Research map / Detection and segmentation / 3D detection and driving
Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network
Yousef Atoum, Joseph Roth, Michael Bliss, Wende Zhang, Xiaoming Liu
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 presence confidence score learning to the coupler detector (ablation) | DCNN · Coupler detection (CVD 3-7 m) | 2D pixel error: A clear margin of 20~45 in pixel errors | Improved |
| use three TCNN networks instead of one for tracking (ablation) | TCNN tracking · Trailer coupler database (CVD 0 m) | x-y plane error: 19.9 cm -> 2.4 cm | Improved |
| use two TCNNs instead of one (ablation) | TCNN tracking · Trailer coupler database (CVD 0 m) | x-y plane error: 19.9 cm -> 4.2 cm | Improved |
| add a fourth TCNN beyond three (ablation) | TCNN tracking · Trailer coupler database (CVD 0 m) | x-y plane error: 2.4 cm -> 2.3 cm | No clear effect |
| estimate contour with CCNN instead of CNN polynomial fitting | contour estimation · Coupler contour estimation (20 px) | precision: 75% -> 92% | Improved |
| estimate contour with CCNN instead of ASM fitting | contour estimation · Coupler contour estimation (20 px) | precision: 63% -> 92% | Improved |
| approach the coupler (smaller distance) for height estimation | height estimators R1-R5 · Height label set (5-fold CV) | absolute mean height error: 0.85 -> 0.45 cm | Improved |
| fuse CCNN contour center with TCNN3 estimate in the full system | Multiplexer-CNN · Trailer coupler database | x-y plane error: 2.4 cm -> 1.4 cm | Improved |
| activate CCNN near the coupler (CVD under 1 m) | Multiplexer-CNN · System speed | FPS: 18.9 -> 11.4 | Hurt |
| use multiple scale-specific TCNNs instead of KCF or C-COT single trackers | coupler tracking · Trailer coupler database | x-y plane error | Improved |
Closest papers by meaning
- RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving (ECCV 2020 · similarity 0.83)
- MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues (NeurIPS 2023 · similarity 0.83)
- 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (TPAMI 2017 · similarity 0.82)
- MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023 · similarity 0.82)
- Stereo R-CNN Based 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.82)
- DALDet: Depth-Aware Learning Based Object Detection for Autonomous Driving (AAAI 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.
