Skip to content

基于YoloX目标检测+DeepSort算法实现多目标追踪Baseline

License

Notifications You must be signed in to change notification settings

Sharpiless/yolox-deepsort

Repository files navigation

项目简介:

使用YOLOX+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中。

代码地址(欢迎star):

https://github.com/Sharpiless/yolox-deepsort/

最终效果:

在这里插入图片描述

运行demo:

python demo.py

下载预训练模型:

Model size mAPtest
0.5:0.95
Speed V100
(ms)
Params
(M)
FLOPs
(G)
weights
YOLOX-s 640 39.6 9.8 9.0 26.8 onedrive/github
YOLOX-m 640 46.4 12.3 25.3 73.8 onedrive/github
YOLOX-l 640 50.0 14.5 54.2 155.6 onedrive/github
YOLOX-x 640 51.2 17.3 99.1 281.9 onedrive/github
YOLOX-Darknet53 640 47.4 11.1 63.7 185.3 onedrive/github

下载 yolox_s.pth 放到 weights 文件夹下

下载 https://github.com/Sharpiless/Yolov5-Deepsort/blob/main/deep_sort/deep_sort/deep/checkpoint/ckpt.t7 放到 deep_sort/deep_sort/deep/checkpoint 文件夹下

训练自己的模型:

训练好后放到 weights 文件夹下

调用接口:

创建检测器:

from AIDetector_pytorch import Detector

det = Detector()

调用检测接口:

result = det.feedCap(im)

其中 im 为 BGR 图像

返回的 result 是字典,result['frame'] 返回可视化后的图像

联系作者:

B站:https://space.bilibili.com/470550823

CSDN:https://blog.csdn.net/weixin_44936889

AI Studio:https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156

Github:https://github.com/Sharpiless

About

基于YoloX目标检测+DeepSort算法实现多目标追踪Baseline

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published