iOS video Processing is slow,how can i run it in background?
I have read the article about OpenCV iOS - Video Processing In the - (void)processImage:(Mat&)image; function can deal with the video's image and output on the screen.Now I want to sign out the car in the video and let it show on the screen by a react.So i changed the - (void)processImage:(Mat&)image; function:
NSString *path = [[NSBundle mainBundle] pathForResource:@"car" ofType:@"xml"];
const char *pstrImage = [path cStringUsingEncoding:NSASCIIStringEncoding];
pHaarCascade = (CvHaarClassifierCascade*)cvLoad(pstrImage);
IplImage pSrcImage = image;
NSLog(@"%d*%d",image.cols,image.rows);
IplImage *pGrayImage = cvCreateImage(cvGetSize(&pSrcImage), IPL_DEPTH_8U, 1);
cvCvtColor(&pSrcImage, pGrayImage, CV_BGR2GRAY);
if (pHaarCascade != NULL) {
CvScalar carCircleColors[]=
{
{{0,0,255}},
{{0,128,255}},
{{0,255,255}},
{{0,255,0}},
{{255,128,0}},
{{255,255,0}},
{{255,0,0}},
{{255,0,255}}
};
CvMemStorage *pcvMStorage = cvCreateMemStorage(0);
cvClearMemStorage(pcvMStorage);
//识别
CvSeq *pcvSeqFaces = cvHaarDetectObjects(pGrayImage, pHaarCascade, pcvMStorage);
NSLog(@"车辆个数:%d",pcvSeqFaces->total);
for(int i = 0; i < pcvSeqFaces->total; i++)
{
CvRect* r = (CvRect*)cvGetSeqElem(pcvSeqFaces, i);
CvPoint p1,p2;
p1.x = r->x;
p2.x = r->x + r->width;
p1.y = r->y;
p2.y = r->y + r->height;
cvRect(p1.x, p1.y, p2.x, p2.y);
cvRectangle(&pSrcImage, p1, p2, carCircleColors[ i % 8]);
}
cvReleaseMemStorage(&pcvMStorage);
image = &pSrcImage;
} else {
NSLog(@"没有车辆");
}
cvReleaseImage(&pGrayImage);
this function can react out the car on the screen but i found it was very slow,that's let me crazy.I want to know how can i let it work quickly.(I am a Chinese,my English is very poor.)
In my experience, using Haarcascade is slow. maybe you could try another algorithm. and see any differences.