research
Thirty-Six Vehicle Points Replaced the Roadside Ruler
A per-frame keypoint template estimates monocular vehicle speed without fixed camera calibration or roadway reference marks.
Summary
A per-frame keypoint template estimates monocular vehicle speed without fixed camera calibration or roadway reference marks.
The method detects 36 vehicle keypoints, updates a homography each frame and compares keypoint-only tracking with warped optical flow. Across more than 400 roadside and overhead clips spanning 30 to 100 miles per hour, warped flow produced mean absolute errors of 15.0 and 9.7 percent on two datasets; trimming edge-of-frame outliers improved those to 11.7 and 7.6 percent. The remaining errors are material for enforcement, so the result supports low-cost estimation research rather than automatic evidentiary reliability.
Why it matters
A per-frame keypoint template estimates monocular vehicle speed without fixed camera calibration or roadway reference marks.
Limits and context
- The method detects 36 vehicle keypoints, updates a homography each frame and compares keypoint-only tracking with warped optical flow.
Key claims
A per-frame keypoint template estimates monocular vehicle speed without fixed camera calibration or roadway reference marks.
Qualification: The method detects 36 vehicle keypoints, updates a homography each frame and compares keypoint-only tracking with warped optical flow.
Evidence: source-2026-08-18-014
Sources
- arXiv preprint 2608.16785arXiv · primary research
Corrections
No corrections have been recorded for this story.