yolov5+Realsence+DeepSense D435i

Create Environment

# create conda environment
conda crate -n <Any name> python=3.8
conda activate <Any name>

# change directory
cd personalize_hand

# clone yolov5
git clone https://github.com/ultralytics/yolov5/tree/aa1859909c96d5e1fc839b2746b45038ee8465c9

# install requirements
pip install -r requirements.txt

# change yolov5 directory
cd yolov5

$ install requirements
pip install -r requirements.txt

Module used

yolov5

https://github.com/ultralytics/yolov5

Yolov5 + Deep Sort with Pytorch

https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch

DeepSense D435i

https://www.intelrealsense.com/depth-camera-d435i/

program introduction

realsence_track.py

We have introduced yolov5 and deepsort from the information acquired by deepsense.

The following parameters are output from the console

frame_idx, id, c, names[c], bbox_left, bbox_top, bbox_w, bbox_h, center_x, center_y,depth

Image displayed

Console Image

Execution method

python realsence_track.py

realsence_track_person.py

Only detect people and output to the console

The following parameters are output from the console

frame_idx, id, c, 'person', bbox_left, bbox_top, bbox_w, bbox_h, center_x, center_y,depth

Execution method

python realsence_track_person.py