2020-03-13 01:36:01 -0600
| received badge | ● Popular Question
(source)
|
2018-10-31 09:30:59 -0600
| received badge | ● Notable Question
(source)
|
2017-09-28 05:56:29 -0600
| received badge | ● Popular Question
(source)
|
2017-04-10 00:39:05 -0600
| received badge | ● Popular Question
(source)
|
2016-02-19 23:06:34 -0600
| received badge | ● Famous Question
(source)
|
2015-10-18 07:58:07 -0600
| received badge | ● Famous Question
(source)
|
2015-01-27 02:38:28 -0600
| received badge | ● Notable Question
(source)
|
2014-10-13 02:55:22 -0600
| received badge | ● Student
(source)
|
2014-10-08 03:33:56 -0600
| received badge | ● Notable Question
(source)
|
2014-08-12 02:22:32 -0600
| received badge | ● Popular Question
(source)
|
2014-06-17 07:18:27 -0600
| received badge | ● Popular Question
(source)
|
2013-11-29 04:53:55 -0600
| asked a question | motempl.c lag Hi, I have one question. For motion detection I found sample in opencv called motempl.c. But there is one problem. When i tied to test it with video, there are some lag. About 1 sec. difference between real video, and motion detection. How to solve this prolem? Code: #include "opencv2/video/tracking.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc_c.h"
#include <time.h>
#include <stdio.h>
#include <ctype.h>
using namespace cv;
static void help(void)
{
printf(
"\nThis program demonstrated the use of motion templates -- basically using the gradients\n"
"of thresholded layers of decaying frame differencing. New movements are stamped on top with floating system\n"
"time code and motions too old are thresholded away. This is the 'motion history file'. The program reads from the camera of your choice or from\n"
"a file. Gradients of motion history are used to detect direction of motoin etc\n"
"Usage :\n"
"./motempl [camera number 0-n or file name, default is camera 0]\n"
);
}
// various tracking parameters (in seconds)
const double MHI_DURATION = 1;
const double MAX_TIME_DELTA = 0.5;
const double MIN_TIME_DELTA = 0.05;
// number of cyclic frame buffer used for motion detection
// (should, probably, depend on FPS)
const int N = 4;
// ring image buffer
IplImage **buf = 0;
int last = 0;
// temporary images
IplImage *mhi = 0; // MHI
IplImage *orient = 0; // orientation
IplImage *mask = 0; // valid orientation mask
IplImage *segmask = 0; // motion segmentation map
CvMemStorage* storage = 0; // temporary storage
// parameters:
// img - input video frame
// dst - resultant motion picture
// args - optional parameters
static void update_mhi( IplImage* img, IplImage* dst, int diff_threshold )
{
double timestamp = (double)clock()/CLOCKS_PER_SEC; // get current time in seconds
CvSize size = cvSize(img->width,img->height); // get current frame size
int i, idx1 = last, idx2;
IplImage* silh;
CvSeq* seq;
CvRect comp_rect;
double count;
double angle;
CvPoint center;
double magnitude;
CvScalar color;
// allocate images at the beginning or
// reallocate them if the frame size is changed
if( !mhi || mhi->width != size.width || mhi->height != size.height ) {
if( buf == 0 ) {
buf = (IplImage**)malloc(N*sizeof(buf[0]));
memset( buf, 0, N*sizeof(buf[0]));
}
for( i = 0; i < N; i++ ) {
cvReleaseImage( &buf[i] );
buf[i] = cvCreateImage( size, IPL_DEPTH_8U, 1 );
cvZero( buf[i] );
}
cvReleaseImage( &mhi );
cvReleaseImage( &orient );
cvReleaseImage( &segmask );
cvReleaseImage( &mask );
mhi = cvCreateImage( size, IPL_DEPTH_32F, 1 );
cvZero( mhi ); // clear MHI at the beginning
orient = cvCreateImage( size, IPL_DEPTH_32F, 1 );
segmask = cvCreateImage( size, IPL_DEPTH_32F, 1 );
mask = cvCreateImage( size, IPL_DEPTH_8U, 1 );
}
cvCvtColor( img, buf[last], CV_BGR2GRAY ); // convert frame to grayscale
idx2 = (last + 1) % N; // index of (last - (N-1))th frame
last = idx2;
silh = buf[idx2];
cvAbsDiff( buf[idx1], buf[idx2], silh ); // get difference between frames
cvThreshold( silh, silh, diff_threshold, 1, CV_THRESH_BINARY ); // and threshold it
cvUpdateMotionHistory( silh, mhi, timestamp, MHI_DURATION ); // update MHI
// convert MHI to blue 8u image
cvCvtScale( mhi, mask, 255./MHI_DURATION,
(MHI_DURATION - timestamp)*255./MHI_DURATION );
cvZero( dst );
cvMerge( mask, 0, 0, 0, dst );
// calculate motion gradient orientation and valid orientation mask
cvCalcMotionGradient( mhi, mask, orient, MAX_TIME_DELTA, MIN_TIME_DELTA, 3 );
if( !storage )
storage = cvCreateMemStorage(0);
else
cvClearMemStorage(storage);
// segment motion: get sequence of motion components ... (more) |
2013-11-22 05:07:34 -0600
| commented question | how to get direction of moving object? hahhhahaha... I know how to track an object, but i don't know how to determine if object is comming in or out |
2013-11-22 04:43:50 -0600
| asked a question | how to get direction of moving object? Hi, I am writing a code for moving objects detection, but now i want to count in/out objects. Now i can count olny how many objects cross the line. What is the best way to do that? For detection I use frames substraction (first frame with current frame). |
2013-11-13 05:55:58 -0600
| commented question | counting algorithm what is the best way to count people? Now i write a code that counts by coordinates (when people cross the line it is counted) |
2013-11-12 13:33:28 -0600
| commented question | counting algorithm |
2013-11-10 12:00:58 -0600
| asked a question | counting algorithm Hello, I have people detection algorithm and it works quite good and now I want to count in/out people. What is the best way to do that? |
2013-10-29 15:33:59 -0600
| asked a question | HOG detection from video Hi, When the input comes from webcam, the detection works fine. But when from video file, it works very slow (video file is playing very slow). Here is my code: #include <iostream>
#include <opencv2/opencv.hpp>
using namespace std;
using namespace cv;
int main (int argc, const char * argv[])
{
VideoCapture cap("video.avi");
cap.set(CV_CAP_PROP_FRAME_WIDTH, 320);
cap.set(CV_CAP_PROP_FRAME_HEIGHT, 240);
if (!cap.isOpened())
return -1;
Mat img;
HOGDescriptor hog;
hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector());
namedWindow("video capture", CV_WINDOW_AUTOSIZE);
while (true)
{
cap >> img;
if (!img.data)
continue;
vector<Rect> found, found_filtered;
hog.detectMultiScale(img, found, 0, Size(8,8), Size(32,32), 1.05, 2);
size_t i, j;
for (i=0; i<found.size(); i++)
{
Rect r = found[i];
for (j=0; j<found.size(); j++)
if (j!=i && (r & found[j])==r)
break;
if (j==found.size())
found_filtered.push_back(r);
}
for (i=0; i<found_filtered.size(); i++)
{
Rect r = found_filtered[i];
r.x += cvRound(r.width*0.1);
r.width = cvRound(r.width*0.8);
r.y += cvRound(r.height*0.06);
r.height = cvRound(r.height*0.9);
rectangle(img, r.tl(), r.br(), cv::Scalar(0,255,0), 2);
}
imshow("video capture", img);
if (waitKey(20) >= 0)
break;
}
return 0;
}
|
2013-10-23 07:19:23 -0600
| commented question | svmlight problems What do you mean windows headers? |
2013-10-21 05:15:49 -0600
| asked a question | svmlight problems Hello, I am trying to train my hog algorithm and I have one problem. In svm_common.h file I have some ambiguity. typedef struct word {
FNUM wnum; /* word number */
FVAL weight; /* word weight */
} WORD;
typedef struct svector {
WORD *words; /* Visual Studio 2012 says that WORD is ambiguous */
Where is the problem? |
2013-10-14 07:38:21 -0600
| asked a question | human detection with HOG. How to improve it? Hello, I have a code for human detection, but it works not as good as I want. I read some articles that is possible to train this detector. I was searching for hour to find some good tutorials for training. Maybe you can help me. #include <iostream>
#include <opencv2/opencv.hpp>
using namespace std;
using namespace cv;
int main (int argc, const char * argv[])
{
VideoCapture cap(CV_CAP_ANY);
cap.set(CV_CAP_PROP_FRAME_WIDTH, 320);
cap.set(CV_CAP_PROP_FRAME_HEIGHT, 240);
if (!cap.isOpened())
return -1;
Mat img;
HOGDescriptor hog;
hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector());
namedWindow("video capture", CV_WINDOW_AUTOSIZE);
while (true)
{
cap >> img;
if (!img.data)
continue;
vector<Rect> found, found_filtered;
hog.detectMultiScale(img, found, 0, Size(8,8), Size(32,32), 1.05, 2);
size_t i, j;
for (i=0; i<found.size(); i++)
{
Rect r = found[i];
for (j=0; j<found.size(); j++)
if (j!=i && (r & found[j])==r)
break;
if (j==found.size())
found_filtered.push_back(r);
}
for (i=0; i<found_filtered.size(); i++)
{
Rect r = found_filtered[i];
r.x += cvRound(r.width*0.1);
r.width = cvRound(r.width*0.8);
r.y += cvRound(r.height*0.06);
r.height = cvRound(r.height*0.9);
rectangle(img, r.tl(), r.br(), cv::Scalar(0,255,0), 2);
}
imshow("video capture", img);
if (waitKey(20) >= 0)
break;
}
return 0;
}
|
2013-10-07 13:24:26 -0600
| asked a question | hog.detectMultiScale parameters Hello,
Can anyone explaine me in simple words what these parameters: 0, Size(6,6), Size(32,32), 1.05, 2 in this function does? do hog.detectMultiScale(img, found, 0, Size(6,6), Size(32,32), 1.05, 2);
|
2013-10-06 11:18:53 -0600
| received badge | ● Critic
(source)
|
2013-10-06 09:20:44 -0600
| asked a question | human recognition Hello,
I want to recognize and track human from viedo stream. What is the best way for this? |
2013-10-06 08:20:50 -0600
| commented question | full body detection with c+ I want to recognize and detect people from video stream |
2013-10-03 08:46:51 -0600
| received badge | ● Editor
(source)
|
2013-10-03 08:44:28 -0600
| asked a question | full body detection with c+ Hi,
I am new with OpenCV. I wrote a code for human full body detection, but it works not very well. Sometimes when I stay infront of camera, it does not recognise me. Maybe I done some mistakes in my code. I hope You understand me. #include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
/** Function Headers */
void detectAndDisplay( Mat frame );
/** Global variables */
String body_cascade_name = "haarcascade_fullbody.xml";
CascadeClassifier body_cascade;
string window_name = "Capture - Face detection";
RNG rng(12345);
/** @function main */
int main( int argc, const char** argv )
{
CvCapture* capture;
Mat frame;
//-- 1. Load the cascades
if( !body_cascade.load( body_cascade_name ) )
{
printf("--(!)Error loading\n"); return -1;
};
//-- 2. Read the video stream
capture = cvCaptureFromCAM( -1 );
cvSetCaptureProperty( capture, CV_CAP_PROP_FRAME_WIDTH, 180 );
cvSetCaptureProperty( capture, CV_CAP_PROP_FRAME_HEIGHT, 180 );
if( capture )
{
while( true )
{
frame = cvQueryFrame( capture );
//-- 3. Apply the classifier to the frame
if( !frame.empty() )
{
detectAndDisplay( frame );
} else {
printf(" --(!) No captured frame -- Break!");
break;
}
int c = waitKey(100);
if( (char)c == 'c' )
{
break;
}
}
}
return 0;
}
/** @function detectAndDisplay */
void detectAndDisplay( Mat frame )
{
vector<Rect> bodys;
Mat frame_gray;
cvtColor( frame, frame_gray, CV_BGR2GRAY );
equalizeHist( frame_gray, frame_gray );
//-- detect body */
body_cascade.detectMultiScale(frame_gray, bodys, 1.1, 2, 18|9, Size(3,7));
for( int j = 0; j < bodys.size(); j++ )
{
Point center( bodys[j].x + bodys[j].width*0.5, bodys[j].y+ + bodys[j].height*0.5 );
ellipse( frame, center, Size( bodys[j].width*0.5, bodys[j].height*0.5), 0, 0, 360, Scalar( 255, 0, 255 ), 4, 8, 0 );
}
imshow( window_name, frame );
}
|