原文地址：http://yangmei.yan1988.blog.163.com/blog/static/2502675320108651841660/
分配图像空间:
IplImage* cvCreateImage(CvSize size, int depth, int channels);
size: cvSize(width,height);
depth: IPL_DEPTH_8U, IPL_DEPTH_8S, IPL_DEPTH_16U,
IPL_DEPTH_16S, IPL_DEPTH_32S, IPL_DEPTH_32F, IPL_DEPTH_64F
channels: 1, 2, 3 or 4.
注意数据为交叉存取.彩色图像的数据编排为b0 g0 r0 b1 g1 r1 ...
举例:
// 分配一个单通道字节图像
IplImage* img1=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
// 分配一个三通道浮点图像
IplImage* img2=cvCreateImage(cvSize(640,480),IPL_DEPTH_32F,3);
释放图像空间:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
cvReleaseImage(&img);
复制图像:
IplImage* img1=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
IplImage* img2;
img2=cvCloneImage(img1);
设定/获取兴趣区域:
void cvSetImageROI(IplImage* image, CvRect rect);
void cvResetImageROI(IplImage* image);
vRect cvGetImageROI(const IplImage* image);
大部分OpenCV函数都支持ROI.
设定/获取兴趣通道:
void cvSetImageCOI(IplImage* image, int coi); // 0=all
int cvGetImageCOI(const IplImage* image);
大部分OpenCV函数暂不支持COI.
读取存储图像
从文件中载入图像:
IplImage* img=0;
img=cvLoadImage(fileName);
if(!img) printf("Could not load image file: %s\n",fileName);
Supported image formats: BMP, DIB, JPEG, JPG, JPE, PNG, PBM, PGM, PPM,
SR, RAS, TIFF, TIF
载入图像默认转为3通道彩色图像. 如果不是，则需加flag:
img=cvLoadImage(fileName,flag);
flag: >0 载入图像转为三通道彩色图像
=0 载入图像转为单通道灰度图像
<0 不转换载入图像(通道数与图像文件相同).
图像存储为图像文件:
if(!cvSaveImage(outFileName,img)) printf("Could not save: %s\n",outFileName);
输入文件格式由文件扩展名决定.
存取图像元素
假设需要读取在i行j列像点的第k通道. 其中, 行数i的范围为[0, height-1], 列数j的范围为[0, width-1], 通道k的范围为[0, nchannels-1].
间接存取: (比较通用, 但效率低, 可读取任一类型图像数据)
对单通道字节图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
CvScalar s;
s=cvGet2D(img,i,j); // get the (i,j) pixel value
printf("intensity=%f\n",s.val[0]);
s.val[0]=111;
cvSet2D(img,i,j,s); // set the (i,j) pixel value
对多通道浮点或字节图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_32F,3);
CvScalar s;
s=cvGet2D(img,i,j); // get the (i,j) pixel value
printf("B=%f, G=%f, R=%f\n",s.val[0],s.val[1],s.val[2]);
s.val[0]=111;
s.val[1]=111;
s.val[2]=111;
cvSet2D(img,i,j,s); // set the (i,j) pixel value
直接存取: (效率高, 但容易出错)
对单通道字节图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
((uchar *)(img->imageData + i*img->widthStep))[j]=111;
对多通道字节图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,3);
((uchar *)(img->imageData + i*img->widthStep))[j*img->nChannels + 0]=111; // B
((uchar *)(img->imageData + i*img->widthStep))[j*img->nChannels + 1]=112; // G
((uchar *)(img->imageData + i*img->widthStep))[j*img->nChannels + 2]=113; // R
对多通道浮点图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_32F,3);
((float *)(img->imageData + i*img->widthStep))[j*img->nChannels + 0]=111; // B
((float *)(img->imageData + i*img->widthStep))[j*img->nChannels + 1]=112; // G
((float *)(img->imageData + i*img->widthStep))[j*img->nChannels + 2]=113; // R
用指针直接存取 : (在某些情况下简单高效)
对单通道字节图像:
IplImage* img = cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
int height = img->height;
int width = img->width;
int step = img->widthStep/sizeof(uchar);
uchar* data = (uchar *)img->imageData;
data[i*step+j] = 111;
对多通道字节图像:
IplImage* img = cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,3);
int height = img->height;
int width = img->width;
int step = img->widthStep/sizeof(uchar);
int channels = img->nChannels;
uchar* data = (uchar *)img->imageData;
data[i*step+j*channels+k] = 111;
对单通道浮点图像(假设用4字节调整):
IplImage* img = cvCreateImage(cvSize(640,480),IPL_DEPTH_32F,3);
int height = img->height;
int width = img->width;
int step = img->widthStep/sizeof(float);
int channels = img->nChannels;
float * data = (float *)img->imageData;
data[i*step+j*channels+k] = 111;
使用 c++ wrapper 进行直接存取: (简单高效)
对单/多通道字节图像，多通道浮点图像定义一个 c++ wrapper:
template<class T> class Image
{
private:
IplImage* imgp;
public:
Image(IplImage* img=0) {imgp=img;}
~Image(){imgp=0;}
void operator=(IplImage* img) {imgp=img;}
inline T* operator[](const int rowIndx) {
return ((T *)(imgp->imageData + rowIndx*imgp->widthStep));}
};
typedef struct{
unsigned char b,g,r;
} RgbPixel;
typedef struct{
float b,g,r;
} RgbPixelFloat;
typedef Image<RgbPixel> RgbImage;
typedef Image<RgbPixelFloat> RgbImageFloat;
typedef Image<unsigned char> BwImage;
typedef Image<float> BwImageFloat;
单通道字节图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,1);
BwImage imgA(img);
imgA[i][j] = 111;
多通道字节图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_8U,3);
RgbImage imgA(img);
imgA[i][j].b = 111;
imgA[i][j].g = 111;
imgA[i][j].r = 111;
多通道浮点图像:
IplImage* img=cvCreateImage(cvSize(640,480),IPL_DEPTH_32F,3);
RgbImageFloat imgA(img);
imgA[i][j].b = 111;
imgA[i][j].g = 111;
imgA[i][j].r = 111;
图像转换
转为灰度或彩色字节图像:
cvConvertImage(src, dst, flags=0);
src = float/byte grayscale/color image
dst = byte grayscale/color image
flags = CV_CVTIMG_FLIP (flip vertically)
CV_CVTIMG_SWAP_RB (swap the R and B channels)
转换彩色图像为灰度图像:
使用OpenCV转换函数:
cvCvtColor(cimg,gimg,CV_BGR2GRAY); // cimg -> gimg
直接转换:
for(i=0;i<cimg->height;i++) for(j=0;j<cimg->width;j++)
gimgA[i][j]= (uchar)(cimgA[i][j].b*0.114 +
cimgA[i][j].g*0.587 +
cimgA[i][j].r*0.299);
颜色空间转换:
cvCvtColor(src,dst,code); // src -> dst
code = CV_<X>2<Y>
<X>/<Y> = RGB, BGR, GRAY, HSV, YCrCb, XYZ, Lab, Luv, HLS
e.g.: CV_BGR2GRAY, CV_BGR2HSV, CV_BGR2Lab
绘图命令
画长方体:
// 用宽度为1的红线在(100,100)与(200,200)之间画一长方体
cvRectangle(img, cvPoint(100,100), cvPoint(200,200), cvScalar(255,0,0), 1);
画圆:
// 在(100,100)处画一半径为20的圆,使用宽度为1的绿线
cvCircle(img, cvPoint(100,100), 20, cvScalar(0,255,0), 1);
画线段:
// 在(100,100)与(200,200)之间画绿色线段，宽度为1
cvLine(img, cvPoint(100,100), cvPoint(200,200), cvScalar(0,255,0), 1);
画一组线段:
CvPoint curve1[]={10,10, 10,100, 100,100, 100,10};
CvPoint curve2[]={30,30, 30,130, 130,130, 130,30, 150,10};
CvPoint* curveArr[2]={curve1, curve2};
int nCurvePts[2]={4,5};
int nCurves=2;
int isCurveClosed=1;
int lineWidth=1;
cvPolyLine(img,curveArr,nCurvePts,nCurves,isCurveClosed,cvScalar(0,255,255),lineWidth);
画内填充色的多边形:
cvFillPoly(img,curveArr,nCurvePts,nCurves,cvScalar(0,255,255));
添加文本:
CvFont font;
double hScale=1.0;
double vScale=1.0;
int lineWidth=1;
cvInitFont(&font,CV_FONT_HERSHEY_SIMPLEX|CV_FONT_ITALIC, hScale,vScale,0,lineWidth);
cvPutText (img,"My comment",cvPoint(200,400), &font, cvScalar(255,255,0));
Other possible fonts:
CV_FONT_HERSHEY_SIMPLEX, CV_FONT_HERSHEY_PLAIN,
CV_FONT_HERSHEY_DUPLEX, CV_FONT_HERSHEY_COMPLEX,
CV_FONT_HERSHEY_TRIPLEX, CV_FONT_HERSHEY_COMPLEX_SMALL,
CV_FONT_HERSHEY_SCRIPT_SIMPLEX, CV_FONT_HERSHEY_SCRIPT_COMPLEX,
综述:
OpenCV有针对矩阵操作的C语言函数. 许多其他方法提供了更加方便的C++接口，其效率与OpenCV一样.
OpenCV将向量作为1维矩阵处理.
矩阵按行存储，每行有4字节的校整.
分配矩阵空间:
CvMat* cvCreateMat(int rows, int cols, int type);
type: 矩阵元素类型. 格式为CV_<bit_depth>(S|U|F)C<number_of_channels>.
例如: CV_8UC1 表示8位无符号单通道矩阵, CV_32SC2表示32位有符号双通道矩阵.
例程:
CvMat* M = cvCreateMat(4,4,CV_32FC1);
释放矩阵空间:
CvMat* M = cvCreateMat(4,4,CV_32FC1);
cvReleaseMat(&M);
复制矩阵:
CvMat* M1 = cvCreateMat(4,4,CV_32FC1);
CvMat* M2;
M2=cvCloneMat(M1);
初始化矩阵:
double a[] = { 1, 2, 3, 4,
5, 6, 7, 8,
9, 10, 11, 12 };
CvMat Ma=cvMat(3, 4, CV_64FC1, a);
另一种方法:
CvMat Ma;
cvInitMatHeader(&Ma, 3, 4, CV_64FC1, a);
初始化矩阵为单位阵:
CvMat* M = cvCreateMat(4,4,CV_32FC1);
cvSetIdentity(M); // 这里似乎有问题，不成功
存取矩阵元素
假设需要存取一个2维浮点矩阵的第(i,j)个元素.
间接存取矩阵元素:
cvmSet(M,i,j,2.0); // Set M(i,j)
t = cvmGet(M,i,j); // Get M(i,j)
直接存取，假设使用4-字节校正:
CvMat* M = cvCreateMat(4,4,CV_32FC1);
int n = M->cols;
float *data = M->data.fl;
data[i*n+j] = 3.0;
直接存取，校正字节任意:
CvMat* M = cvCreateMat(4,4,CV_32FC1);
int step = M->step/sizeof(float);
float *data = M->data.fl;
(data+i*step)[j] = 3.0;
直接存取一个初始化的矩阵元素:
double a[16];
CvMat Ma = cvMat(3, 4, CV_64FC1, a);
a[i*4+j] = 2.0; // Ma(i,j)=2.0;
矩阵/向量操作
矩阵-矩阵操作:
CvMat *Ma, *Mb, *Mc;
cvAdd(Ma, Mb, Mc); // Ma+Mb -> Mc
cvSub(Ma, Mb, Mc); // Ma-Mb -> Mc
cvMatMul(Ma, Mb, Mc); // Ma*Mb -> Mc
按元素的矩阵操作:
CvMat *Ma, *Mb, *Mc;
cvMul(Ma, Mb, Mc); // Ma.*Mb -> Mc
cvDiv(Ma, Mb, Mc); // Ma./Mb -> Mc
cvAddS(Ma, cvScalar(-10.0), Mc); // Ma.-10 -> Mc
向量乘积:
double va[] = {1, 2, 3};
double vb[] = {0, 0, 1};
double vc[3];
CvMat Va=cvMat(3, 1, CV_64FC1, va);
CvMat Vb=cvMat(3, 1, CV_64FC1, vb);
CvMat Vc=cvMat(3, 1, CV_64FC1, vc);
double res=cvDotProduct(&Va,&Vb); // 点乘: Va . Vb -> res
cvCrossProduct(&Va, &Vb, &Vc); // 向量积: Va x Vb -> Vc
end{verbatim}
注意 Va, Vb, Vc 在向量积中向量元素个数须相同.
单矩阵操作:
CvMat *Ma, *Mb;
cvTranspose(Ma, Mb); // transpose(Ma) -> Mb (不能对自身进行转置)
CvScalar t = cvTrace(Ma); // trace(Ma) -> t.val[0]
double d = cvDet(Ma); // det(Ma) -> d
cvInvert(Ma, Mb); // inv(Ma) -> Mb
非齐次线性系统求解:
CvMat* A = cvCreateMat(3,3,CV_32FC1);
CvMat* x = cvCreateMat(3,1,CV_32FC1);
CvMat* b = cvCreateMat(3,1,CV_32FC1);
cvSolve(&A, &b, &x); // solve (Ax=b) for x
特征值分析(针对对称矩阵):
CvMat* A = cvCreateMat(3,3,CV_32FC1);
CvMat* E = cvCreateMat(3,3,CV_32FC1);
CvMat* l = cvCreateMat(3,1,CV_32FC1);
cvEigenVV(&A, &E, &l); // l = A的特征值 (降序排列)
// E = 对应的特征向量 (每行)
奇异值分解SVD:
CvMat* A = cvCreateMat(3,3,CV_32FC1);
CvMat* U = cvCreateMat(3,3,CV_32FC1);
CvMat* D = cvCreateMat(3,3,CV_32FC1);
CvMat* V = cvCreateMat(3,3,CV_32FC1);
cvSVD(A, D, U, V, CV_SVD_U_T|CV_SVD_V_T); // A = U D V^T
标号使得 U 和 V 返回时被转置(若没有转置标号，则有问题不成功!!!).
视频序列操作
从视频序列中抓取一帧
OpenCV支持从摄像头或视频文件(AVI)中抓取图像.
从摄像头获取初始化:
CvCapture* capture = cvCaptureFromCAM(0); // capture from video device #0
从视频文件获取初始化:
CvCapture* capture = cvCaptureFromAVI("infile.avi");
抓取帧:
IplImage* img = 0;
if(!cvGrabFrame(capture)){ // 抓取一帧
printf("Could not grab a frame\n\7");
exit(0);
}
img=cvRetrieveFrame(capture); // 恢复获取的帧图像
要从多个摄像头同时获取图像, 首先从每个摄像头抓取一帧. 在抓取动作都结束后再恢复帧图像.
释放抓取源:
cvReleaseCapture(&capture);
注意由设备抓取的图像是由capture函数自动分配和释放的. 不要试图自己释放它.
获取/设定帧信息
获取设备特性:
cvQueryFrame(capture); // this call is necessary to get correct
// capture properties
int frameH = (int) cvGetCaptureProperty(capture, CV_CAP_PROP_FRAME_HEIGHT);
int frameW = (int) cvGetCaptureProperty(capture, CV_CAP_PROP_FRAME_WIDTH);
int fps = (int) cvGetCaptureProperty(capture, CV_CAP_PROP_FPS);
int numFrames = (int) cvGetCaptureProperty(capture, CV_CAP_PROP_FRAME_COUNT);
所有帧数似乎只与视频文件有关. 用摄像头时不对，奇怪!!!.
获取帧信息:
float posMsec = cvGetCaptureProperty(capture, CV_CAP_PROP_POS_MSEC);
int posFrames = (int) cvGetCaptureProperty(capture, CV_CAP_PROP_POS_FRAMES);
float posRatio = cvGetCaptureProperty(capture, CV_CAP_PROP_POS_AVI_RATIO);
获取所抓取帧在视频序列中的位置, 从首帧开始按[毫秒]算. 或者从首帧开始从0标号, 获取所抓取帧的标号. 或者取相对位置，首帧为0，末帧为1, 只对视频文件有效.
设定所抓取的第一帧标号:
// 从视频文件相对位置0.9处开始抓取
cvSetCaptureProperty(capture, CV_CAP_PROP_POS_AVI_RATIO, (double)0.9);
只对从视频文件抓取有效. 不过似乎也不成功!!!
存储视频文件
初始化视频存储器:
CvVideoWriter *writer = 0;
int isColor = 1;
int fps = 25; // or 30
int frameW = 640; // 744 for firewire cameras
int frameH = 480; // 480 for firewire cameras
writer=cvCreateVideoWriter("out.avi",CV_FOURCC('P','I','M','1'),
fps,cvSize(frameW,frameH),isColor);
其他有效编码:
CV_FOURCC('P','I','M','1') = MPEG-1 codec
CV_FOURCC('M','J','P','G') = motion-jpeg codec (does not work well)
CV_FOURCC('M', 'P', '4', '2') = MPEG-4.2 codec
CV_FOURCC('D', 'I', 'V', '3') = MPEG-4.3 codec
CV_FOURCC('D', 'I', 'V', 'X') = MPEG-4 codec
CV_FOURCC('U', '2', '6', '3') = H263 codec
CV_FOURCC('I', '2', '6', '3') = H263I codec
CV_FOURCC('F', 'L', 'V', '1') = FLV1 codec
若把视频编码设为-1则将打开一个编码选择窗口(windows系统下).
存储视频文件:
IplImage* img = 0;
int nFrames = 50;
for(i=0;i<nFrames;i++){
cvGrabFrame(capture); // 抓取帧
img=cvRetrieveFrame(capture); // 恢复图像
cvWriteFrame(writer,img); // 将帧添加入视频文件
}
若想在抓取中查看抓取图像, 可在循环中加入下列代码:
cvShowImage("mainWin", img);
key=cvWaitKey(20); // wait 20 ms
若没有20[毫秒]延迟，将无法正确显示视频序列.
释放视频存储器:
cvReleaseVideoWriter(&writer);
277
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
