Skip to content

yolov5 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

License

Notifications You must be signed in to change notification settings

maikelaolin/Chinese_license_plate_detection_recognition

This branch is 9 commits behind we0091234/Chinese_license_plate_detection_recognition:main.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Apr 4, 2024
5342e5b · Apr 4, 2024

History

98 Commits
Aug 29, 2023
Sep 15, 2022
Apr 4, 2024
Mar 20, 2023
Mar 8, 2023
Mar 6, 2023
Feb 28, 2024
Sep 15, 2022
May 8, 2023
Mar 20, 2023
Sep 15, 2022
Mar 27, 2023
Sep 15, 2022
Apr 4, 2024
Feb 20, 2023
Feb 4, 2023
Feb 4, 2023
Mar 27, 2023
Nov 18, 2022
Sep 15, 2022
Mar 24, 2023
Mar 20, 2023
Dec 3, 2022
Sep 15, 2022
Aug 29, 2023
Sep 15, 2022
Mar 6, 2023

Repository files navigation

What's New

2022.12.04 车辆和车牌一起检测看这里车辆系统

yolov8 车牌检测+识别

yolov7 车牌检测+识别

安卓NCNN

最全车牌识别算法,支持12种中文车牌类型

环境要求: python >=3.6 pytorch >=1.7

图片测试demo:

直接运行detect_plate.py 或者运行如下命令行:

python detect_plate.py --detect_model weights/plate_detect.pt  --rec_model weights/plate_rec_color.pth --image_path imgs --output result

测试文件夹imgs,结果保存再 result 文件夹中

视频测试demo 2.MP4 提取码:41aq

python detect_plate.py --detect_model weights/plate_detect.pt  --rec_model weights/plate_rec_color.pth --video 2.mp4

视频文件为2.mp4 保存为result.mp4

车牌检测训练

车牌检测训练链接如下:

车牌检测训练

车牌识别训练

车牌识别训练链接如下:

车牌识别训练

支持如下:

  • 1.单行蓝牌
  • 2.单行黄牌
  • 3.新能源车牌
  • 4.白色警用车牌
  • 5.教练车牌
  • 6.武警车牌
  • 7.双层黄牌
  • 8.双层白牌
  • 9.使馆车牌
  • 10.港澳粤Z牌
  • 11.双层绿牌
  • 12.民航车牌

Image

部署

1.安卓NCNN

2.onnx demo 百度网盘: k874

python onnx_infer.py --detect_model weights/plate_detect.onnx  --rec_model weights/plate_rec_color.onnx  --image_path imgs --output result_onnx

3.tensorrt 部署见tensorrt_plate

4.openvino demo 版本2022.2

 python openvino_infer.py --detect_model weights/plate_detect.onnx --rec_model weights/plate_rec.onnx --image_path imgs --output result_openvino

References

联系

或者加qq群:871797331(已满) 837982567(二群) 询问

Image

About

yolov5 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.0%
  • Shell 2.4%
  • Other 0.6%