update

README.md

@@ -1,6 +1,16 @@
-# tracking_ros [![rostest](https://github.com/ojh6404/tracking_ros/actions/workflows/docker_build.yml/badge.svg)](https://github.com/ojh6404/tracking_ros/actions/workflows/docker_build.yml) [![peripheral](https://github.com/ojh6404/tracking_ros/actions/workflows/python_check.yml/badge.svg)](https://github.com/ojh6404/tracking_ros/actions/workflows/python_check.yml)
+# tracking_ros  [![python_check](https://github.com/ojh6404/tracking_ros/actions/workflows/python_check.yml/badge.svg)](https://github.com/ojh6404/tracking_ros/actions/workflows/python_check.yml)
 
-ROS package for [Detic](https://github.com/facebookresearch/Detic). Run on both CPU and GPU, GPU is way performant, but work fine also with CPU (take few seconds to process single image).
+ROS package for tracking, using [SAM](https://github.com/facebookresearch/Detic), [Cutie](https://github.com/hkchengrex/Cutie.git), [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO.git), [DEVA](https://github.com/hkchengrex/Tracking-Anything-with-DEVA.git).
+
+## Setup
+
+### Prerequisite
+This package is build upon
+- ROS1 (Noetic)
+- catkin virtualenv (python>=3.9 used for DEVA)
+- (Optional) docker and nvidia-container-toolkit (for environment safety)
+
+## Install
 
 ## step1: build docker container
 *Ofcourse you can build this pacakge on your workspace and launch as normal ros package. But for those using CUDA, the following docker based approach might be safer and easy.*