数据内存 2/3,每两个相邻的像素,一个丢弃 V 数据,一个丢弃 U 数据YUV4:4:4
数据,每一个 Y 共用一组 UV 分量,在内存中的长度是h * w + h * w + h * w = h * w *3
,与RGB(h * w * 3)
格式视频数据内存一样- YUV 存储格式:
packed
(打包格式):每个像素点的 Y,U,V 是连续交叉存储的(YUVYUVYUVYUV)planar
(平面格式):先连续存储所有像素点的 Y,紧接着存储所有像素点的 U,随后是所有像素点的V(YYYYUUVV)semi-planar
(半平面格式):先连续存储所有像素点的 Y,紧接着连续交叉存储所有像素点的U,V(YYYYUV)- YUV444 & RGB 相互转换:
- 图形显示时常用 RGB 模型,而 YUV 常用在数据传输场景,所以这两种颜色模型之间经常需要进行转换
- 可以根据其采样格式来从码流中还原每个像素点的
YUV
值,进而通过YUV
与RGB
的转换公式提取出每个像素点的RGB
值,然后显示出来(可参考博客:YUV 采样与恢复 )
- YUV 转 RGB:输入图像的宽度和高度必须为偶数;输入图像的
y 和 uv plane
的stride
必须相同
// BT601(SDTV)/BT709(HDTV)/BT2020(UHDTV) 定义了 RGB 和 YUV 互转的色域标准规范
// BT2020 的 YUV 转换公式和 BT601 BT709 都是不同的,但是两者的取值范围是相同的,一般 HD 视频(1080p)使用 BT601
// 转换, UHDTV(4k或8K)使用 BT2020 协议转换, 若视频信号中无色域标志或者色彩转换矩阵, 默认使用 BT601 即可,
// ffmpeg 转 rgb 也是这样操作的。
// 参考:https://www.zhihu.com/question/20656646/answer/261286123
#define ROUND(f) static_cast<int>(f + 0.5f)
static int RoundToByte(float f) {
int i = ROUND(f);
return (i < 0) ? 0 : ((i > 255) ? 255 : i);
}
// BT.601 limited range YUV to RGB reference
// RGB 范围 [0,255],Y 范围 [16,235] ,UV 范围 [16,239]。如果计算结果超过了取值范围要进行截取
R = RoundToByte(1.164 * (Y - 16) + 1.596 * (V - 128));
G = RoundToByte(1.164 * (Y - 16) - 0.391 * (U - 128) - 0.813 * (V - 128));
B = RoundToByte(1.164 * (Y - 16) + 2.018 * (U - 128));
// BT.601 full range YUV to RGB reference (aka JPEG)
// RGB 的范围是 [0,255],Y 和 UV 的范围是[0,255]。如果计算结果超过了取值范围要进行截取
R = RoundToByte(Y + 1.40200 * (V - 128));
G = RoundToByte(Y - 0.34414 * (U - 128) - 0.71414 * (V - 128));
B = RoundToByte(Y + 1.77200 * (U - 128));
// BT.709 limited range YUV to RGB reference
R = RoundToByte(1.164 * (Y - 16) + 1.793 * (V - 128));
G = RoundToByte(1.164 * (Y - 16) - 0.213 * (U - 128) - 0.533 * (V - 128));
B = RoundToByte(1.164 * (Y - 16) + 2.112 * (U - 128));
// BT.709 full range YUV to RGB reference
R = RoundToByte(Y + 1.57480 * (V - 128));
G = RoundToByte(Y - 0.18732 * (U - 128) - 0.46812 * (V - 128));
B = RoundToByte(Y + 1.85560 * (U - 128));
// BT.2020 limited range YUV to RGB reference
R = RoundToByte(1.164384 * (Y - 16) + 1.678670 * (V - 128));
G = RoundToByte(1.164384 * (Y - 16) - 0.187326 * (U - 128) - 0.650420 * (V - 128));
B = RoundToByte(1.164384 * (Y - 16) + 2.141770 * (U - 128));
// BT.2020 full range YUV to RGB reference
R = RoundToByte(Y + 1.474600 * (V - 128));
G = RoundToByte(Y - 0.164553 * (U - 128) - 0.571353 * (V - 128));
B = RoundToByte(Y + 1.881400 * (U - 128));
- RGB 转 YUV:输入图像的宽度和高度必须为偶数
#define ROUND(f) static_cast<int>(f + 0.5f)
static int RoundToByte(float f) {
int i = ROUND(f);
return (i < 0) ? 0 : ((i > 255) ? 255 : i);
}
// RGB to YCbCr(YUV444),YCbCr 是 YUV 颜色空间的偏移版本,适用于数字视频
// RGB 范围 [0,255],Y 范围 [16,235] ,UV 范围 [16,239]。如果计算结果超过了取值范围要进行截取。
// BT.601 limited range RGB to YUV reference
Y = RoundToByte(0.257 * R + 0.504 * G + 0.098 * B + 16);
U = RoundToByte(-0.148 * R - 0.291 * G + 0.439 * B + 128);
V = RoundToByte(0.439 * R - 0.368 * G - 0.071 * B + 128);
// BT.601 full range RGB to YUV reference (aka JPEG)
Y = RoundToByte(0.299 * R + 0.587 * G + 0.114 * B);
U = RoundToByte(-0.169 * R - 0.331 * G + 0.500 * B + 128);
V = RoundToByte(0.500 * R - 0.419 * G - 0.081 * B + 128);
// BT.709 limited range RGB to YUV reference
Y = RoundToByte(0.183 * R + 0.614 * G + 0.062 * B + 16);
U = RoundToByte(-0.101 * R - 0.339 * G + 0.439 * B + 128);
V = RoundToByte(0.439 * R - 0.399 * G - 0.040 * B + 128);
// BT.709 full range RGB to YUV reference (aka JPEG)
Y = RoundToByte(0.213 * R + 0.715 * G + 0.072 * B);
U = RoundToByte(-0.115 * R - 0.385 * G + 0.500 * B + 128);
V = RoundToByte(0.500 * R - 0.454 * G - 0.046 * B + 128);
// OpenCV 读取 BGR 图像转换成 YUV444
for(l32Index1 = 0; l32Index1 < cv_img.rows; l32Index1++)
{
for(l32Index2 = 0; l32Index2 < cv_img.cols; l32Index2++)
{
# Y = 0.257*R + 0.504*G + 0.098*B + 16
f32YTmp = 0.257 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[2]) + 0.504 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[1]) + 0.098 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[0]) + 16;
u8YTmp = MIN(256, (uchar)(f32YTmp + 0.5f));
cv_img_yuv.at<cv::Vec3b>(l32Index1, l32Index2)[0] = u8YTmp;
# U = -0.148*R - 0.291*G + 0.439*B + 128
f32UTmp = -0.148 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[2]) - 0.291 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[1]) + 0.439 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[0]) + 128;
u8UTmp = (uchar)(f32UTmp + 0.5f);
cv_img_yuv.at<cv::Vec3b>(l32Index1, l32Index2)[1] = u8UTmp;
# V = 0.439*R - 0.368*G - 0.071*B + 128
f32VTmp = 0.439 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[2]) - 0.368 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[1]) - 0.071 * (int)(cv_img.at<cv::Vec3b>(l32Index1, l32Index2)[0]) + 128;
u8VTmp = (uchar)(f32VTmp + 0.5f);
cv_img_yuv.at<cv::Vec3b>(l32Index1, l32Index2)[2] = u8VTmp;
}
}
二、YUV 采样格式介绍
2.1、YUV420(NV12、NV21、I420、YV12)
# NV12、NV21 的存储格式为 Y 平面,UV 打包一个平面,共两个平面,即:先连续存储 Y,然后连续交叉存储 UV
# 不同点在于 UV 的排列顺序,SP 为 Semi-Planar 的缩写
# NV12:先是 w * h 长度的 Y,后面跟 w * h * 0.5 长度的 UV(交叉存储),总长度为 w * h * 1.5
# NV21:先是 w * h 长度的 Y,后面跟 w * h * 0.5 长度的 VU(交叉存储),总长度为 w * h * 1.5
NV12: YYYYYYYY UVUV => YUV420SP # iOS 平台常用 NV12
NV21: YYYYYYYY VUVU => YUV420SP # Android 平台常用 NV21
# I420、YV12 三个分量均为平面格式,共三个平面,即:先连续存储 Y,然后连续存储 U,最后连续存储 V
# 不同点在于 U V 的排列顺序,P 为 Planar 的缩写
# I420:先是 w * h 长度的 Y,后面跟 w * h * 0.25 长度的 U, 最后是 w * h * 0.25 长度的 V,总长度为 w * h * 1.5
# YV12:先是 w * h 长度的 Y,后面跟 w * h * 0.25 长度的 V, 最后是 w * h * 0.25 长度的 U,总长度为 w * h * 1.5
I420: YYYYYYYY UU VV => YUV420P # Android 平台常用 I420
YV12: YYYYYYYY VV UU => YUV420P
- 假设一个分辨率为
6X4
的YUV
图像(占用内存大小 6 ∗ 4 ∗ 1.5 = 36 6*4*1.5=36 6∗4∗1.5=36),它们的格式如下图:
2.1.1、NV12/NV21 转 BGR/RGB HWC
- 转换的时候指定转换标准,默认是
BT601 limited
,结构体指定不一样可以转换成BGR/RGB
// 1、NV12ToRGB24(BGRHWC)和 NV21ToRGB24(BGRHWC) 的函数接口(convert_argb.cc)
// 注意这两个函数底层传入的都是 &kYuvI601Constants;没有 kYvuI601Constants
// Convert NV12 to RGB24.
LIBYUV_API
int NV12ToRGB24(const uint8_t* src_y,
int src_stride_y,
const uint8_t* src_uv,
int src_stride_uv,
uint8_t* dst_rgb24,
int dst_stride_rgb24,
int width,
int height) {
return NV12ToRGB24Matrix(src_y, src_stride_y, src_uv, src_stride_uv,
dst_rgb24, dst_stride_rgb24, &kYuvI601Constants,
width, height);
}
// Convert NV21 to RGB24.
LIBYUV_API
int NV21ToRGB24(const uint8_t* src_y,
int src_stride_y,
const uint8_t* src_vu,
int src_stride_vu,
uint8_t* dst_rgb24,
int dst_stride_rgb24,
int width,
int height) {
return NV21ToRGB24Matrix(src_y, src_stride_y, src_vu, src_stride_vu,
dst_rgb24, dst_stride_rgb24, &kYuvI601Constants,
width, height);
}
// 2、 Conversion matrix for YUV to RGB 结构体矩阵(kYuvI601Constants)定义在 convert_argb.h 中
// 实现在 row_common.cc(MAKEYUVCONSTANTS)
// BT.601 full range YUV to RGB reference (aka JPEG)
// * R = Y + V * 1.40200
// * G = Y - U * 0.34414 - V * 0.71414
// * B = Y + U * 1.77200
// KR = 0.299; KB = 0.114
// U and V contributions to R,G,B.
#define UB 113 /* round(1.77200 * 64) */
#define UG 22 /* round(0.34414 * 64) */
#define VG 46 /* round(0.71414 * 64) */
#define VR 90 /* round(1.40200 * 64) */
// Y contribution to R,G,B. Scale and bias.
#define YG 16320 /* round(1.000 * 64 * 256 * 256 / 257) */
#define YB 32 /* 64 / 2 */
MAKEYUVCONSTANTS(JPEG, YG, YB, UB, UG, VG, VR)
// 3、convert_argb.h 中定义的转换结构体
// Conversion matrix for YUV to RGB(实际使用下来是 BGR)
LIBYUV_API extern const struct YuvConstants kYuvI601Constants; // BT.601
LIBYUV_API extern const struct YuvConstants kYuvJPEGConstants; // BT.601 full
LIBYUV_API extern const struct YuvConstants kYuvH709Constants; // BT.709
LIBYUV_API extern const struct YuvConstants kYuvF709Constants; // BT.709 full
LIBYUV_API extern const struct YuvConstants kYuv2020Constants; // BT.2020
LIBYUV_API extern const struct YuvConstants kYuvV2020Constants; // BT.2020 full
// Conversion matrix for YVU to BGR(实际使用下来是 RGB)
LIBYUV_API extern const struct YuvConstants kYvuI601Constants; // BT.601
LIBYUV_API extern const struct YuvConstants kYvuJPEGConstants; // BT.601 full
LIBYUV_API extern const struct YuvConstants kYvuH709Constants; // BT.709
LIBYUV_API extern const struct YuvConstants kYvuF709Constants; // BT.709 full
LIBYUV_API extern const struct YuvConstants kYvu2020Constants; // BT.2020
LIBYUV_API extern const struct YuvConstants kYvuV2020Constants; // BT.2020 full
// 4、NV12ToRGB24Matrix + 自由选择转换标准进行转换
// 4.1、NV12 To BGRHWC
libyuv::NV12ToRGB24Matrix(pu8DstY, s32Width, pu8DstUV, s32Width,
bgr_hwc_img, s32Width * 3,
&libyuv::kYuvJPEGConstants, // BT601 FULL
s32Width, s32Height);
// 4.2、NV12 To RGBHWC:使用 NV21 接口函数
libyuv::NV21ToRGB24Matrix(pu8DstY, s32Width, pu8DstUV, s32Width,
bgr_hwc_img, s32Width * 3,
&libyuv::kYuvJPEGConstants, // BT601 FULL
s32Width, s32Height);
// 5、NV12ToRGB24Matrix + 自由选择转换标准进行转换
// 5.1、NV21 To BGRHWC
libyuv::NV21ToRGB24Matrix(pu8DstY, s32Width, pu8DstUV, s32Width,
bgr_hwc_img, s32Width * 3,
&libyuv::kYuvJPEGConstants, // BT601 FULL
s32Width, s32Height);
// 5.2、NV21 To RGBHWC:使用 NV12 接口函数
libyuv::NV12ToRGB24Matrix(pu8DstY, s32Width, pu8DstUV, s32Width,
bgr_hwc_img, s32Width * 3,
&libyuv::kYuvJPEGConstants, // BT601 FULL
s32Width, s32Height);
- NV12RoiScaleToRGB24
void NV12RoiScaleToRGB24(u8 *src_y, u8 *src_uv, s32 src_stride,
s32 *roi_x, s32 *roi_y, s32 *roi_w, s32 *roi_h,
u8 *dst_rgb24, s32 dst_w, s32 dst_h) {
// 裁剪的坐标 X 和 Y 必须是偶数,否则可能得到 NV21
// 裁剪的宽和高必须是偶数(2n*2n*1.5 = 6n2),正好是 6 的倍数(每四个 Y 对应一个 UV)
// TODO:可考虑使用结构体简化代码
*roi_x = (*roi_x % 2) ? (*roi_x - 1) : *roi_x;
*roi_y = (*roi_y % 2) ? (*roi_y - 1) : *roi_y;
*roi_w = (*roi_w % 2) ? (*roi_w - 1) : *roi_w;
*roi_h = (*roi_h % 2) ? (*roi_h - 1) : *roi_h;
// 取得 SRC YUV 首地址
u8 *src_roi_y = (u8 *) (src_y + src_stride * (*roi_y) + (*roi_x));
// NV12 在竖直方向上进行了 1/2 下采样,水平方向上并未做下采样,所以只需 roi_y 减半
uint16_t *src_roi_uv = (uint16_t *) (src_uv + src_stride * (*roi_y) / 2 + (*roi_x));
// 开辟缩放中间结果内存(NV12),TODO:可考虑通过参数传入,Open 的时候开辟
u8 *dst_tmp_buffer = (u8 *) calloc(1, dst_w * dst_h * 1.5); // H*WC,BGR888
u8 *dst_y = dst_tmp_buffer;
u8 *dst_uv = dst_tmp_buffer + dst_w * dst_h;
libyuv::ScalePlane(src_roi_y, src_stride, *roi_w, *roi_h, dst_y, dst_w, dst_w, dst_h, libyuv::kFilterBilinear);
libyuv::ScalePlane_16(src_roi_uv, src_stride / 2, (*roi_w) / 2, (*roi_h) / 2, (u16 *) dst_uv, dst_w / 2,
dst_w / 2, dst_h / 2, libyuv::kFilterNone);
libyuv::NV12ToRGB24(dst_y, dst_w, dst_uv, dst_w, dst_rgb24, dst_w * 3, dst_w, dst_h);
if (dst_tmp_buffer != NULL) {
free(dst_tmp_buffer);
dst_tmp_buffer = NULL;
}
}
2.1.2、BGR/RGB 转 NV12/NV21
- 注意设置
flag_hwc
#define ROUND(f) static_cast<int>(f + 0.5f)
static int RoundToByte(float f)
{
int i = ROUND(f);
return (i < 0) ? 0 : ((i > 255) ? 255 : i);
}
static void BGRToNV12(u8 *src, int src_stride, u8 *dst_y, u8 *dst_uv, int dst_stride, int width, int height, int flag_hwc = 1)
{
int b, g, r;
for (int i = 0; i < height; i++)
{
for (int j = 0; j < width; j++)
{
if (flag_hwc)
{
b = src[i * src_stride * 3 + j * 3 + 0];
g = src[i * src_stride * 3 + j * 3 + 1];
r = src[i * src_stride * 3 + j * 3 + 2];
}
else
{
b = src[(i + height * 0) * src_stride + j];
g = src[(i + height * 1) * src_stride + j];
r = src[(i + height * 2) * src_stride + j];
}
// BT.601 limited range RGB to YUV
dst_y[i * dst_stride + j] = RoundToByte(0.257 * r + 0.504 * g + 0.098 * b + 16);
// i 和 j 均为奇数的时候
if ((i % 2) && (j % 2))
{
dst_uv[i / 2 * dst_stride + j - 1] = RoundToByte(-0.148 * r - 0.291 * g + 0.439 * b + 128); // U 分量
dst_uv[i / 2 * dst_stride + j] = RoundToByte(0.439 * r - 0.368 * g - 0.071 * b + 128); // V 分量
}
}
}
}
static void RGBToNV12(u8 *src, int src_stride, u8 *dst_y, u8 *dst_uv, int dst_stride, int width, int height, int flag_hwc = 1)
{
int b, g, r;
for (int i = 0; i < height; i++)
{
for (int j = 0; j < width; j++)
{
if (flag_hwc)
{
r = src[i * src_stride * 3 + j * 3 + 0];
g = src[i * src_stride * 3 + j * 3 + 1];
b = src[i * src_stride * 3 + j * 3 + 2];
}
else
{
r = src[(i + height * 0) * src_stride + j];
g = src[(i + height * 1) * src_stride + j];
b = src[(i + height * 2) * src_stride + j];
}
// BT.601 limited range RGB to YUV
dst_y[i * dst_stride + j] = RoundToByte(0.257 * r + 0.504 * g + 0.098 * b + 16);
// i 和 j 均为奇数的时候
if ((i % 2) && (j % 2))
{
dst_uv[i / 2 * dst_stride + j - 1] = RoundToByte(-0.148 * r - 0.291 * g + 0.439 * b + 128); // U 分量
dst_uv[i / 2 * dst_stride + j] = RoundToByte(0.439 * r - 0.368 * g - 0.071 * b + 128); // V 分量
}
}
}
}
static void BGRToNV21(u8 *src, int src_stride, u8 *dst_y, u8 *dst_uv, int dst_stride, int width, int height, int flag_hwc = 1)
{
int b, g, r;
for (int i = 0; i < height; i++)
{
for (int j = 0; j < width; j++)
{
if (flag_hwc)
{
b = src[i * src_stride * 3 + j * 3 + 0];
g = src[i * src_stride * 3 + j * 3 + 1];
r = src[i * src_stride * 3 + j * 3 + 2];
}
else
{
b = src[(i + height * 0) * src_stride + j];
g = src[(i + height * 1) * src_stride + j];
r = src[(i + height * 2) * src_stride + j];
}
// BT.601 limited range RGB to YUV
dst_y[i * dst_stride + j] = RoundToByte(0.257 * r + 0.504 * g + 0.098 * b + 16);
// i 和 j 均为奇数的时候
if ((i % 2) && (j % 2))
{
dst_uv[i / 2 * dst_stride + j - 1] = RoundToByte(0.439 * r - 0.368 * g - 0.071 * b + 128); // V 分量
dst_uv[i / 2 * dst_stride + j] = RoundToByte(-0.148 * r - 0.291 * g + 0.439 * b + 128); // U 分量
}
}
}
}
static void RGBToNV21(u8 *src, int src_stride, u8 *dst_y, u8 *dst_uv, int dst_stride, int width, int height, int flag_hwc = 1)
{
int b, g, r;
for (int i = 0; i < height; i++)
{
for (int j = 0; j < width; j++)
{
if (flag_hwc)
{
r = src[i * src_stride * 3 + j * 3 + 0];
g = src[i * src_stride * 3 + j * 3 + 1];
b = src[i * src_stride * 3 + j * 3 + 2];
}
else
{
r = src[(i + height * 0) * src_stride + j];
g = src[(i + height * 1) * src_stride + j];
b = src[(i + height * 2) * src_stride + j];
}
// BT.601 limited range RGB to YUV
dst_y[i * dst_stride + j] = RoundToByte(0.257 * r + 0.504 * g + 0.098 * b + 16);
// i 和 j 均为奇数的时候
if ((i % 2) && (j % 2))
{
dst_uv[i / 2 * dst_stride + j - 1] = RoundToByte(0.439 * r - 0.368 * g - 0.071 * b + 128); // V 分量
dst_uv[i / 2 * dst_stride + j] = RoundToByte(-0.148 * r - 0.291 * g + 0.439 * b + 128); // U 分量
}
}
}
}
- BGRHWCToNV12
static void BGRHWCToNV12(uint8_t *src_bgr, uint32_t src_stride_bgr, uint8_t *dst_y, uint32_t dst_stride_y,
uint8_t *dst_uv, uint32_t dst_stride_uv, uint32_t width, uint32_t height, int32_t flag_nv12) {
uint8_t *pu8DstY = dst_y;
uint8_t *pu8DstU = dst_uv;
uint8_t *pu8Srcbgr = src_bgr;
#ifdef _ARM_NEON_
uint8x8x3_t u883RGB;
uint8x8x2_t u882UV;
uint8x8_t u8x8Y, u8x8UV;
for (int32_t i = 0; i < height; i++)
{
for (int32_t j = 0; j < src_stride_bgr * 3; j += 24)
{
u883RGB = vld3_u8(pu8Srcbgr + i * src_stride_bgr * 3 + j); // 一次读取3 * 8个u8数据
uint16x8_t u16x8_B = vmulq_n_u16(vmovl_u8(u883RGB.val[0]), 29); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_G = vmulq_n_u16(vmovl_u8(u883RGB.val[1]), 150); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_R = vmulq_n_u16(vmovl_u8(u883RGB.val[2]), 74); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_Y = vaddq_u16(vaddq_u16(u16x8_B, u16x8_G), u16x8_R); // 74 * r + 150 * g + 29 * b
u8x8Y = vmin_u8(vmax_u8(vmovn_u16(vshrq_n_u16(u16x8_Y, 8)), vdup_n_u8(0)), vdup_n_u8(255));
vst1_u8(pu8DstY + j / 3, u8x8Y); // Y
if ((i % 2))
{
uint16x8_t u16x8_B1 = vmulq_n_u16(vmovl_u8(u883RGB.val[0]), 128); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_G1 = vmulq_n_u16(vmovl_u8(u883RGB.val[1]), 84); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_R1 = vmulq_n_u16(vmovl_u8(u883RGB.val[2]), 43); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_U = vsubq_u16(vsubq_u16(u16x8_B1, u16x8_G1), u16x8_R1); // -43 * r - 84 * g + 128 * b
// u8x8U = vmovn_u16(vshrq_n_u16(u16x8_U, 8));
uint16x8_t u16x8_B2 = vmulq_n_u16(vmovl_u8(u883RGB.val[0]), 21); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_G2 = vmulq_n_u16(vmovl_u8(u883RGB.val[1]), 107); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_R2 = vmulq_n_u16(vmovl_u8(u883RGB.val[2]), 128); // 一次读取8 x 2 个 uint8的数据,并强制转换成uint16
uint16x8_t u16x8_V = vsubq_u16(vsubq_u16(u16x8_R2, u16x8_G2), u16x8_B2); // 128 * r - 107 * g - 21 * b
// u8x8V = vmovn_u16(vshrq_n_u16(u16x8_V, 8));
if (flag_nv12)
{ // nv12
u882UV = vtrn_u8(vmovn_u16(vshrq_n_u16(u16x8_U, 8)), vmovn_u16(vshrq_n_u16(u16x8_V, 8)));
}
else
{ // nv21
u882UV = vtrn_u8(vmovn_u16(vshrq_n_u16(u16x8_V, 8)), vmovn_u16(vshrq_n_u16(u16x8_U, 8)));
}
u8x8UV = vmin_u8(vmax_u8(vadd_u8(u882UV.val[0], vdup_n_u8(128)), vdup_n_u8(0)), vdup_n_u8(255));
vst1_u8(pu8DstU + j / 3, u8x8UV); // UV
}
}
int32_t num = src_stride_bgr / 8;
int32_t rest = src_stride_bgr % 8;
for (int32_t j = 0; j < rest; j++)
{
int32_t b = pu8Srcbgr[i * src_stride_bgr * 3 + num * 3 * 8 + j * 3];
int32_t g = pu8Srcbgr[i * src_stride_bgr * 3 + num * 3 * 8 + j * 3 + 1];
int32_t r = pu8Srcbgr[i * src_stride_bgr * 3 + num * 3 * 8 + j * 3 + 2];
int32_t y = ((74 * r + 150 * g + 29 * b) >> 8); // 0-255, BT601 FULL
pu8DstY[i * dst_stride_y + num * 8 + j] = (y < 0) ? 0 : ((y > 255) ? 255 : y);
if ((i % 2) && (j % 2))
{
int32_t u = ((-43 * r - 84 * g + 128 * b) >> 8) + 128; // 0-255
int32_t v = ((128 * r - 107 * g - 21 * b) >> 8) + 128; // 0-255
if (flag_nv12)
{
pu8DstU[i / 2 * dst_stride_uv + num * 8 + j - 1] = (u < 0) ? 0 : ((u > 255) ? 255 : u); // NV12
pu8DstU[i / 2 * dst_stride_uv + num * 8 + j] = (v < 0) ? 0 : ((v > 255) ? 255 : v);
}
else
{
pu8DstU[i / 2 * dst_stride_uv + num * 8 + j - 1] = (v < 0) ? 0 : ((v > 255) ? 255 : v); // NV21
pu8DstU[i / 2 * dst_stride_uv + num * 8 + j] = (u < 0) ? 0 : ((u > 255) ? 255 : u);
}
}
}
pu8DstY += dst_stride_y;
if ((i % 2))
{
pu8DstU += dst_stride_uv;
}
}
#else
int32_t i, j;
int32_t b, g, r, y, u, v;
for (i = 0; i < height; i++) {
for (j = 0; j < width; j++) {
b = pu8Srcbgr[i * src_stride_bgr * 3 + j * 3];
g = pu8Srcbgr[i * src_stride_bgr * 3 + j * 3 + 1];
r = pu8Srcbgr[i * src_stride_bgr * 3 + j * 3 + 2];
y = ((74 * r + 150 * g + 29 * b) >> 8); // 0-255, BT601 FULL
pu8DstY[i * dst_stride_y + j] = (y < 0) ? 0 : ((y > 255) ? 255 : y);
if ((i % 2) && (j % 2)) {
u = ((-43 * r - 84 * g + 128 * b) >> 8) + 128; // 0-255
v = ((128 * r - 107 * g - 21 * b) >> 8) + 128; // 0-255
if (flag_nv12) {
pu8DstU[i / 2 * dst_stride_uv + j - 1] = (u < 0) ? 0 : ((u > 255) ? 255 : u); // NV12
pu8DstU[i / 2 * dst_stride_uv + j] = (v < 0) ? 0 : ((v > 255) ? 255 : v);
} else {
pu8DstU[i / 2 * dst_stride_uv + j - 1] = (v < 0) ? 0 : ((v > 255) ? 255 : v); // NV21
pu8DstU[i / 2 * dst_stride_uv + j] = (u < 0) ? 0 : ((u > 255) ? 255 : u);
}
}
}
}
#endif
}
2.2、YUV422(NV16、NV61、I422、YV16、YUVY、VYUY、UYVY)
# NV16、NV61 的存储格式为 Y 平面,UV 打包一个平面,共两个平面,即:先连续存储 Y,然后连续交叉存储 UV
# 不同点在于 UV 的排列顺序,SP 为 Semi-Planar 的缩写
# NV16:先是 w * h 长度的 Y,后面跟 w * h 长度的 UV(交叉存储),总长度为 w * h * 2
# NV61:先是 w * h 长度的 Y,后面跟 w * h 长度的 VU(交叉存储),总长度为 w * h * 2
NV16: YYYYYYYY UVUVUVUV => YUV422SP
NV61: YYYYYYYY VUVUVUVU => YUV422SP
# I422、YV16 三个分量均为平面格式,共三个平面,即:先连续存储 Y,然后连续存储 U,最后连续存储 V
# 不同点在于 U V 的排列顺序,P 为 Planar 的缩写
# I422:先是 w * h 长度的 Y,后面跟 w * h * 0.5 长度的 U, 最后是 w * h * 0.5 长度的 V,总长度为 w * h * 2
# YV16:先是 w * h 长度的 Y,后面跟 w * h * 0.5 长度的 V, 最后是 w * h * 0.5 长度的 U,总长度为 w * h * 2
I422: YYYYYYYY UUUU VVVV => YUV422P
YV16: YYYYYYYY VVVV UUUU => YUV422P
# YUVY、VYUY、UYVY 为打包格式:每个像素点的 Y,U,V 是连续交叉存储
# YUVY:在 Packed 内部,YUV 的排列顺序是 YUVY,两个 Y 共用一组 UV
# VYUY:在 Packed 内部,YUV 的排列顺序是 VYUY,两个 Y 共用一组 UV
# UYVY:在 Packed 内部,YUV 的排列顺序是 UYVY,两个 Y 共用一组 UV
YUVY: YUVY YUVY YUVY YUVY => YUV422
VYUY: VYUY VYUY VYUY VYUY => YUV422
UYVY: UYVY UYVY UYVY UYVY => YUV422
2.3、YUV444(I444、YV24)
# I444、YV24三个分量均为平面格式,共三个平面,即:先连续存储 Y,然后连续存储 U,最后连续存储 V
# 不同点在于 U V 的排列顺序,P 为 Planar 的缩写
# I444:先是 w * h 长度的 Y,后面跟 w * h 长度的 U, 最后是 w * h 长度的 V,总长度为 w * h * 3
# YV24:先是 w * h 长度的 Y,后面跟 w * h 长度的 V, 最后是 w * h 长度的 U,总长度为 w * h * 3
I444: YYYYYYYY UUUUUUUU VVVVVVVV => YUV444
YV24: YYYYYYYY VVVVVVVV UUUUUUUU => YUV444
NV12 转 I444
void NV12_to_I444(uint8_t* nv12data, uint8_t* i444data, int frameWidth, int frameHeight) {
uint8_t* nv12_src[2];
nv12_src[0] = nv12data;
nv12_src[1] = nv12_src[0] + frameWidth * frameHeight;
uint8_t* yuv444_dst[3];
yuv444_dst[0] = i444data;
yuv444_dst[1] = yuv444_dst[0] + frameWidth * frameHeight;
yuv444_dst[2] = yuv444_dst[1] + frameWidth * frameHeight;
// Y
memcpy(yuv444_dst[0], nv12_src[0], frameWidth * frameHeight);
// UV
for (int i = 0; i < frameWidth * frameHeight / 2; i++) {
if (i % 2 == 0) {// U,NV12中一位对应444中4位
*(yuv444_dst[1]) = *(nv12_src[1] + i);
*(yuv444_dst[1] + frameWidth) = *(nv12_src[1] + i);
yuv444_dst[1]++;
*(yuv444_dst[1]) = *(nv12_src[1] + i);
*(yuv444_dst[1] + frameWidth) = *(nv12_src[1] + i);
yuv444_dst[1]++;
}
else {// V,NV12中一位对应444中4位
*(yuv444_dst[2]) = *(nv12_src[1] + i);
*(yuv444_dst[2] + frameWidth) = *(nv12_src[1] + i);
yuv444_dst[2]++;
*(yuv444_dst[2]) = *(nv12_src[1] + i);
*(yuv444_dst[2] + frameWidth) = *(nv12_src[1] + i);
yuv444_dst[2]++;
}
if ((i > frameWidth && i % frameWidth == 0)) { // UV 分量跳行
yuv444_dst[1] = yuv444_dst[1] + frameWidth;
yuv444_dst[2] = yuv444_dst[2] + frameWidth;
}
}
}
// 使用 libyuv 实现,NV12ToI420 或 NV21ToI420
libyuv::NV12ToI420(ptr_tmp_y, s32width, (uint8_t*)ptr_tmp_uv, s32width , ptr_tmpI420_y, s32width,
ptr_tmpI420_u, s32width/2, ptr_tmpI420_v, s32width/2 ,s32width, s32height );
libyuv::I420ToI444(ptr_tmpI420_y, s32width, ptr_tmpI420_u, s32width / 2, ptr_tmpI420_v , s32width / 2,
ptr_tmpI444_y, s32width, ptr_tmpI444_u, s32width, ptr_tmpI444_v, s32width, s32width, s32height );
NV12 转 I444 同时进行缩放
/*====================================================================
函数名 : UtiBilinearResizeRoiOneChannel
功能 : 采用双线性插值的方法将单通道图像的Roi区域进行缩放
算法实现 :
引用全局变量: 无
输入参数说明: u8 *pu8SrcImage : 源图像地址[in]
u8 *pu8DstImage : 目的图像的地址[out]
tRectIn : 源图像的ROI框[in]
u32SrcStride : 源图像的步进值[in]
u32DstWidth : 目的图像的宽度[in]
u32DstHeight : 目的图像的高度[in]
u32DstStride : 目的图像的步进值[in]
返回值说明 : 无
====================================================================*/
void UtiBilinearResizeRoiOneChannel(u8 *pu8SrcImage, u8 *pu8DstImage, TRect tRectIn, u32 u32SrcStride, u32 u32DstWidth, u32 u32DstHeight, u32 u32DstStride)
{
u8 *pu8SrcLine1 = NULL;
u8 *pu8SrcLine2 = NULL;
u8 *pu8Dst = NULL;
u32 u32WY1, u32WY2;
u32 u32WX1, u32WX2;
u32 u32XPosition, u32YPosition;
u32 u32XSrc, u32YSrc;
u32 u32XStride, u32YStride;
u32 u32Vn0, u32Vn1;
u32 u32RowIndex;
u32 u32LineIndex;
u32 u32YPositionInit = 0;
u32 u32XPositionInit = 0;
u32 u32SrcXOffset = tRectIn.l32Left;
u32 u32SrcYOffset = tRectIn.l32Top;
u32 u32SrcWidth = tRectIn.l32Width;
u32 u32SrcHeight = tRectIn.l32Height;
u32XStride = ((u32SrcWidth - 1) << 16) / (u32DstWidth - 1);//pow(2,16)*Src_width/Dst_width
u32YStride = ((u32SrcHeight - 1) << 16) / (u32DstHeight - 1);//pow(2,16)*Src_height/Dst_height
//判断是否需要进行起始点偏移
if(0 == ((u32XStride << 16) >> 27))
{
u32XStride = ((u32SrcWidth - 2) << 16) / (u32DstWidth - 1);//pow(2,16)*Src_width/Dst_width
u32XPositionInit = 1 << 15;
}
if(0 == ((u32YStride << 16) >> 27))
{
u32YStride = ((u32SrcHeight - 2) << 16) / (u32DstHeight - 1);//pow(2,16)*Src_height/Dst_height
u32YPositionInit = 1 << 15;
}
//按起始坐标偏移
u32YPosition = u32YPositionInit + (u32SrcYOffset << 16);
for(u32RowIndex = 0; u32RowIndex < u32DstHeight; u32RowIndex++)
{
u32YSrc = u32YPosition >> 16;
//垂直方向权值
u32WY2 = (u32YPosition << 16) >> 29;
u32WY1 = 8 - u32WY2;
//放大权值以利用_dotprsu2指令右移16位特点
u32WY2 *= 1024;
u32WY1 *= 1024;
pu8SrcLine1 = pu8SrcImage + u32YSrc * u32SrcStride;
pu8SrcLine2 = u32WY2 == 0 ? pu8SrcLine1 : pu8SrcLine1 + u32SrcStride; //在最后一行的时候,读的数据是不参与运算的,但VC不允许越界读,因此这里加判断防止读越界
pu8Dst = pu8DstImage + u32RowIndex * u32DstStride;//u32DstWidth;
//按起始坐标偏移
u32XPosition = u32XPositionInit + (u32SrcXOffset << 16);
for(u32LineIndex = 0; u32LineIndex < u32DstWidth; u32LineIndex++)
{
//定点数的高16位就是整数部分
u32XSrc = u32XPosition >> 16;
//定点数的低16位就是小数部分,我们使用其高3位作为权值(范围0-8)
u32WX2 = (u32XPosition << 16) >> 29;
u32WX1 = 8 - u32WX2;
//水平线性滤波--下面的操作对应于_dotpu4指令
u32Vn0 = pu8SrcLine1[u32XSrc] * u32WX1 + pu8SrcLine1[u32XSrc + 1] * u32WX2;
u32Vn1 = pu8SrcLine2[u32XSrc] * u32WX1 + pu8SrcLine2[u32XSrc + 1] * u32WX2;
//垂直线性滤波--下面的操作对应于_dotprsu2指令
*pu8Dst++ = (u8)((u32Vn0 * u32WY1 + u32Vn1 * u32WY2 + 0x8000) >> 16);
u32XPosition += u32XStride;
}
u32YPosition += u32YStride;
}
}
/*====================================================================
函数名 : UtiBilinearResizeRoiTwoChannel
功能 : 采用双线性插值的方法将交织的两通道图像的Roi区域进行分通道缩放,如uv数据
算法实现 :
引用全局变量: 无
输入参数说明: u8 *pu8SrcData : 源图像地址[in]
u8 *pu8DstChn1 : 目的图像的地址[out]
u8 *pu8DstChn2 : 目的图像的地址[out]
tRectIn : 源图像的ROI框[in]
u32SrcStride : 源图像的步进值[in]
u32DstWidth : 目的图像的宽度[in]
u32DstHeight : 目的图像的高度[in]
u32DstStride : 目的图像的步进值[in]
返回值说明 : 无
====================================================================*/
void UtiBilinearResizeRoiTwoChannel(u8 *pu8SrcData, u8 *pu8DstChn1, u8 *pu8DstChn2, TRect tRect, u32 u32SrcStride, u32 u32DstWidth, u32 u32DstHeight, u32 u32DstStride)
{
u8 *pu8SrcLine1 = NULL;
u8 *pu8SrcLine2 = NULL;
u8 *pu8DstChn1Tmp = NULL;
u8 *pu8DstChn2Tmp = NULL;
u32 u32WY1, u32WY2;
u32 u32WX1, u32WX2;
u32 u32XPosition, u32YPosition;
u32 u32XSrc, u32YSrc;
u32 u32XStride, u32YStride;
u32 u32Vn0, u32Vn1;
u32 u32RowIndex;
u32 u32LineIndex;
u32 u32YPositionInit = 0;
u32 u32XPositionInit = 0;
u32 u32SrcXOffset = tRect.l32Left;
u32 u32SrcYOffset = tRect.l32Top;
u32 u32SrcWidth = tRect.l32Width;
u32 u32SrcHeight = tRect.l32Height;
u32XStride = ((u32SrcWidth - 1) << 16) / (u32DstWidth - 1);//pow(2,16)*Src_width/Dst_width
u32YStride = ((u32SrcHeight - 1) << 16) / (u32DstHeight - 1);//pow(2,16)*Src_height/Dst_height
//判断是否需要进行起始点偏移
if(0 == ((u32XStride << 16) >> 27))
{
u32XStride = ((u32SrcWidth - 2) << 16) / (u32DstWidth - 1);//pow(2,16)*Src_width/Dst_width
u32XPositionInit = 1 << 15;
}
if(0 == ((u32YStride << 16) >> 27))
{
u32YStride = ((u32SrcHeight - 2) << 16) / (u32DstHeight - 1);//pow(2,16)*Src_height/Dst_height
u32YPositionInit = 1 << 15;
}
//按起始坐标偏移
u32YPosition = u32YPositionInit + (u32SrcYOffset << 16);
for(u32RowIndex = 0; u32RowIndex < u32DstHeight; u32RowIndex++)
{
u32YSrc = u32YPosition >> 16;
//垂直方向权值
u32WY2 = (u32YPosition << 16) >> 29;
u32WY1 = 8 - u32WY2;
//放大权值以利用_dotprsu2指令右移16位特点
u32WY2 *= 1024;
u32WY1 *= 1024;
pu8SrcLine1 = pu8SrcData + u32YSrc * u32SrcStride;
pu8SrcLine2 = u32WY2 == 0 ? pu8SrcLine1 : pu8SrcLine1 + u32SrcStride; //在最后一行的时候,读的数据是不参与运算的,但VC不允许越界读,因此这里加判断防止读越界
pu8DstChn1Tmp = pu8DstChn1 + (u32RowIndex)* u32DstStride;
pu8DstChn2Tmp = pu8DstChn2 + (u32RowIndex)* u32DstStride;
//按起始坐标偏移
u32XPosition = u32XPositionInit + (u32SrcXOffset << 16);
for(u32LineIndex = 0; u32LineIndex < u32DstWidth; u32LineIndex++)
{
//定点数的高16位就是整数部分
u32XSrc = u32XPosition >> 16;
u32XSrc *= 2;
//定点数的低16位就是小数部分,我们使用其高3位作为权值(范围0-8)
u32WX2 = (u32XPosition << 16) >> 29;
u32WX1 = 8 - u32WX2;
//水平线性滤波--下面的操作对应于_dotpu4指令
u32Vn0 = pu8SrcLine1[u32XSrc] * u32WX1 + pu8SrcLine1[u32XSrc + 2] * u32WX2;
u32Vn1 = pu8SrcLine2[u32XSrc] * u32WX1 + pu8SrcLine2[u32XSrc + 2] * u32WX2;
//垂直线性滤波--下面的操作对应于_dotprsu2指令
*pu8DstChn1Tmp++ = (u8)((u32Vn0 * u32WY1 + u32Vn1 * u32WY2 + 0x8000) >> 16);
//水平线性滤波--下面的操作对应于_dotpu4指令
u32Vn0 = pu8SrcLine1[u32XSrc + 1] * u32WX1 + pu8SrcLine1[u32XSrc + 3] * u32WX2;
u32Vn1 = pu8SrcLine2[u32XSrc + 1] * u32WX1 + pu8SrcLine2[u32XSrc + 3] * u32WX2;
//垂直线性滤波--下面的操作对应于_dotprsu2指令
*pu8DstChn2Tmp++ = (u8)((u32Vn0 * u32WY1 + u32Vn1 * u32WY2 + 0x8000) >> 16);
u32XPosition += u32XStride;
}
u32YPosition += u32YStride;
}
}
/*====================================================================
函数名 : UtiBilinearResizeRoiNV12ToYUV444
功能 : 输入图像NV12转Y4444,同时转类型和缩放
算法实现 :
引用全局变量: 无
输入参数说明: ptSrcImg: 源图像[in]
ptDstImg : 目的图像(Y444格式的YUV)[out]
tRect: 源图待转区域
返回值说明 : -1 缩放失败 0 缩放成功
====================================================================*/
static l32 UtiBilinearResizeRoiNV12ToYUV444(TImage *ptSrcImg, TImage *ptDstImg, TRect tRectIn)
{
u8 *pu8SrcY = NULL;
u8 *pu8SrcU = NULL;
u8 *pu8SrcV = NULL;
u8 *pu8DstY = NULL;
u8 *pu8DstU = NULL;
u8 *pu8DstV = NULL;
u8 *pu8SrcUV = NULL;
l32 l32SrcImgStride;
l32 l32SrcWidth = ptSrcImg->atPlane[0].l32Width;
l32 l32SrcHeight = ptSrcImg->atPlane[0].l32Height;
l32 l32SrcStride = ptSrcImg->atPlane[0].l32Stride;
l32 l32DstWidth = ptDstImg->atPlane[0].l32Width;
l32 l32DstHeight = ptDstImg->atPlane[0].l32Height;
l32 l32DstStride = ptDstImg->atPlane[0].l32Stride;
TRect tRectInTmp;
//参数检查
if(AI_NV12 != ptSrcImg->u32Type)
{
printf("The src image type is not supported in UtiBilinearResizeRoiNV12ToYUV444!\n");
return -1;
}
//如果输入框的宽高为0,则默认是全图
if(tRectIn.l32Width == 0 || tRectIn.l32Height == 0)
{
tRectIn.l32Left = 0;
tRectIn.l32Top = 0;
tRectIn.l32Width = ptSrcImg->atPlane[0].l32Width;
tRectIn.l32Height = ptSrcImg->atPlane[0].l32Height;
}
//保证起始点对应uv的正确位置和长宽是偶数
tRectInTmp.l32Left = (tRectIn.l32Left >> 1) << 1;
tRectInTmp.l32Top = (tRectIn.l32Top >> 1) << 1;
tRectInTmp.l32Width = (tRectIn.l32Width >> 1) << 1;
tRectInTmp.l32Height = (tRectIn.l32Height >> 1) << 1;
l32SrcImgStride = ptSrcImg->atPlane[0].l32Stride;
//源图像
pu8SrcY = (u8 *)ptSrcImg->atPlane[0].pvBuffer;
pu8SrcUV = (u8 *)ptSrcImg->atPlane[1].pvBuffer;
//目的图像
pu8DstY = (u8 *)ptDstImg->atPlane[0].pvBuffer;
pu8DstU = (u8 *)ptDstImg->atPlane[1].pvBuffer;
pu8DstV = (u8 *)ptDstImg->atPlane[2].pvBuffer;
//Y分量
UtiBilinearResizeRoiOneChannel(pu8SrcY, pu8DstY, tRectInTmp, l32SrcImgStride, l32DstWidth, l32DstHeight, l32DstWidth);
//UV分量
tRectInTmp.l32Left = tRectInTmp.l32Left >> 1;
tRectInTmp.l32Top = tRectInTmp.l32Top >> 1;
tRectInTmp.l32Width = tRectInTmp.l32Width >> 1;
tRectInTmp.l32Height = tRectInTmp.l32Height >> 1;
l32SrcImgStride = ptSrcImg->atPlane[1].l32Stride;
UtiBilinearResizeRoiTwoChannel(pu8SrcUV, pu8DstU, pu8DstV, tRectInTmp, l32SrcImgStride, l32DstWidth, l32DstHeight, l32DstWidth);
return 0;
}
RGB2I444
def round2byte(f):
f = np.round(f)
f = np.where(f < 0, 0, f)
f = np.where(f > 255, 255, f)
return f.astype(np.uint8)
# 训练的时候可以考虑用不同的标准 BT601/BT601FULL/BT709/BT709FULL/BT2020/BT2020FULL
def rgb2i444(img_rgb_resized):
h, w = img_rgb_resized.shape[:2]
img_i444 = np.zeros((h, w, 3), dtype=np.uint8)
img_i444[:, :, 0] = round2byte(np.sum(img_rgb_resized * np.array([0.257, 0.504, 0.098]), axis=2) + 16)
img_i444[:, :, 1] = round2byte(np.sum(img_rgb_resized * np.array([-0.148, -0.291, 0.439]), axis=2) + 128)
img_i444[:, :, 2] = round2byte(np.sum(img_rgb_resized * np.array([0.439, -0.368, -0.071]), axis=2) + 128)
return img_i444
三、常用视频分辨率及码率、帧率介绍
- 常用视频分辨率(w*h):
720P(1280*720):
表示视频有 720 行像素(height),大约 100w 像素,P(Progressive 的缩写)本身表示的是逐行扫描
1080P(1920*1080):
表示视频有 1080 行像素(height),大约 200w 像素2K(2048*1080):
表示视频有2048(2*2^10=2K)
列的像素数(width),大约 200w 像素,最常见的是影院级别的 2K,其它还有2048×1536(QXGA)2560×1600(WQXGA),2560×1440(Quad HD)
等4K(3840*2160/4096*2160):
表示视频有4096(4*2^10=4K)
列的像素数(width),大约 800~900 w 像素
- 码流(Data Rate):
- 也叫码率,指的是视频文件在
单位时间内使用的数据流量
,对视频编码画面质量的控制起到重要作用 - 在同样分辨率下,视频文件码流越大,压缩比就越小,画面质量就越好
- 也叫码率,指的是视频文件在
- 帧率(fps):
- 指的是每秒钟传输图片的帧数,帧率越高,性能越好
- H.264 和 H.265 的区别:
- 均指视频编码的标准,H265 在保证清晰度的同时降低了码流,可以节约存储空间,同时降低了网络带宽
- 均指视频编码的标准,H265 在保证清晰度的同时降低了码流,可以节约存储空间,同时降低了网络带宽
四、读取 YUV(NV12) 视频文件并保存
- 1、使用 FFMPEG 工具实现:
- nv12 数据转 jpg:
.\ffmpeg.exe -y -s 1920x1080 -pix_fmt nv12 -i .\output\1_NV12.yuv .\output\1_NV12\image%d.jpg
- jpg 数据转 nv12:
.\ffmpeg.exe -s 1920x1080 -i .\input\image%d.jpg -pix_fmt nv12 test.yuv
- h265 数据转 nv12:
.\ffmpeg.exe -i .\input\1.h265 -s 1920x1080 -pix_fmt nv12 .\output\1_NV12.yuv
- nv12 数据转 h265:
.\ffmpeg.exe -video_size 1920x1080 -pix_fmt nv21 -i input.yuv -vcodec h265 output.h265
- imglist 转 mp4:
.\ffmpeg.exe -y -r 30 -f concat -safe 0 -i filelist.txt -b:v 4096000 -c:v libx264 -vf fps=30 -pix_fmt yuv420p out.mp4
- Note:ffmpeg 还有其它很强大的一些功能,如 imglist 转 mp4、yuv 转 h265 等等
- nv12 数据转 jpg:
- 2、python 代码实现如下:
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import cv2
import numpy as np
def yuv2bgr(file_name, height, width, start_frame):
"""
:param file_name: 待处理 YUV 视频的名字
:param height: YUV 视频中图像的高
:param width: YUV 视频中图像的宽
:param start_frame: 起始帧
:return: None
"""
fp = open(file_name, 'rb')
fp.seek(0, 2) # 设置文件指针到文件流的尾部 + 偏移 0
fp_end = fp.tell() # 获取文件尾指针位置
frame_size = height * width * 3 // 2 # 一帧图像所占用的内存字节数
num_frame = fp_end // frame_size # 计算 YUV 文件包含图像数
print("This yuv file has {} frame imgs!".format(num_frame))
fp.seek(frame_size * start_frame, 0) # 设置文件指针到文件流的起始位置 + 偏移 frame_size * startframe
print("Extract imgs start frame is {}!".format(start_frame + 1))
for i in range(num_frame - start_frame):
yyyy_uv = np.zeros(shape=frame_size, dtype='uint8', order='C')
for j in range(frame_size):
yyyy_uv[j] = ord(fp.read(1)) # 读取 YUV 数据,并转换为 unicode
img = yyyy_uv.reshape((height * 3 // 2, width)).astype('uint8') # NV12 的存储格式为:YYYY UV 分布在两个平面(其在内存中为 1 维)
bgr_img = cv2.cvtColor(img, cv2.COLOR_YUV2BGR_NV12) # 由于 opencv 不能直接读取 YUV 格式的文件, 所以要转换一下格式,支持的转换格式可参考资料 5
cv2.imwrite('yuv2bgr/{}.jpg'.format(i + 1), bgr_img) # 改变后缀即可实现不同格式图片的保存(jpg/bmp/png...)
print("Extract frame {}".format(i + 1))
fp.close()
print("job done!")
return None
if __name__ == '__main__':
yuv2bgr(filename='xxx.yuv', height=1080, width=1920, startfrm=0)
# BGR2NV21
def bgr2nv21(image_path, image_height, image_width):
bgr = cv2.imread(image_path)
B = []
G = []
R = []
YUV = []
for i in range(image_height):
for j in range(image_width):
B.append(bgr[i * image_width * 3 + j * 3])
G.append(bgr[i * image_width * 3 + j * 3 + 1])
R.append(bgr[i * image_width * 3 + j * 3 + 2])
y = ((74 * R + 150 * G + 29 * B) / 256)
u = ((-43 * R - 84 * G + 112 * B) / 255) + 128
v = ((128 * R - 107 * G - 21 * B) / 255) + 128
YUV[i * image_width + j] = min(max(y, 0), 255)
YUV[(i // 2 + image_height) * image_width + (j // 2) * 2] = min(max(v, 0), 255)
YUV[(i // 2 + image_height) * image_width + (j // 2) * 2 + 1] = min(max(u, 0), 255)
yuv_name = image_path.replace("png", "yuv")
np.tofile(yuv_name)
- 3、OpenCV 中支持的颜色转换如下所示(py opencv 只需把
cv::
换成cv.
即可):
enum cv::ColorConversionCodes {
cv::COLOR_BGR2BGRA = 0,
cv::COLOR_RGB2RGBA = COLOR_BGR2BGRA,
cv::COLOR_BGRA2BGR = 1,
cv::COLOR_RGBA2RGB = COLOR_BGRA2BGR,
cv::COLOR_BGR2RGBA = 2,
cv::COLOR_RGB2BGRA = COLOR_BGR2RGBA,
cv::COLOR_RGBA2BGR = 3,
cv::COLOR_BGRA2RGB = COLOR_RGBA2BGR,
cv::COLOR_BGR2RGB = 4,
cv::COLOR_RGB2BGR = COLOR_BGR2RGB,
cv::COLOR_BGRA2RGBA = 5,
cv::COLOR_RGBA2BGRA = COLOR_BGRA2RGBA,
cv::COLOR_BGR2GRAY = 6,
cv::COLOR_RGB2GRAY = 7,
cv::COLOR_GRAY2BGR = 8,
cv::COLOR_GRAY2RGB = COLOR_GRAY2BGR,
cv::COLOR_GRAY2BGRA = 9,
cv::COLOR_GRAY2RGBA = COLOR_GRAY2BGRA,
cv::COLOR_BGRA2GRAY = 10,
cv::COLOR_RGBA2GRAY = 11,
cv::COLOR_BGR2BGR565 = 12,
cv::COLOR_RGB2BGR565 = 13,
cv::COLOR_BGR5652BGR = 14,
cv::COLOR_BGR5652RGB = 15,
cv::COLOR_BGRA2BGR565 = 16,
cv::COLOR_RGBA2BGR565 = 17,
cv::COLOR_BGR5652BGRA = 18,
cv::COLOR_BGR5652RGBA = 19,
cv::COLOR_GRAY2BGR565 = 20,
cv::COLOR_BGR5652GRAY = 21,
cv::COLOR_BGR2BGR555 = 22,
cv::COLOR_RGB2BGR555 = 23,
cv::COLOR_BGR5552BGR = 24,
cv::COLOR_BGR5552RGB = 25,
cv::COLOR_BGRA2BGR555 = 26,
cv::COLOR_RGBA2BGR555 = 27,
cv::COLOR_BGR5552BGRA = 28,
cv::COLOR_BGR5552RGBA = 29,
cv::COLOR_GRAY2BGR555 = 30,
cv::COLOR_BGR5552GRAY = 31,
cv::COLOR_BGR2XYZ = 32,
cv::COLOR_RGB2XYZ = 33,
cv::COLOR_XYZ2BGR = 34,
cv::COLOR_XYZ2RGB = 35,
cv::COLOR_BGR2YCrCb = 36,
cv::COLOR_RGB2YCrCb = 37,
cv::COLOR_YCrCb2BGR = 38,
cv::COLOR_YCrCb2RGB = 39,
cv::COLOR_BGR2HSV = 40,
cv::COLOR_RGB2HSV = 41,
cv::COLOR_BGR2Lab = 44,
cv::COLOR_RGB2Lab = 45,
cv::COLOR_BGR2Luv = 50,
cv::COLOR_RGB2Luv = 51,
cv::COLOR_BGR2HLS = 52,
cv::COLOR_RGB2HLS = 53,
cv::COLOR_HSV2BGR = 54,
cv::COLOR_HSV2RGB = 55,
cv::COLOR_Lab2BGR = 56,
cv::COLOR_Lab2RGB = 57,
cv::COLOR_Luv2BGR = 58,
cv::COLOR_Luv2RGB = 59,
cv::COLOR_HLS2BGR = 60,
cv::COLOR_HLS2RGB = 61,
cv::COLOR_BGR2HSV_FULL = 66,
cv::COLOR_RGB2HSV_FULL = 67,
cv::COLOR_BGR2HLS_FULL = 68,
cv::COLOR_RGB2HLS_FULL = 69,
cv::COLOR_HSV2BGR_FULL = 70,
cv::COLOR_HSV2RGB_FULL = 71,
cv::COLOR_HLS2BGR_FULL = 72,
cv::COLOR_HLS2RGB_FULL = 73,
cv::COLOR_LBGR2Lab = 74,
cv::COLOR_LRGB2Lab = 75,
cv::COLOR_LBGR2Luv = 76,
cv::COLOR_LRGB2Luv = 77,
cv::COLOR_Lab2LBGR = 78,
cv::COLOR_Lab2LRGB = 79,
cv::COLOR_Luv2LBGR = 80,
cv::COLOR_Luv2LRGB = 81,
cv::COLOR_BGR2YUV = 82,
cv::COLOR_RGB2YUV = 83,
cv::COLOR_YUV2BGR = 84,
cv::COLOR_YUV2RGB = 85,
// YUV 4:2:0 formats family
cv::COLOR_YUV2RGB_NV12 = 90,
cv::COLOR_YUV2BGR_NV12 = 91,
cv::COLOR_YUV2RGB_NV21 = 92,
cv::COLOR_YUV2BGR_NV21 = 93,
cv::COLOR_YUV420sp2RGB = COLOR_YUV2RGB_NV21,
cv::COLOR_YUV420sp2BGR = COLOR_YUV2BGR_NV21,
cv::COLOR_YUV2RGBA_NV12 = 94,
cv::COLOR_YUV2BGRA_NV12 = 95,
cv::COLOR_YUV2RGBA_NV21 = 96,
cv::COLOR_YUV2BGRA_NV21 = 97,
cv::COLOR_YUV420sp2RGBA = COLOR_YUV2RGBA_NV21,
cv::COLOR_YUV420sp2BGRA = COLOR_YUV2BGRA_NV21,
cv::COLOR_YUV2RGB_YV12 = 98,
cv::COLOR_YUV2BGR_YV12 = 99,
cv::COLOR_YUV2RGB_IYUV = 100,
cv::COLOR_YUV2BGR_IYUV = 101,
cv::COLOR_YUV2RGB_I420 = COLOR_YUV2RGB_IYUV,
cv::COLOR_YUV2BGR_I420 = COLOR_YUV2BGR_IYUV,
cv::COLOR_YUV420p2RGB = COLOR_YUV2RGB_YV12,
cv::COLOR_YUV420p2BGR = COLOR_YUV2BGR_YV12,
cv::COLOR_YUV2RGBA_YV12 = 102,
cv::COLOR_YUV2BGRA_YV12 = 103,
cv::COLOR_YUV2RGBA_IYUV = 104,
cv::COLOR_YUV2BGRA_IYUV = 105,
cv::COLOR_YUV2RGBA_I420 = COLOR_YUV2RGBA_IYUV,
cv::COLOR_YUV2BGRA_I420 = COLOR_YUV2BGRA_IYUV,
cv::COLOR_YUV420p2RGBA = COLOR_YUV2RGBA_YV12,
cv::COLOR_YUV420p2BGRA = COLOR_YUV2BGRA_YV12,
cv::COLOR_YUV2GRAY_420 = 106,
cv::COLOR_YUV2GRAY_NV21 = COLOR_YUV2GRAY_420,
cv::COLOR_YUV2GRAY_NV12 = COLOR_YUV2GRAY_420,
cv::COLOR_YUV2GRAY_YV12 = COLOR_YUV2GRAY_420,
cv::COLOR_YUV2GRAY_IYUV = COLOR_YUV2GRAY_420,
cv::COLOR_YUV2GRAY_I420 = COLOR_YUV2GRAY_420,
cv::COLOR_YUV420sp2GRAY = COLOR_YUV2GRAY_420,
cv::COLOR_YUV420p2GRAY = COLOR_YUV2GRAY_420,
// YUV 4:2:2 formats family
cv::COLOR_YUV2RGB_UYVY = 107,
cv::COLOR_YUV2BGR_UYVY = 108,
cv::COLOR_YUV2RGB_Y422 = COLOR_YUV2RGB_UYVY,
cv::COLOR_YUV2BGR_Y422 = COLOR_YUV2BGR_UYVY,
cv::COLOR_YUV2RGB_UYNV = COLOR_YUV2RGB_UYVY,
cv::COLOR_YUV2BGR_UYNV = COLOR_YUV2BGR_UYVY,
cv::COLOR_YUV2RGBA_UYVY = 111,
cv::COLOR_YUV2BGRA_UYVY = 112,
cv::COLOR_YUV2RGBA_Y422 = COLOR_YUV2RGBA_UYVY,
cv::COLOR_YUV2BGRA_Y422 = COLOR_YUV2BGRA_UYVY,
cv::COLOR_YUV2RGBA_UYNV = COLOR_YUV2RGBA_UYVY,
cv::COLOR_YUV2BGRA_UYNV = COLOR_YUV2BGRA_UYVY,
cv::COLOR_YUV2RGB_YUY2 = 115,
cv::COLOR_YUV2BGR_YUY2 = 116,
cv::COLOR_YUV2RGB_YVYU = 117,
cv::COLOR_YUV2BGR_YVYU = 118,
cv::COLOR_YUV2RGB_YUYV = COLOR_YUV2RGB_YUY2,
cv::COLOR_YUV2BGR_YUYV = COLOR_YUV2BGR_YUY2,
cv::COLOR_YUV2RGB_YUNV = COLOR_YUV2RGB_YUY2,
cv::COLOR_YUV2BGR_YUNV = COLOR_YUV2BGR_YUY2,
cv::COLOR_YUV2RGBA_YUY2 = 119,
cv::COLOR_YUV2BGRA_YUY2 = 120,
cv::COLOR_YUV2RGBA_YVYU = 121,
cv::COLOR_YUV2BGRA_YVYU = 122,
cv::COLOR_YUV2RGBA_YUYV = COLOR_YUV2RGBA_YUY2,
cv::COLOR_YUV2BGRA_YUYV = COLOR_YUV2BGRA_YUY2,
cv::COLOR_YUV2RGBA_YUNV = COLOR_YUV2RGBA_YUY2,
cv::COLOR_YUV2BGRA_YUNV = COLOR_YUV2BGRA_YUY2,
cv::COLOR_YUV2GRAY_UYVY = 123,
cv::COLOR_YUV2GRAY_YUY2 = 124,
cv::COLOR_YUV2GRAY_Y422 = COLOR_YUV2GRAY_UYVY,
cv::COLOR_YUV2GRAY_UYNV = COLOR_YUV2GRAY_UYVY,
cv::COLOR_YUV2GRAY_YVYU = COLOR_YUV2GRAY_YUY2,
cv::COLOR_YUV2GRAY_YUYV = COLOR_YUV2GRAY_YUY2,
cv::COLOR_YUV2GRAY_YUNV = COLOR_YUV2GRAY_YUY2,
// alpha premultiplication
cv::COLOR_RGBA2mRGBA = 125,
cv::COLOR_mRGBA2RGBA = 126,
cv::COLOR_RGB2YUV_I420 = 127,
cv::COLOR_BGR2YUV_I420 = 128,
cv::COLOR_RGB2YUV_IYUV = COLOR_RGB2YUV_I420,
cv::COLOR_BGR2YUV_IYUV = COLOR_BGR2YUV_I420,
cv::COLOR_RGBA2YUV_I420 = 129,
cv::COLOR_BGRA2YUV_I420 = 130,
cv::COLOR_RGBA2YUV_IYUV = COLOR_RGBA2YUV_I420,
cv::COLOR_BGRA2YUV_IYUV = COLOR_BGRA2YUV_I420,
cv::COLOR_RGB2YUV_YV12 = 131,
cv::COLOR_BGR2YUV_YV12 = 132,
cv::COLOR_RGBA2YUV_YV12 = 133,
cv::COLOR_BGRA2YUV_YV12 = 134,
cv::COLOR_BayerBG2BGR = 46,
cv::COLOR_BayerGB2BGR = 47,
cv::COLOR_BayerRG2BGR = 48,
cv::COLOR_BayerGR2BGR = 49,
cv::COLOR_BayerBG2RGB = COLOR_BayerRG2BGR,
cv::COLOR_BayerGB2RGB = COLOR_BayerGR2BGR,
cv::COLOR_BayerRG2RGB = COLOR_BayerBG2BGR,
cv::COLOR_BayerGR2RGB = COLOR_BayerGB2BGR,
cv::COLOR_BayerBG2GRAY = 86,
cv::COLOR_BayerGB2GRAY = 87,
cv::COLOR_BayerRG2GRAY = 88,
cv::COLOR_BayerGR2GRAY = 89,
cv::COLOR_BayerBG2BGR_VNG = 62,
cv::COLOR_BayerGB2BGR_VNG = 63,
cv::COLOR_BayerRG2BGR_VNG = 64,
cv::COLOR_BayerGR2BGR_VNG = 65,
cv::COLOR_BayerBG2RGB_VNG = COLOR_BayerRG2BGR_VNG,
cv::COLOR_BayerGB2RGB_VNG = COLOR_BayerGR2BGR_VNG,
cv::COLOR_BayerRG2RGB_VNG = COLOR_BayerBG2BGR_VNG,
cv::COLOR_BayerGR2RGB_VNG = COLOR_BayerGB2BGR_VNG,
cv::COLOR_BayerBG2BGR_EA = 135,
cv::COLOR_BayerGB2BGR_EA = 136,
cv::COLOR_BayerRG2BGR_EA = 137,
cv::COLOR_BayerGR2BGR_EA = 138,
cv::COLOR_BayerBG2RGB_EA = COLOR_BayerRG2BGR_EA,
cv::COLOR_BayerGB2RGB_EA = COLOR_BayerGR2BGR_EA,
cv::COLOR_BayerRG2RGB_EA = COLOR_BayerBG2BGR_EA,
cv::COLOR_BayerGR2RGB_EA = COLOR_BayerGB2BGR_EA,
cv::COLOR_BayerBG2BGRA = 139,
cv::COLOR_BayerGB2BGRA = 140,
cv::COLOR_BayerRG2BGRA = 141,
cv::COLOR_BayerGR2BGRA = 142,
cv::COLOR_BayerBG2RGBA = COLOR_BayerRG2BGRA,
cv::COLOR_BayerGB2RGBA = COLOR_BayerGR2BGRA,
cv::COLOR_BayerRG2RGBA = COLOR_BayerBG2BGRA,
cv::COLOR_BayerGR2RGBA = COLOR_BayerGB2BGRA,
cv::COLOR_COLORCVT_MAX = 143
}
五、libyuv 库的编译和使用
1、libyuv 下载
- git 下载:可通过
README.chromium
查看版本号 - 或者通过网页下载压缩包:https://chromium.googlesource.com/libyuv/libyuv/+/refs/heads/master
2、libyuv 编译
# 编译指定平台的库,只需要把相应的编译器换一下就好了
# 1、使用 make 来编译(默认为 gcc/g++ 编译器,生成静态库 libyuv.a)
cd libyuv-master/
vim linux.mk
# 更改为自己的编译器和编译选项
CC=/home/manzp/projects/19.sigmastar/gcc-sigmastar-9.1.0-2020.07-x86_64_arm-linux-gnueabihf/bin/arm-linux-gnueabihf-sigmastar-9.1.0-gcc
CFLAGS:=-mcpu=cortex-a53 -fno-aggressive-loop-optimizations -O3 -fomit-frame-pointer -ffast-math -Wall -fPIC -fpermissive -mfpu=neon-vfpv4
CFLAGS+=-Iinclude/
CXX=/home/manzp/projects/19.sigmastar/gcc-sigmastar-9.1.0-2020.07-x86_64_arm-linux-gnueabihf/bin/arm-linux-gnueabihf-sigmastar-9.1.0-g++
CXXFLAGS:=-mcpu=cortex-a53 -fno-aggressive-loop-optimizations -O3 -fomit-frame-pointer -ffast-math -Wall -fPIC -fpermissive -mfpu=neon-vfpv4
CXXFLAGS+=-Iinclude/
# 编译和重新编译
make -f linux.mk -j16 # 默认生成静态库
make -f linux.mk clean # 使用不同的编译器重新编译前记得 clean 一下
# 2、使用 cmake 来编译,默认 debug build,out 下面有 libyuv.a libyuv.so 及 yuvconvert 产生
mkdir out
cd out
cmake ..
cmake --build .
# release build/install,如果想用自己的编译器,加上 -DCROSS_COMPILE=arm-himix200-linux
mkdir out
cd out
cmake -DCMAKE_INSTALL_PREFIX="/usr/lib" -DCMAKE_BUILD_TYPE="Release" ..
cmake --build . --config Release
sudo cmake --build . --target install --config Release
# 3、使用 ndk-build 来编译
mkdir prj_android_build/jni
cp Android.mk prj_android_build/jni
# 修改编译路径
# 新增Application.mk
/opt/android-ndk-r21e/ndk-build
3、libyuv 使用
libyuv is an open source project that includes YUV scaling and conversion functionality.
- Scale YUV to prepare content for compression, with point, bilinear or box filter.
- Convert to YUV from webcam formats for compression.
- Convert to RGB formats for rendering/effects.
- Rotate by 90/180/270 degrees to adjust for mobile devices in portrait mode.
- Optimized for SSSE3/AVX2 on x86/x64
- Optimized for Neon on Arm.
- Optimized for MSA on Mips.
- 将 libyuv.h 包含到工程,直接调用转换函数即可
void NV12Crop(uint8_t *src_y, uint8_t *src_uv, int src_stride_y,
int* roi_x, int* roi_y, int* roi_w, int* roi_h,
uint8_t *dst_yuv) {
// 裁剪的坐标 X 和 Y 必须是偶数,否则可能得到 NV21
// 裁剪的宽和高必须是偶数(2n*2n*1.5 = 6n2),正好是 6 的倍数(每四个 Y 对应一个 UV)
*roi_x = (*roi_x % 2) ? (*roi_x - 1) : *roi_x;
*roi_y = (*roi_y % 2) ? (*roi_y - 1) : *roi_y;
*roi_w = (*roi_w % 2) ? (*roi_w - 1) : *roi_w;
*roi_h = (*roi_h % 2) ? (*roi_h - 1) : *roi_h;
// 取得 SRC YUV 首地址
unsigned char *src_roi_y = src_y + src_stride_y * (*roi_y) + (*roi_x);
// NV12在竖直方向上进行了 1/2 下采样,水平方向上并未做下采样,所以只需 roi_y 减半
unsigned char *src_roi_uv = src_uv + src_stride_y * (*roi_y) / 2 + (*roi_x);
unsigned char *dst_y = dst_yuv;
unsigned char *dst_uv = dst_yuv + (*roi_w) * (*roi_h);
for (int h = 0; h < *roi_h; h++) {
// ROI 按行 copy Y
memcpy(dst_y + (*roi_w) * h, src_roi_y + src_stride_y * h, *roi_w);
if (h < *roi_h / 2) {
// ROI 按行 copy UV
memcpy(dst_uv + (*roi_w) * h, src_roi_uv + src_stride_y * h, *roi_w);
}
}
}
void NV12RoiScaleToRGB24(u8 *src_y, u8 *src_uv, s32 src_stride,
s32 *roi_x, s32 *roi_y, s32 *roi_w, s32 *roi_h,
u8 *dst_rgb24, s32 dst_w, s32 dst_h) {
// 裁剪的坐标 X 和 Y 必须是偶数,否则可能得到 NV21
// 裁剪的宽和高必须是偶数(2n*2n*1.5 = 6n2),正好是 6 的倍数(每四个 Y 对应一个 UV)
// TODO:可考虑使用结构体简化代码
*roi_x = (*roi_x % 2) ? (*roi_x - 1) : *roi_x;
*roi_y = (*roi_y % 2) ? (*roi_y - 1) : *roi_y;
*roi_w = (*roi_w % 2) ? (*roi_w - 1) : *roi_w;
*roi_h = (*roi_h % 2) ? (*roi_h - 1) : *roi_h;
// 取得 SRC YUV 首地址
u8 *src_roi_y = (u8 *) (src_y + src_stride * (*roi_y) + (*roi_x));
// NV12 在竖直方向上进行了 1/2 下采样,水平方向上并未做下采样,所以只需 roi_y 减半
uint16_t *src_roi_uv = (uint16_t *) (src_uv + src_stride * (*roi_y) / 2 + (*roi_x));
// 开辟缩放中间结果内存(NV12),TODO:可考虑通过参数传入,Open 的时候开辟
u8 *dst_tmp_buffer = (u8 *) calloc(1, dst_w * dst_h * 1.5); // H*WC,BGR888
u8 *dst_y = dst_tmp_buffer;
u8 *dst_uv = dst_tmp_buffer + dst_w * dst_h;
libyuv::ScalePlane(src_roi_y, src_stride, *roi_w, *roi_h, dst_y, dst_w, dst_w, dst_h, libyuv::kFilterBilinear);
libyuv::ScalePlane_16(src_roi_uv, src_stride / 2, (*roi_w) / 2, (*roi_h) / 2, (u16 *) dst_uv, dst_w / 2,
dst_w / 2, dst_h / 2, libyuv::kFilterNone);
libyuv::NV12ToRGB24(dst_y, dst_w, dst_uv, dst_w, dst_rgb24, dst_w * 3, dst_w, dst_h);
if (dst_tmp_buffer != NULL) {
free(dst_tmp_buffer);
dst_tmp_buffer = NULL;
}
}
void NV12RoiToRGB24Perspective(u8 *src_y, u8 *src_uv, s32 src_stride,
s32 LeftTopx, s32 LeftTopy, s32 RightTopx, s32 RightTopy,
s32 LeftBottomx, s32 LeftBottomy, s32 RightBottomx, s32 RightBottomy,
u8 *dst_rgb24, s32 dst_w, s32 dst_h) {
// 裁剪的坐标 X 和 Y 必须是偶数,否则可能得到 NV21
// 裁剪的宽和高必须是偶数(2n*2n*1.5 = 6n2),正好是 6 的倍数(每四个Y对应一个UV)
s32 offset = 10; // 上下左右各自外扩 10 个像素,为放射变换做准备
s32 roi_x = s32(LeftTopx - offset);
s32 roi_y = s32(LeftTopy - offset);
roi_x = (roi_x < 0) ? 0 : roi_x; // 防止扩大后越界
roi_y = (roi_y < 0) ? 0 : roi_y;
s32 roi_w = s32(RightBottomx - LeftTopx + 1 + 2 * offset);
s32 roi_h = s32(RightBottomy - LeftTopy + 1 + 2 * offset);
roi_w = ((roi_x + roi_w) < src_stride) ? roi_w : (src_stride - roi_x); // 防止扩大后越界
roi_h = ((roi_y + roi_h) < src_stride) ? roi_h : (src_stride - roi_x);
// 确保输入坐标均为偶数
roi_x = (roi_x % 2) ? (roi_x - 1) : roi_x;
roi_y = (roi_y % 2) ? (roi_y - 1) : roi_y;
roi_w = (roi_w % 2) ? (roi_w - 1) : roi_w;
roi_h = (roi_h % 2) ? (roi_h - 1) : roi_h;
// 取得 SRC YUV 首地址
u8 *src_roi_y = src_y + src_stride * roi_y + roi_x;
// NV12 在竖直方向上进行了 1/2 下采样,水平方向上并未做下采样,所以只需 roi_y 减半
u8 *src_roi_uv = src_uv + src_stride * roi_y / 2 + roi_x;
// 开辟中间结果内存转为 H*WC,BGR888,TODO:可考虑通过参数传入,Open 的时候开辟
u8 *dst_tmp_buffer = (u8 *) calloc(1, roi_w * roi_h * 3);
libyuv::NV12ToRGB24(src_roi_y, src_stride, src_roi_uv, src_stride, dst_tmp_buffer, roi_w * 3, roi_w, roi_h);
// 透视变换
PerspectiveTransform(dst_tmp_buffer, dst_rgb24, roi_w, roi_h, dst_w, dst_h,
LeftTopx - roi_x, LeftTopy - roi_y,
RightTopx - roi_x, RightTopy - roi_y,
LeftBottomx - roi_x, LeftBottomy - roi_y,
RightBottomx - roi_x, RightBottomy - roi_y); // 需输入相对位置
// TODO: 若处理完成后后续模块还要用,则需要返回相对原图的坐标点,可考虑使用指针数组简化
if (dst_tmp_buffer != NULL) {
free(dst_tmp_buffer);
dst_tmp_buffer = NULL;
}
}
六、参考资料
1、详解YUV数据格式
2、YUV 格式详解,只看这一篇就够了
3、图像原始格式(YUV444 YUV422 YUV420)一探究竟
4、libyuv库简单使用
5、详解 YUV,一文搞定 YUV 是什么!
6、ARMv8 SIMD和浮点指令编程:Libyuv I420 转 ARGB 流程分析