guanfuchen/video_obj
基于视频的目标检测算法研究
This project helps researchers and practitioners in computer vision better understand and implement video object detection algorithms. It compiles and reviews various methods that overcome limitations of single-image detection, such as motion blur or small objects, by leveraging temporal information from video sequences. The outcome is a better ability to accurately identify and locate objects within video streams, which is useful for professionals working with video analytics or surveillance.
501 stars. No commits in the last 6 months.
Use this if you are developing or studying video object detection algorithms and need a comprehensive overview of existing techniques, relevant datasets, and academic papers.
Not ideal if you are looking for a ready-to-use software tool for immediate deployment of video object detection, as this project focuses on research and academic review.
Stars
501
Forks
100
Language
Python
License
—
Category
Last pushed
Aug 29, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/guanfuchen/video_obj"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
IBM/MAX-Object-Detector
Localize and identify multiple objects in a single image.
LSH9832/edgeyolo
an edge-real-time anchor-free object detector with decent performance
stephanecharette/DarkMark
Marking up images for use with Darknet.
amdegroot/ssd.pytorch
A PyTorch Implementation of Single Shot MultiBox Detector
aditya-vora/FCHD-Fully-Convolutional-Head-Detector
Code for FCHD - A fast and accurate head detector