suyogduttjain/fusionseg
Video Object Segmentation
This helps automatically isolate and track specific objects across video footage. You provide a video, and it outputs a sequence of images where the object of interest is clearly segmented from its background, frame by frame. This is useful for researchers in computer vision or anyone needing to analyze object movement or presence in video recordings.
124 stars. No commits in the last 6 months.
Use this if you need to automatically segment and track a generic object throughout an entire video.
Not ideal if you require interactive or manual control over the segmentation process, or if your use case is commercial without prior approval.
Stars
124
Forks
46
Language
C++
License
—
Category
Last pushed
Jul 09, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/suyogduttjain/fusionseg"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRBonn/lidar-bonnetal
Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving
JonasSchult/Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet,...
nsavinov/semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
PRBonn/LiDAR-MOS
(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting...
yanx27/2DPASS
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) :fire: