Disentangling Monocular 3D Object Detection: From Single to Multi-Class Recognition
- 18 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (3) , 1219-1231
Abstract
In this paper we introduce a method for multi-class, monocular 3D object detection from a single RGB image, which exploits a novel disentangling transformation and a novel, self-supervised confidence estimation method for predicted 3D bounding boxes. The proposed disentangling transformation isolates the contribution made by different groups of parameters to a given loss, without changing its nature. This brings two advantages: i) it simplifies the training dynamics in the presence of losses with complex interactions of parameters, and ii) it allows us to avoid the issue of balancing independent regression terms. We further apply this disentangling transformation to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. We also critically review the AP metric used in KITTI3D and resolve a flaw which affected and biased all previously published results on monocular 3D detection. Our improved metric is now used as official KITTI3D metric. We provide extensive experimental evaluations and ablation studies on the KITTI3D and nuScenes datasets, setting new state-of-the-art results. We provide additional results on all the classes of KITTI3D as well as nuScenes datasets to further validate the robustness of our method, demonstrating its ability to generalize for different types of objects.Keywords
This publication has 45 references indexed in Scilit:
- Multi-view 3D Object Detection Network for Autonomous Driving2017
- Deep MANTA: A Coarse-to-Fine Many-Task Network for Joint 2D and 3D Vehicle Analysis from Monocular Image2017
- 3D Bounding Box Estimation Using Deep Learning and Geometry2017
- Reconstructing vehicles from a single image: Shape priors for road scene understanding2017
- Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection2017
- Deep Residual Learning for Image Recognition2016
- Monocular 3D Object Detection for Autonomous Driving2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Data-driven 3D Voxel Patterns for object category recognition2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009