Skip to content

Hungarian algorithm + Kalman filter multitarget tracker implementation.

License

Notifications You must be signed in to change notification settings

cl886699/Multitarget-tracker

 
 

Repository files navigation

travis ci:

Multitarget-tracker

Hungarian algorithm + Kalman filter multitarget tracker implementation.

Demo Videos

  • MobileNet SSD and tracking for low resolution and low quality videos from car DVR:

Tracking:

  • Mouse tracking:

Tracking:

  • Motion Detection and tracking:

Motion Detection and tracking:

  • Multiple Faces tracking:

Multiple Faces tracking:

  • Simple Abandoned detector:

Simple Abandoned detector:

Parameters

  1. Background substraction: built-in Vibe, SuBSENSE and LOBSTER; MOG2 from opencv; MOG, GMG and CNT from opencv_contrib
  2. Foreground segmentation: contours
  3. Matching: Hungrian algorithm or algorithm based on weighted bipartite graphs
  4. Tracking: Linear or Unscented Kalman filter for objects center or for object coordinates and size
  5. Use or not local tracker (LK optical flow) to smooth trajectories
  6. Tracking for lost objects and collision resolving: built-in DAT or STAPLE; KCF, MIL, MedianFlow, GOTURN, MOSSE or CSRT from opencv_contrib
  7. Haar face detector from OpenCV
  8. HOG and C4 pedestrian detectors
  9. MobileNet SSD detector with inference from OpenCV and models from chuanqi305/MobileNet-SSD
  10. YOLO and Tiny YOLO detectors from https://pjreddie.com/darknet/yolo/ (inference from opencv_dnn or from https://github.com/AlexeyAB/darknet )
  11. Simple Abandoned detector

Build

  1. Download project sources
  2. Install CMake
  3. Install OpenCV (https://github.com/opencv/opencv) and OpenCV contrib (https://github.com/opencv/opencv_contrib) repositories
  4. Configure project CmakeLists.txt, set OpenCV_DIR.
  5. If opencv_contrib don't installed then disable options USE_OCV_BGFG=OFF, USE_OCV_KCF=OFF and USE_OCV_UKF=OFF
  6. If you want to use native darknet YOLO detector with CUDA + cuDNN then set BUILD_YOLO_LIB=ON
  7. Go to the build directory and run make

Usage:

       Usage:
         ./MultitargetTracker <path to movie file> [--example]=<number of example 0..6> [--start_frame]=<start a video from this position> [--end_frame]=<play a video to this position> [--end_delay]=<delay in milliseconds after video ending> [--out]=<name of result video file> [--show_logs]=<show logs> [--gpu]=<use OpenCL>
         ./MultitargetTracker ../data/atrium.avi -e=1 -o=../data/atrium_motion.avi
       Press:
       * 'm' key for change mode: play|pause. When video is paused you can press any key for get next frame.
       * Press Esc to exit from video

       Params: 
       1. Movie file, for example ../data/atrium.avi
       2. [Optional] Number of example: 0 - MouseTracking, 1 - MotionDetector, 2 - FaceDetector, 3 - PedestrianDetector, 4 - MobileNet SSD detector, 5 - YOLO OpenCV detector, 6 - Yolo Darknet detector
          -e=0 or --example=1
       3. [Optional] Frame number to start a video from this position
          -sf=0 or --start_frame==1500
       4. [Optional] Play a video to this position (if 0 then played to the end of file)
          -ef=0 or --end_frame==200
       5. [Optional] Delay in milliseconds after video ending
          -ed=0 or --end_delay=1000
       6. [Optional] Name of result video file
          -o=out.avi or --out=result.mp4
       7. [Optional] Show Trackers logs in terminal
          -sl=1 or --show_logs=0
       8. [Optional] Use built-in OpenCL
          -g=1 or --gpu=0

Thirdparty libraries

License

GNU GPLv3: http://www.gnu.org/licenses/gpl-3.0.txt

About

Hungarian algorithm + Kalman filter multitarget tracker implementation.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C 45.4%
  • C++ 45.0%
  • Cuda 6.8%
  • Makefile 1.9%
  • CMake 0.9%
  • Objective-C 0.0%