yolo

Introduction

YOLO, whose full name is you only look once, refers to the ability to identify the class and location of objects in a diagram by browsing only once, as named in a 2016 research paper by Redmon et al. YOLO implements real-time object detection used in cutting-edge technologies such as self-driving cars. This project is implemented under openeuler 22.03 via libtorch and uses the ros2-foxy framework to publish topics under.

Software Architecture

Software architecture description https://pjreddie.com/darknet/yolo/

yolo
├── 3rdparty
│ ├── argcomplete-1.11.1
│ ├── attrs-21.2.0
│ ├─ catkin_pkg-0.4.22
│ ├─ coverage5.4
│ ├── Cython-0.29.24
│ ├─ distlib-0.3.3
│ ├── docutils-0.16
│ ├── empy-3.3.4
│ ├─ importlib_metadata-3.8.0
│ ├─ iniconfig-1.1.1
│ ├── lark-1.0.0
│ ├─ more-itertools-5.0.0
│ ├── notify2-0.3.1
│ ├─ numpy-1.21.2
│ ├─ packaging-21.3
│ ├── pluggy-1.0.0
│ ├── py-1.11.0
│ ├── pyparsing-2.4.7
│ ├── pytest-6.2.5
│ ├── pytest-cov-3.0.0
│ ├── pytest-repeat-0.9.1
│ ├── pytest-rerunfailures-10.2
│ ├── pytest-runner-5.3.1
│ ├── python-dateutil-2.8.1
│ ├── PyYAML-5.4
│ ├── setuptools-50.0.0
│ ├── setuptools_scm-4.1.2
│ ├── six-1.15.0
│ ├── toml-0.10.2
│ ├─ typing_extensions-3.7.4
│ ├─ vcstools-0.1.42
│ ├── wheel-0.33.0
│ └── zipp-1.0.0
├── build_tools
│ └── colcon
└─ workspace
    └─ src
        ├─ ament
        ├── eclipse-cyclonedds
        ├── eProsima
        ├─ osrf
        ├─ ros
        ├─ ros2
        ├─ ros-perception
        ├─ ros-planning
        ├─ ros-tooling
        ├─ ros-tracing
        ├─ ros-visualization
        ├─ yolov3_ros2
        └─ temp_3rdparty
            ├─ eigen-3.3.7
            ├─ flann-1.9.1
            ├── libtorch
            ├── opencv-3.4.16
            └── pcl-1.12

installation tutorial

1. Download the rpm package

wget https://117.78.1.88/build/home:voladorL:branches:openEuler:22.03:LTS/standard_x86_64/x86_64/yolov3/yolov3-1.0.0-1.oe2203.x86_ 64.rpm

2. Install the rpm package

sudo rpm -ivh yolov3-1.0.0-1.oe2203.x86_64.rpm --nodeps --force

Instructions for use

After the installation is complete, the following output detectnode will be available in /opt/ros/foxy/lib/yolov3_ros2 directory, which means the installation is successful

cd /opt/ros/foxy
source setup.sh
rviz2#open rviz

Add components Image and MarkerArray, change Fixed Frame to base_link Modify various configuration file paths to absolute paths on your own system

cd /opt/ros/foxy
source setup.sh
ros2 run yolov3_ros2 detectnode --ros-args -p parameterPath:=/home/l/ros2/yolov3-ros2/yolov3-1.0.0/workspace/src/yolov3_ros2/config/ parameters.txt#Remember to change the path to your own parameters.txt parameters file

Add topics according to the topics in the parameters file parameters.txt

Contribution

1. Fork the repository
2. Create Feat_xxx branch
3. Commit your code
4. Create Pull Request

Gitee Feature

1. You can use Readme_XXX.md to support different languages, such as Readme_en.md, Readme_zh.md
2. Gitee blog blog.gitee.com
3. Explore open source project https://gitee.com/explore
4. The most valuable open source project GVP
5. The manual of Gitee https://gitee.com/help
6. The most popular members https://gitee.com/gitee-stars/