Use YOLOv4 for real-time multi-object tracking, which can be applied to various fields such as monitoring systems and traffic flow analysis. 

 

[Instructions]

 

 

1_YOLOv4-Multiple-Object-Tracking.ipynb

 

os.system("start src/darknet/build/darknet/x64/yolo_console_dll.exe data/coco.names model/yolov4.cfg model/yolov4.weights data/test.mp4 true")

 

  • data/coco.names : Define the category name. 
  • model/yolov4.cfg : The cfg of the model includes the parameter setting of the model structure and so on. 
  • model/yolov4.weights : Model files. 
  • data/test.mp4 : Tested videos. 
  • true : Use kalman_filter, applied to a fixed camera. 

 

If you want to track your own objects, you can train the object detection model through other solutions, and then track them through this solution. 

 

 

inference.png

 

This SDK is built in AppForAI - AI Dev Tools.

 

Purchase license separately: USD 600, permanent authorization, single APP authorization, single machine authorization, one-year activation, one-year download, one-year update, one-year email technical support.