# 08recognition-parking_plot_number

**Repository Path**: linClubs/recognition-parking_plot_number

## Basic Information

- **Project Name**: 08recognition-parking_plot_number
- **Description**: 使用yolov5-v6先完成车位号的检测与识别，然后采用opencv-dnn-cpp模块部署；c++环境，部署只需要要opencv库
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2022-02-09
- **Last Updated**: 2023-08-25

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 基于yolov5-opencv-dnn-cpp的车位号识别系统

## recognition-parking_plot_number

使用yolov5-v6先完成车位号的检测与识别，然后采用opencv-dnn-cpp模块部署；c++环境，部署只需要要opencv库

## 1  版本推荐
### 1.1 使用opencv模块部署yolov5-6.0版本
	基于6.0版本的yolov5:https://github.com/ultralytics/yolov5

### 1.2 OpenCV>=3,本人测试代码是在opencv3.4.12版本

  [OpenCV视频安装教程](https://www.bilibili.com/video/BV17K4y1h7uK/)


### 1.3 导出onnx模型需要将opset设置成12（原来默认的是13，在opencv下面会报错，原因未知）
 
	python path/to/export.py --weights yolov5s.pt --img [640,640] --opset 12 --include onnx

## 2 测试代码用的detect_img.cpp

### 2.1 直接编译运行
	
	mkdir build
	cd build
	cmake ..
	make
	./detect_img
	
### 2.2  如果要运行detect_avi.cpp与detect_img2.cpp

  需要修改图片（视频）源的路径与yolo检测模型onnx的路径，建议直接用绝对路径

## 3 车位号检测效果

  [检测结果图一链接](https://gitee.com/linClubs/recognition-parking_plot_number/blob/master/image/result.jpg)

  [检测结果图二链接](https://gitee.com/linClubs/recognition-parking_plot_number/blob/master/image/result_1.png)

  [检测结果图三链接](https://gitee.com/linClubs/recognition-parking_plot_number/blob/master/image/result_2.png)