OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
video-object-detection 开源项目推荐(45 个)
video-object-detection 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 45 个仓库Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
用于 CMU 的多摄像头监控视频对象检测和跟踪系统的开箱即用代码和模型。速度优化的 Faster-RCNN 模型。基于 Tensorflow。也支持 EfficientDet。WACVW'20
基于视频的目标检测算法研究
Using yolov3 & yolov4 weights objects are being detected from live video frame along with the measurement of the object from the camera without the support of any extra hardware device.
This is a list of awesome articles about object detection from video.
video detection papers
Video detection library
[ECCV-20] Official PyTorch implementation of HoughNet, a voting-based object detector.
该项目在 GitHub 上没有填写描述
Implementation of Mobile Video Object Detection with Temporally-Aware Feature Maps using PyTorch
A pytorch implementation of Detect and Track (https://arxiv.org/abs/1710.03958)
Building a Yolov8n model from scratch and performing object detection in optical remote sensing images and videos.
update some video object detection papers (视频目标检测论文和代码整理)
PyTorch implementation of Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
Sequence Level Semantics Aggregation for Video Object Detection
Spatial-Temporal Feature Transformation for Video Object Detection, MICCAI2021
Search for objects on video (possible with IP cameras)
A collection of some awesome video object detection series projects.
[WACV 2023] A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/video-object-detection。
- 该话题在 GitHub 上共有 45 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 7680 Star,覆盖 2 种主要语言,数据更新于 2026-11-10。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。