https://github.com/monsiw/object-detection-yolo

The project aims to use a trained model in the YOLO network to detect objects that will be detected by the robot structure with a computer on which ROS has been installed. ROS manages the individual packages used in the project.
https://github.com/monsiw/object-detection-yolo

darknet detection-model linux robotics ros ros-noetic yolov3

Last synced: 3 months ago
JSON representation

The project aims to use a trained model in the YOLO network to detect objects that will be detected by the robot structure with a computer on which ROS has been installed. ROS manages the individual packages used in the project.

• Host: GitHub
• URL: https://github.com/monsiw/object-detection-yolo
• Owner: monsiw
• Created: 2023-01-12T08:19:29.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2023-02-22T18:00:56.000Z (almost 2 years ago)
• Last Synced: 2024-08-01T03:16:45.118Z (6 months ago)
• Topics: darknet, detection-model, linux, robotics, ros, ros-noetic, yolov3
• Language: C
• Homepage:
• Size: 9.91 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Object Detection with Robotic Platform

An idea of this project is to implement the functionality object recognition on the Intel NUC10i5FNB computer, which is part of a car-like structure (image below). This robot moves using 4 wheels, where the two front wheels are controlled by a servo and the two rear wheels are powered by a motor with a nominal voltage of 12V each. The entire facility is powered by a 5000mAh Bashing lithium polymer battery by GensAce, which can be charged by connecting an external power supply to the dashboard. At the very top of the chassis, there is a HAMA camera for image recording. The board with the programmed controller accepts signals from the computer and distributes them to the wheels.





## Start

In the workspace you need to build your packages using


*catkin_make*


*source devel/setup.bash*

## Inference with *darknet_ros* package

In order to start inference of chosen model write *roslaunch darknet_ros darknet_ros.launch* in the terminal



 


## Robot movement 


*rosrun teleop_twist_keyboard teleop_twist_keyboard.py*



The keys represent the following maneuvers: 


• __*u*__  key is responsible for driving forward with the front wheels turned to the right, 


• __*i*__  key is responsible for moving forward with the front wheels in the starting position, 


• __*o*__  key is responsible for driving forward with the front wheels turned to the left, 


• __*j*__  key is responsible for turning the front wheels to the right, 


• __*k*__  key stops movement, 


• __*l*__  key is responsible for turning the front wheels to the left, 


• __*m*__  key is responsible for driving backwards with the front wheels turned to the right, 


• __*,*__  key is responsible for driving backwards with the front wheels in the starting position, 


• __*.*__  key is responsible for driving backwards with the front wheels turned to the left. 










With *rosrun rqt_graph rqt_graph* you should see the graph posted below 
 




## Citing

[1] Arguedas M., et al.: ROS OpenCV camera driver – https://github.com/OTL/cv_camera. 


[2] Baltovski T., et al.: teleop_twist_keyboard – https://github.com/ros-teleop/teleop_twist_keyboard. 


[3] Bjelonic M.: YOLO ROS: Real-Time Object Detection for ROS – https://github.com/leggedrobotics/darknet_ros.