opencv 3.0 图像格式转换 cvtColor

关于如何将灰度图转化为彩图(伪彩),类似于matlab的 imagesc() 。

请见 http://blog.csdn.net/billbliss/article/details/43452173

 

言归正传:

cvtColor的功能是将图像的格式作转换

根据opencv 2.4.9的官方文档

cvtColor 有以下功能:

The conventional ranges for R, G, and B channel values are:
0 to 255 for CV_8U images
0 to 65535 for CV_16U images
0 to 1 for CV_32F images


RGB \leftrightarrow GRAY ( CV_BGR2GRAY, CV_RGB2GRAY, CV_GRAY2BGR, CV_GRAY2RGB )
RGB \leftrightarrow CIE XYZ.Rec 709 with D65 white point ( CV_BGR2XYZ, CV_RGB2XYZ, CV_XYZ2BGR, CV_XYZ2RGB )
RGB \leftrightarrow YCrCb JPEG (or YCC) ( CV_BGR2YCrCb, CV_RGB2YCrCb, CV_YCrCb2BGR, CV_YCrCb2RGB )
RGB \leftrightarrow HSV ( CV_BGR2HSV, CV_RGB2HSV, CV_HSV2BGR, CV_HSV2RGB )
RGB \leftrightarrow HLS ( CV_BGR2HLS, CV_RGB2HLS, CV_HLS2BGR, CV_HLS2RGB )
RGB \leftrightarrow CIE L*a*b* ( CV_BGR2Lab, CV_RGB2Lab, CV_Lab2BGR, CV_Lab2RGB )
RGB \leftrightarrow CIE L*u*v* ( CV_BGR2Luv, CV_RGB2Luv, CV_Luv2BGR, CV_Luv2RGB )
Bayer \rightarrow RGB ( CV_BayerBG2BGR, CV_BayerGB2BGR, CV_BayerRG2BGR, CV_BayerGR2BGR,V_BayerBG2RGB, CV_BayerGB2RGB, CV_BayerRG2RGB, CV_BayerGR2RGB )

在opencv3.0 中,格式的选项很多。

具体可查阅代码type_c.h 的 line 87:

enum
{
    CV_BGR2BGRA    =0,
    CV_RGB2RGBA    =CV_BGR2BGRA,

    CV_BGRA2BGR    =1,
    CV_RGBA2RGB    =CV_BGRA2BGR,

    CV_BGR2RGBA    =2,
    CV_RGB2BGRA    =CV_BGR2RGBA,

    CV_RGBA2BGR    =3,
    CV_BGRA2RGB    =CV_RGBA2BGR,

    CV_BGR2RGB     =4,
    CV_RGB2BGR     =CV_BGR2RGB,

    CV_BGRA2RGBA   =5,
    CV_RGBA2BGRA   =CV_BGRA2RGBA,

    CV_BGR2GRAY    =6,
    CV_RGB2GRAY    =7,
    CV_GRAY2BGR    =8,
    CV_GRAY2RGB    =CV_GRAY2BGR,
    CV_GRAY2BGRA   =9,
    CV_GRAY2RGBA   =CV_GRAY2BGRA,
    CV_BGRA2GRAY   =10,
    CV_RGBA2GRAY   =11,

    CV_BGR2BGR565  =12,
    CV_RGB2BGR565  =13,
    CV_BGR5652BGR  =14,
    CV_BGR5652RGB  =15,
    CV_BGRA2BGR565 =16,
    CV_RGBA2BGR565 =17,
    CV_BGR5652BGRA =18,
    CV_BGR5652RGBA =19,

    CV_GRAY2BGR565 =20,
    CV_BGR5652GRAY =21,

    CV_BGR2BGR555  =22,
    CV_RGB2BGR555  =23,
    CV_BGR5552BGR  =24,
    CV_BGR5552RGB  =25,
    CV_BGRA2BGR555 =26,
    CV_RGBA2BGR555 =27,
    CV_BGR5552BGRA =28,
    CV_BGR5552RGBA =29,

    CV_GRAY2BGR555 =30,
    CV_BGR5552GRAY =31,

    CV_BGR2XYZ     =32,
    CV_RGB2XYZ     =33,
    CV_XYZ2BGR     =34,
    CV_XYZ2RGB     =35,

    CV_BGR2YCrCb   =36,
    CV_RGB2YCrCb   =37,
    CV_YCrCb2BGR   =38,
    CV_YCrCb2RGB   =39,

    CV_BGR2HSV     =40,
    CV_RGB2HSV     =41,

    CV_BGR2Lab     =44,
    CV_RGB2Lab     =45,

    CV_BayerBG2BGR =46,
    CV_BayerGB2BGR =47,
    CV_BayerRG2BGR =48,
    CV_BayerGR2BGR =49,

    CV_BayerBG2RGB =CV_BayerRG2BGR,
    CV_BayerGB2RGB =CV_BayerGR2BGR,
    CV_BayerRG2RGB =CV_BayerBG2BGR,
    CV_BayerGR2RGB =CV_BayerGB2BGR,

    CV_BGR2Luv     =50,
    CV_RGB2Luv     =51,
    CV_BGR2HLS     =52,
    CV_RGB2HLS     =53,

    CV_HSV2BGR     =54,
    CV_HSV2RGB     =55,

    CV_Lab2BGR     =56,
    CV_Lab2RGB     =57,
    CV_Luv2BGR     =58,
    CV_Luv2RGB     =59,
    CV_HLS2BGR     =60,
    CV_HLS2RGB     =61,

    CV_BayerBG2BGR_VNG =62,
    CV_BayerGB2BGR_VNG =63,
    CV_BayerRG2BGR_VNG =64,
    CV_BayerGR2BGR_VNG =65,

    CV_BayerBG2RGB_VNG =CV_BayerRG2BGR_VNG,
    CV_BayerGB2RGB_VNG =CV_BayerGR2BGR_VNG,
    CV_BayerRG2RGB_VNG =CV_BayerBG2BGR_VNG,
    CV_BayerGR2RGB_VNG =CV_BayerGB2BGR_VNG,

    CV_BGR2HSV_FULL = 66,
    CV_RGB2HSV_FULL = 67,
    CV_BGR2HLS_FULL = 68,
    CV_RGB2HLS_FULL = 69,

    CV_HSV2BGR_FULL = 70,
    CV_HSV2RGB_FULL = 71,
    CV_HLS2BGR_FULL = 72,
    CV_HLS2RGB_FULL = 73,

    CV_LBGR2Lab     = 74,
    CV_LRGB2Lab     = 75,
    CV_LBGR2Luv     = 76,
    CV_LRGB2Luv     = 77,

    CV_Lab2LBGR     = 78,
    CV_Lab2LRGB     = 79,
    CV_Luv2LBGR     = 80,
    CV_Luv2LRGB     = 81,

    CV_BGR2YUV      = 82,
    CV_RGB2YUV      = 83,
    CV_YUV2BGR      = 84,
    CV_YUV2RGB      = 85,

    CV_BayerBG2GRAY = 86,
    CV_BayerGB2GRAY = 87,
    CV_BayerRG2GRAY = 88,
    CV_BayerGR2GRAY = 89,

    //YUV 4:2:0 formats family
    CV_YUV2RGB_NV12 = 90,
    CV_YUV2BGR_NV12 = 91,
    CV_YUV2RGB_NV21 = 92,
    CV_YUV2BGR_NV21 = 93,
    CV_YUV420sp2RGB = CV_YUV2RGB_NV21,
    CV_YUV420sp2BGR = CV_YUV2BGR_NV21,

    CV_YUV2RGBA_NV12 = 94,
    CV_YUV2BGRA_NV12 = 95,
    CV_YUV2RGBA_NV21 = 96,
    CV_YUV2BGRA_NV21 = 97,
    CV_YUV420sp2RGBA = CV_YUV2RGBA_NV21,
    CV_YUV420sp2BGRA = CV_YUV2BGRA_NV21,

    CV_YUV2RGB_YV12 = 98,
    CV_YUV2BGR_YV12 = 99,
    CV_YUV2RGB_IYUV = 100,
    CV_YUV2BGR_IYUV = 101,
    CV_YUV2RGB_I420 = CV_YUV2RGB_IYUV,
    CV_YUV2BGR_I420 = CV_YUV2BGR_IYUV,
    CV_YUV420p2RGB = CV_YUV2RGB_YV12,
    CV_YUV420p2BGR = CV_YUV2BGR_YV12,

    CV_YUV2RGBA_YV12 = 102,
    CV_YUV2BGRA_YV12 = 103,
    CV_YUV2RGBA_IYUV = 104,
    CV_YUV2BGRA_IYUV = 105,
    CV_YUV2RGBA_I420 = CV_YUV2RGBA_IYUV,
    CV_YUV2BGRA_I420 = CV_YUV2BGRA_IYUV,
    CV_YUV420p2RGBA = CV_YUV2RGBA_YV12,
    CV_YUV420p2BGRA = CV_YUV2BGRA_YV12,

    CV_YUV2GRAY_420 = 106,
    CV_YUV2GRAY_NV21 = CV_YUV2GRAY_420,
    CV_YUV2GRAY_NV12 = CV_YUV2GRAY_420,
    CV_YUV2GRAY_YV12 = CV_YUV2GRAY_420,
    CV_YUV2GRAY_IYUV = CV_YUV2GRAY_420,
    CV_YUV2GRAY_I420 = CV_YUV2GRAY_420,
    CV_YUV420sp2GRAY = CV_YUV2GRAY_420,
    CV_YUV420p2GRAY = CV_YUV2GRAY_420,

    //YUV 4:2:2 formats family
    CV_YUV2RGB_UYVY = 107,
    CV_YUV2BGR_UYVY = 108,
    //CV_YUV2RGB_VYUY = 109,
    //CV_YUV2BGR_VYUY = 110,
    CV_YUV2RGB_Y422 = CV_YUV2RGB_UYVY,
    CV_YUV2BGR_Y422 = CV_YUV2BGR_UYVY,
    CV_YUV2RGB_UYNV = CV_YUV2RGB_UYVY,
    CV_YUV2BGR_UYNV = CV_YUV2BGR_UYVY,

    CV_YUV2RGBA_UYVY = 111,
    CV_YUV2BGRA_UYVY = 112,
    //CV_YUV2RGBA_VYUY = 113,
    //CV_YUV2BGRA_VYUY = 114,
    CV_YUV2RGBA_Y422 = CV_YUV2RGBA_UYVY,
    CV_YUV2BGRA_Y422 = CV_YUV2BGRA_UYVY,
    CV_YUV2RGBA_UYNV = CV_YUV2RGBA_UYVY,
    CV_YUV2BGRA_UYNV = CV_YUV2BGRA_UYVY,

    CV_YUV2RGB_YUY2 = 115,
    CV_YUV2BGR_YUY2 = 116,
    CV_YUV2RGB_YVYU = 117,
    CV_YUV2BGR_YVYU = 118,
    CV_YUV2RGB_YUYV = CV_YUV2RGB_YUY2,
    CV_YUV2BGR_YUYV = CV_YUV2BGR_YUY2,
    CV_YUV2RGB_YUNV = CV_YUV2RGB_YUY2,
    CV_YUV2BGR_YUNV = CV_YUV2BGR_YUY2,

    CV_YUV2RGBA_YUY2 = 119,
    CV_YUV2BGRA_YUY2 = 120,
    CV_YUV2RGBA_YVYU = 121,
    CV_YUV2BGRA_YVYU = 122,
    CV_YUV2RGBA_YUYV = CV_YUV2RGBA_YUY2,
    CV_YUV2BGRA_YUYV = CV_YUV2BGRA_YUY2,
    CV_YUV2RGBA_YUNV = CV_YUV2RGBA_YUY2,
    CV_YUV2BGRA_YUNV = CV_YUV2BGRA_YUY2,

    CV_YUV2GRAY_UYVY = 123,
    CV_YUV2GRAY_YUY2 = 124,
    //CV_YUV2GRAY_VYUY = CV_YUV2GRAY_UYVY,
    CV_YUV2GRAY_Y422 = CV_YUV2GRAY_UYVY,
    CV_YUV2GRAY_UYNV = CV_YUV2GRAY_UYVY,
    CV_YUV2GRAY_YVYU = CV_YUV2GRAY_YUY2,
    CV_YUV2GRAY_YUYV = CV_YUV2GRAY_YUY2,
    CV_YUV2GRAY_YUNV = CV_YUV2GRAY_YUY2,

    // alpha premultiplication
    CV_RGBA2mRGBA = 125,
    CV_mRGBA2RGBA = 126,

    CV_RGB2YUV_I420 = 127,
    CV_BGR2YUV_I420 = 128,
    CV_RGB2YUV_IYUV = CV_RGB2YUV_I420,
    CV_BGR2YUV_IYUV = CV_BGR2YUV_I420,

    CV_RGBA2YUV_I420 = 129,
    CV_BGRA2YUV_I420 = 130,
    CV_RGBA2YUV_IYUV = CV_RGBA2YUV_I420,
    CV_BGRA2YUV_IYUV = CV_BGRA2YUV_I420,
    CV_RGB2YUV_YV12  = 131,
    CV_BGR2YUV_YV12  = 132,
    CV_RGBA2YUV_YV12 = 133,
    CV_BGRA2YUV_YV12 = 134,

    // Edge-Aware Demosaicing
    CV_BayerBG2BGR_EA = 135,
    CV_BayerGB2BGR_EA = 136,
    CV_BayerRG2BGR_EA = 137,
    CV_BayerGR2BGR_EA = 138,

    CV_BayerBG2RGB_EA = CV_BayerRG2BGR_EA,
    CV_BayerGB2RGB_EA = CV_BayerGR2BGR_EA,
    CV_BayerRG2RGB_EA = CV_BayerBG2BGR_EA,
    CV_BayerGR2RGB_EA = CV_BayerGB2BGR_EA,

    CV_COLORCVT_MAX  = 139
};

 

  • 2
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
DPM(Deformable Part-based Model) Cascade是一种常用的目标检测算法,在OpenCV 3.0中已经支持。在DPM Cascade中,目标被分为多个部分,每个部分用一个分类器来检测,这些分类器被组成一个级联分类器,来提高检测速度和准确率。 TBB和OpenMP是常用的多线程库,可以加速DPM Cascade的检测。在使用TBB和OpenMP之前,需要先安装它们。在Linux系统中,可以通过以下命令安装: ``` sudo apt-get install libtbb-dev sudo apt-get install libomp-dev ``` 在Windows系统中,可以在Intel官网下载TBB和OpenMP的安装程序进行安装。 下面是基于OpenCV 3.0的DPM Cascade检测代码,附带TBB和OpenMP加速: ```python import cv2 import numpy as np # 加载级联分类器 cascade = cv2.CascadeClassifier('path/to/cascade.xml') # 加载图像 img = cv2.imread('path/to/image.jpg') # 转换为灰度图像 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 检测目标 rects = cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=3, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE) # 绘制矩形框 for (x, y, w, h) in rects: cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2) # 显示结果 cv2.imshow('result', img) cv2.waitKey(0) cv2.destroyAllWindows() ``` 加入TBB和OpenMP加速的代码如下: ```python import cv2 import numpy as np import time import threading import multiprocessing # 加载级联分类器 cascade = cv2.CascadeClassifier('path/to/cascade.xml') # 加载图像 img = cv2.imread('path/to/image.jpg') # 转换为灰度图像 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 检测目标 start_time = time.time() rects = cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=3, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE) end_time = time.time() print('串行检测时间:', end_time-start_time) # 绘制矩形框 for (x, y, w, h) in rects: cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2) # 显示结果 cv2.imshow('result', img) cv2.waitKey(0) cv2.destroyAllWindows() # TBB并行检测 def detect_with_tbb(gray, cascade): rects = cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=3, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE) return rects start_time = time.time() tbb_results = [] tbb = threading.Thread(target=tbb_results.append, args=(detect_with_tbb(gray, cascade),)) tbb.start() tbb.join() end_time = time.time() print('TBB检测时间:', end_time-start_time) # 绘制矩形框 for (x, y, w, h) in tbb_results[0]: cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2) # 显示结果 cv2.imshow('result', img) cv2.waitKey(0) cv2.destroyAllWindows() # OpenMP并行检测 def detect_with_omp(gray, cascade): rects = cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=3, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE) return rects start_time = time.time() omp_results = [] omp = multiprocessing.Process(target=omp_results.append, args=(detect_with_omp(gray, cascade),)) omp.start() omp.join() end_time = time.time() print('OpenMP检测时间:', end_time-start_time) # 绘制矩形框 for (x, y, w, h) in omp_results[0]: cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2) # 显示结果 cv2.imshow('result', img) cv2.waitKey(0) cv2.destroyAllWindows() ``` 在上面的代码中,我们使用了Python的多线程库threading和多进程库multiprocessing来实现TBB和OpenMP的并行化。通过比较串行检测时间和并行检测时间,可以看出TBB和OpenMP都可以有效地加速DPM Cascade的检测。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值