tonysy/Deep-Feature-Flow-Segmentation
Deep Feature Flow for Video Semantic Segmentation
This project helps computer vision researchers efficiently identify and categorize objects frame-by-frame in video footage, even when objects are moving. It takes in video data, such as recordings of urban scenes, and outputs a detailed, pixel-level segmentation of everything present in each frame. Researchers focused on autonomous driving, robotics, or surveillance analysis would use this.
No commits in the last 6 months.
Use this if you need to perform semantic segmentation on video data, where accurately labeling every pixel in each frame by category is critical.
Not ideal if you are working with still images only, or if your primary goal is object detection rather than detailed pixel-level categorization.
Stars
35
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jun 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tonysy/Deep-Feature-Flow-Segmentation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.