Skip to content

增加摄像头显示车辆人物数量 - #4582

Closed
heeyusike wants to merge 11 commits into
OpenHUTB:mainfrom
heeyusike:main
Closed

heeyusike wants to merge 11 commits into
OpenHUTB:mainfrom
heeyusike:main

Conversation

@heeyusike

Copy link
Copy Markdown
Contributor

修改概述:
优化事故检测模块,新增摄像头画面的车辆 / 人物实时计数、检测置信度显示,同时细化事故类型区分功能

修改的详细描述

1.调整core/detector.py中_calculate_accident函数:将原 “是否事故” 的布尔判断,升级为 “多车事故”“人车接触事故” 的类型区分;
2.优化detect_frame函数:在摄像头画面中新增 “行人 / 小车 / 卡车” 实时数量统计,同时给目标框标注增加检测置信度(保留 2 位小数);

经过了什么样的测试?

  1. . 操作系统
  2. Python版本等操作系统
  3. Python版本等

运行效果

动图、视频、截图等
a4878c02548e460ca825e2938d105c55

Refactor configuration management to support environment variables and improve readability.
Refactor main program for accident video detection with performance improvements, flexible configurations, and enhanced logging. Added support for recognizing people and vehicles.
Refactor processing functions for accident video recognition, adding distance calculation and box center retrieval.
Enhance accident detection with video saving and FPS display.
Refactor main program for driving accident video recognition tool with enhanced performance, flexible configuration, and improved logging. Added support for detecting people and vehicles.
优化了驾驶事故视频识别工具的性能和灵活性,支持命令行动态配置,替换print为日志模块,增强了用户交互体验和程序健壮性。
Enhance accident detection with type differentiation, confidence scoring, and target counting.
@donghaiwang

Copy link
Copy Markdown
Member

需要连接模拟器获取数据

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants