Research map / Detection and segmentation / Open-set and few-shot detection
Full-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of Polarization
Ning Li, Yongqiang Zhao, Quan Pan, Seong G. Kong, Jonathan Cheung-Wai Chan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add horizon constraint (ablation) | zero-distribution road detection · LDDRS | IoU (%): 67.52 -> 88.69 | Improved |
| add horizon constraint (ablation) | zero-distribution road detection · LDDRS | Running time (ms): 194 -> 67 | Improved |
| add DoP and edge constraints to AoP constraint (ablation) | zero-distribution road detection · LDDRS | IoU (%): 85.41 -> 88.69 | Improved |
| add DoP and edge constraints to AoP constraint (ablation) | zero-distribution road detection · LDDRS | Precision (%): 90.21 -> 93.48 | Improved |
| add DoP and edge constraints to AoP constraint (ablation) | zero-distribution road detection · LDDRS | Recall (%): 94.12 -> 94.50 | No clear effect |
| use HSV fusion instead of RGB fusion of polarization images | DeepLabv3+ · LDDRS | IoU (%): 86.90 -> 88.73 | Improved |
| use polarization fusion image instead of intensity image | DeepLabv3+ · LDDRS | IoU (%): 79.28 -> 88.73 | Improved |
| down-sample input 2 times (ablation) | proposed method · LDDRS | IoU (%): 88.69 -> 87.43 | Hurt |
| down-sample input 4 times (ablation) | proposed method · LDDRS | IoU (%): 88.69 -> 85.76 | Hurt |
| compare with DeepLabv3+ HSV fusion | proposed method · LDDRS | IoU (%): 88.73 -> 88.74 | No clear effect |
Closest papers by meaning
- PolarFormer: Multi-Camera 3D Object Detection with Polar Transformer (AAAI 2023 · similarity 0.83)
- Monocular BEV Perception of Road Scenes via Front-to-Top View Projection (TPAMI 2024 · similarity 0.83)
- Homography Guided Temporal Fusion for Road Line and Marking Segmentation (ICCV 2023 · similarity 0.83)
- Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts (CVPR 2024 · similarity 0.82)
- Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset (CVPR 2024 · similarity 0.81)
- Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing (NeurIPS 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
