This repo uses YOLOv5 and DeepSORT to implement object tracking algorithm. Also using TensorRTX to transform model to engine, and deploying all code on the NVIDIA Xavier with TensorRT further.

This repo is a C++ version of yolov5_deepsort_tensorrt. Packing all C++ programs into .so files, using Python script to call C++ programs further.

Using camera calibration and PnP to translate Pixel Coordinates System 2D coordinate point (u, v) to World Coordinate System 3D coordinate point (X, Y, Z).

This repo introduces how to integrate Tensorflow framework into ROS with object detection API.