1 Star 3 Fork 2

wythe_qiu / reflective-clothes-detect

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README

reflective-clothes-detect and dataset

工作服(反光衣)检测数据集

  • author is leilei
  • reflective-clothes-detect qq群: 980489677
  • 如果此项目对您有所帮助,请给个star,您的star是对我的鼓励!

Some details

  • reflective-clothes-detect-dataset (with xml annotations 1083) download: BaiDuYunPan 提取码->(dooh)
  • yolov5s's weight is in reflective-clothes-detect-dataset !

Applicable instructions

  1. download BaidDuYunPan's data and weight file
  2. put yolov5s's weight file into yolov5 folder
  3. cd yolov5, and excuting an order:
    python detect.py --source ***/aaa.jpg --weights ./best.pt
  4. convert VOC2021 to YOLO format:
    call yolov5's voc_label_Re.py

How to use dataset?

  • We annotate the reflective-clothes-detect-dataset as Pascal VOC format:

    --VOC2021(反光衣)
        --Annotations (xml_num: 1083)
        --ImageSets(Main)
        --JPEGImages (image_num: 1083)
    
        --images (yolov5 need, the same with JPEGImages)
        --labels (yolov4-5 need)
        --txt_yolov5 (yolov5 need 2021_train.txt)
        --2021_train.txt (yolov4 need)
    
        --yolov5_weight (yolov5s's weight)
    
        --label_name: reflective_clothes、other_clothes
  • If you want to crawl some images

    Please refer to this crawler code on github:
    https://github.com/gengyanlei/fire-detect-yolov4 -> crawl_baidu.py

实际应用(Practical application)

  • 基于SHWD数据集进行安全帽-反光衣-整体人 5类标注训练yolov4-yolov5,实现施工区域or危险区域检测
  • Based on the SHWD data set, perform the five-category labeling training yolov4-yolov5 for helmet-reflective clothing-holistic people to achieve detection of construction areas or dangerous areas.

demo

  • ./result:
new_demo
demo1
----
demo2
----

How to expand reflective clothing data?

  1. Based on the trained yolov4 model of 1083 reflective clothing images, expand the reflective clothing category of the SHWD data set;
  2. Based on the data set expanded by 0 steps, train yolov4.

如何基于此项目进行反光衣数据扩充,并进行自动标注?

  1. 基于1083张反光衣图像训练好的yolov4模型,对SHWD数据集进行反光衣类别扩充;
  2. 基于0步骤扩充得到的数据集,训练yolov4.

Cite

  • yolov5 (supports empty-labeled images)
  • yolov4 (supports empty-labeled images)
  • 博客blog
  • 本数据仅学术探索!!!

Other

空文件

简介

reflective-clothes-detect-dataset、helemet detection、工作服(反光衣)检测数据集、安全帽检测、施工人员穿戴检测 展开 收起
取消

发行版

暂无发行版

贡献者

全部

近期动态

加载更多
不能加载更多了
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/wythe_qiu/reflective-clothes-detect.git
git@gitee.com:wythe_qiu/reflective-clothes-detect.git
wythe_qiu
reflective-clothes-detect
reflective-clothes-detect
master

搜索帮助

344bd9b3 5694891 D2dac590 5694891