Research map / Video / Video segmentation and tracking
Event-Aided Time-To-Collision Estimation for Autonomous Driving
Jinghang Li, Bangyan Liao, Xiuyuan Lu, Peidong Liu, Shaojie Shen, Yi Zhou
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 |
|---|---|---|---|
| initialize CMax with the proposed robust linear solver (ablation) | CMax · Synthetic Suburban_Const_Vel | runtime (s): 1.37 -> 0.82 s; error 3.76% -> 3.25% | Improved |
| initialize CMax with the proposed linear solver on real slider and FCWD data (ablation) | CMax · Slider_500 | e_TTC: 4.18% -> 4.18% | No clear effect |
| use the proposed geometric measurement instead of raw normal flow in the initializer (ablation) | Robust linear solver · Synthetic sequences | relative TTC error | Improved |
| use time-variant affine model instead of constant or simplified affine model (ablation) | Event-based TTC model fitting · Image of warped events contrast | IWE contrast | Improved |
| use event-based least-squares registration instead of CMax | TTC estimation · Synthetic Suburban_Acc | runtime (s): 1.32 -> 0.01 s; error 5.06% -> 3.58% | Improved |
| use proposed method instead of CMax on real FCWD data | TTC estimation · FCWD 1 | e_TTC: 2.42% -> 9.84% | Hurt |
| increase lateral offset of preceding vehicle beyond 3 m (ablation) | Proposed method · Synthetic with lateral offset | relative TTC error: below 10% for offsets under 3 m | Hurt |
Closest papers by meaning
- Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving Cars (CVPR 2018 · similarity 0.87)
- Event-based Optical Flow Using Spatio-temporal Registration (TPAMI 2026 · similarity 0.87)
- EventDrive: Event Cameras for Vision-Language Driving Intelligence (CVPR 2026 · similarity 0.87)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.86)
- Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras (CVPR 2025 · similarity 0.84)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.84)
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.
