MonoEF: Extrinsic Parameter Free Monocular 3D Object Detection
- 21 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 10114-10128
Abstract
Monocular 3D object detection is an important task in autonomous driving. It can be easily intractable where there exists ego-car pose change w.r.t. ground plane. This is common due to the slight fluctuation of road smoothness and slope. Due to the lack of insight in industrial application, existing methods on open datasets neglect the camera pose information, which inevitably results in the detector being susceptible to camera extrinsic parameters. The perturbation of objects is very popular in most autonomous driving cases for industrial products. To this end, we propose a novel method to capture camera pose to formulate the detector free from extrinsic perturbation. Specifically, the proposed framework predicts camera extrinsic parameters by detecting vanishing point and horizon change. A converter is designed to rectify perturbative features in the latent space. By doing so, our 3D detector works independent of the extrinsic parameter variations and produces accurate results in realistic cases, e.g., potholed and uneven roads, where almost all existing monocular detectors fail to handle. Experiments demonstrate our method yields the best performance compared with the other state-of-the-arts by a large margin on both KITTI 3D and nuScenes datasets.Keywords
Funding Information
- National Key R&D Program of China (2018YFC1900700)
- National Natural Science Foundation of China (61772340)
This publication has 56 references indexed in Scilit:
- End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networksThe International Journal of Robotics Research, 2017
- 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
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- 3D Object Proposals Using Stereo Imagery for Accurate Object Class DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks2017
- Robust object proposals re-ranking for object detection in autonomous driving using convolutional neural networksSignal Processing: Image Communication, 2017
- Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection2017
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- Monocular 3D Object Detection for Autonomous Driving2016