AI Paper Atlas

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

Joint Monocular 3D Vehicle Detection and Tracking

Hou-Ning Hu, Qi-Zhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krahenbuhl, Trevor Darrell, Fisher Yu

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 260 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 deep feature correlation to association (ablation)KF3D tracker · GTA trackingMOTA / FN: 69.616 -> 69.843 MOTA; FN 21.298 -> 18.547Improved
add depth-order matching and occlusion-aware association (ablation)KF3D tracker without deep feature · GTA trackingmismatches (MM): 17480 -> 16042Improved
add depth-order matching and occlusion-aware association (ablation)KF3D tracker with deep feature · GTA trackingmismatches (MM): 27639 -> 25860Improved
replace Kalman filter with LSTM motion model (ablation)full tracker · GTA trackingMOTA: 70.126 -> 70.439Improved
replace Kalman filter with LSTM motion model (ablation)3D estimation · GTA 3D IoU AP (Easy, AP70)3D IoU AP70: 6.14 -> 7.89Improved
add Kalman filter smoothing over single-frame estimation (ablation)3D estimation · GTA 3D IoU AP (Easy, AP70)3D IoU AP70: 6.13 -> 6.14No clear effect
use 3D motion model instead of 2D (ablation)tracker without deep feature or order · GTA tracking (100m)MOTA: 57.042 -> 69.616Improved
predict projection of 3D box center instead of using 2D box center (ablation)tracking pipeline · KITTI training setIDS / MOTA: IDS 315 -> 190; MOTA 91.06 -> 91.58Improved
increase depth-module training data from 1% to 100% (ablation)3D box estimation · GTAAbs Rel: 0.258 -> 0.112Improved
use ground-truth camera pose instead of Mono-VO pose (ablation)tracker · KITTIMOTA: 71.079 -> 71.215No clear effect
add location-based matching and reduce max-age from 30 to 20 (ablation)tracker · KITTI (appendix)MOTA: 89.93 -> 90.97Improved
monocular 3D tracker versus LiDAR-centric baseline at 30mproposed tracker · Argoverse val (30m)MOTA: 73.02 -> 77.93Improved

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