MasterHow/PanoFlow
[T-ITS 2023] PanoFlow: Learning Optical Flow for Panoramic Images
This project helps self-driving car engineers and researchers analyze how objects in a 360-degree panoramic view are moving. It takes in pairs of consecutive panoramic images of a city scene, identifies specific elements like vehicles, pedestrians, or roads, and outputs a visual representation of their motion, known as optical flow. This allows for detailed understanding of movement dynamics in complex urban environments.
No commits in the last 6 months.
Use this if you need to accurately track and visualize movement within wide-angle, panoramic video data, especially for autonomous navigation or environmental monitoring in cityscapes.
Not ideal if your primary interest is standard, non-panoramic video analysis or if you don't require detailed semantic segmentation alongside motion estimation.
Stars
57
Forks
3
Language
Python
License
MIT
Category
Last pushed
Oct 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/MasterHow/PanoFlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.