AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving

Peiliang Li, Tong Qin, andShaojie Shen

ECCV 2018 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 157 citations (OpenAlex)

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 changedWhereMeasuredEffect
add feature observation to semantic measurement (ablation)semantic 3D object tracking · KITTI tracking, easy objectsAP_bv IoU 0.25: 63.12 -> 76.23Improved
add motion model to semantic measurement (ablation)semantic 3D object tracking · KITTI tracking, hard objectsAP_bv IoU 0.25: 53.18 -> 58.84Improved
add motion model to semantic plus feature (ablation)semantic 3D object tracking · KITTI tracking, hard objectsAP_bv IoU 0.25: 66.18 -> 70.85Improved
add motion model to semantic plus feature (ablation)semantic 3D object tracking · KITTI tracking, easy objectsAP_bv IoU 0.5: 48.82 -> 46.96Hurt
add point cloud alignment to S+F+M (ablation)semantic 3D object tracking · KITTI tracking, easy objectsAP_bv IoU 0.25: 77.87 -> 88.07Improved
add point cloud alignment to S+F+M (ablation)semantic 3D object tracking · KITTI tracking, easy objectsAP_3d IoU 0.5: 40.50 -> 48.51Improved
add point cloud alignment to S+F+M (ablation)semantic 3D object tracking · KITTI tracking, hard objectsAP_3d IoU 0.5: 34.59 -> 34.54No clear effect
add feature observation to semantic measurement (ablation)semantic 3D object tracking · KITTI trackingruntime (ms): 120 -> 170Hurt
add motion model to semantic measurement (ablation)semantic 3D object tracking · KITTI trackingruntime (ms): 120 -> 121No clear effect
full system versus 3DOP stereo detectorS+F+M+P · KITTI tracking, easy objectsAP_3d IoU 0.5: 53.73 vs 48.51Hurt
full system versus 3DOP stereo detectorS+F+M+P · KITTI tracking, easy objectsAP_bv IoU 0.25: 81.34 -> 88.07Improved
full system versus 3DOP stereo detectorS+F+M+P · KITTI trackingruntime (ms): 1200 -> 173Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy