文件列表:

CMakeLists.txt (2136, 2015-09-18)
Demo.cpp (1721, 2015-09-18)
build (0, 2015-09-18)
build\FOR_LINUX_USERS (3, 2015-09-18)
config (0, 2015-09-18)
config\BlobTracking.xml (215, 2015-09-18)
config\PixelBasedAdaptiveSegmenter.xml (437, 2015-09-18)
config\VehicleCouting.xml (296, 2015-09-18)
dataset (0, 2015-09-18)
dataset\video.avi (1049784, 2015-09-18)
include (0, 2015-09-18)
include\opencv (0, 2015-09-18)
include\opencv\cv.h (3438, 2015-09-18)
include\opencv\cv.hpp (2411, 2015-09-18)
include\opencv\cvaux.h (2850, 2015-09-18)
include\opencv\cvaux.hpp (2346, 2015-09-18)
include\opencv\cvwimage.h (2184, 2015-09-18)
include\opencv\cxcore.h (2465, 2015-09-18)
include\opencv\cxcore.hpp (2423, 2015-09-18)
include\opencv\cxeigen.hpp (2265, 2015-09-18)
include\opencv\cxmisc.h (110, 2015-09-18)
include\opencv\highgui.h (2306, 2015-09-18)
include\opencv\ml.h (2189, 2015-09-18)
include\opencv2 (0, 2015-09-18)
include\opencv2\calib3d (0, 2015-09-18)
include\opencv2\calib3d\calib3d.hpp (41241, 2015-09-18)
include\opencv2\contrib (0, 2015-09-18)
include\opencv2\contrib\contrib.hpp (38786, 2015-09-18)
include\opencv2\contrib\detection_based_tracker.hpp (3042, 2015-09-18)
include\opencv2\contrib\hybridtracker.hpp (7099, 2015-09-18)
include\opencv2\contrib\openfabmap.hpp (12807, 2015-09-18)
include\opencv2\contrib\retina.hpp (23958, 2015-09-18)
include\opencv2\core (0, 2015-09-18)
include\opencv2\core\affine.hpp (15428, 2015-09-18)
include\opencv2\core\core.hpp (186571, 2015-09-18)
include\opencv2\core\core_c.h (78509, 2015-09-18)
... ...

Vehicle Detection, Tracking and Counting ======================================== Last page update: **30/04/2015** Last version: **1.0.0** (see Release Notes for more info) Hi everyone, There are several ways to perform vehicle detection, tracking and counting. Here is a step-by-step of a simplest way to do this: 1. First, you will need to detect the moving objects. An easy way to do vehicle detection is by using a Background Subtraction (BS) algorithm. You can try to use a background subtraction library like [BGSLibrary](https://github.com/andrewssobral/bgslibrary#bgslibrary). 2. For vehicle tracking, you will need to use a tracking algorithm. A simplest way to do this is by using a blob tracker algorithm (see [cvBlob](https://code.google.com/p/cvblob/) or [OpenCVBlobsLib](http://opencvblobslib.github.io/opencvblobslib/)). So, send the foreground mask to **cvBlob** or **OpenCVBlobsLib**. For example, the **cvBlob** library provide some methods to get the **centroid**, the **track** and the **ID** of the moving objects. You can also set to draw a **bounding box**, the **centroid** and the **angle** of the tracked object. 3. And then, check if the **centroid** of the moving object has crossed a **region of interest** (i.e. virtual line) in your video. 4. Voil! enjoy it :) Additional informations: * There is a Visual Studio 2013 template project in the **vs2013/** folder. Open it in the Visual Studio IDE and select [Release]-[Win32] mode. * The include files for the OpenCV 2.4.10 are provided in the **include/** folder, and the related static libraries are provided in the **lib/x86/vc12** folder.

Example code ------------ ```C++ #include #include #include #include "package_bgs/PBAS/PixelBasedAdaptiveSegmenter.h" #include "package_tracking/BlobTracking.h" #include "package_analysis/VehicleCouting.h" int main(int argc, char **argv) { /* Open video file */ CvCapture *capture = 0; capture = cvCaptureFromAVI("dataset/video.avi"); if(!capture){ std::cerr << "Cannot open video!" << std::endl; return 1; } /* Background Subtraction Algorithm */ IBGS *bgs; bgs = new PixelBasedAdaptiveSegmenter; /* Blob Tracking Algorithm */ cv::Mat img_blob; BlobTracking* blobTracking; blobTracking = new BlobTracking; /* Vehicle Counting Algorithm */ VehicleCouting* vehicleCouting; vehicleCouting = new VehicleCouting; std::cout << "Press 'q' to quit..." << std::endl; int key = 0; IplImage *frame; while(key != 'q') { frame = cvQueryFrame(capture); if(!frame) break; cv::Mat img_input(frame); cv::imshow("Input", img_input); // bgs->process(...) internally process and show the foreground mask image cv::Mat img_mask; bgs->process(img_input, img_mask); if(!img_mask.empty()) { // Perform blob tracking blobTracking->process(img_input, img_mask, img_blob); // Perform vehicle counting vehicleCouting->setInput(img_blob); vehicleCouting->setTracks(blobTracking->getTracks()); vehicleCouting->process(); } key = cvWaitKey(1); } delete vehicleCouting; delete blobTracking; delete bgs; cvDestroyAllWindows(); cvReleaseCapture(&capture); return 0; } ``` Release Notes: -------------- * Version 1.0.0: First version.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：