Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding

2020-05-27 · Yunlei Tang, Sebastian Dorn, Chiragkumar Savani

Localizing objects in 3D space and understanding their associated 3D properties is challenging given only monocular RGB images. The situation is compounded by the loss of depth information during perspective projection. We present Center3D, a one-stage anchor-free approach, to efficiently estimate 3D location and depth using only monocular RGB images. By exploiting the difference between 2D and 3D centers, we are able to estimate depth consistently. Center3D uses a combination of classification and regression to understand the hidden depth information more robustly than each method alone. Our method employs two joint approaches: (1) LID: a classification-dominated approach with sequential Linear Increasing Discretization. (2) DepJoint: a regression-dominated approach with multiple Eigen's transformations for depth estimation. Evaluating on KITTI dataset for moderate objects, Center3D improved the AP in BEV from $29.7\%$ to $42.8\%$, and the AP in 3D from $18.6\%$ to $39.1\%$. Compared with state-of-the-art detectors, Center3D has achieved the best speed-accuracy trade-off in realtime monocular object detection.

📄 PDF Abstract BibTeX arXiv:2005.13423

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object Detection Depth Estimation General Classification Monocular 3D Object Detection object-detection Object Detection regression

Tracking Objects as Points

2020-04-02 · ECCV 2020 8 · Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detectio…

Multi-Object Tracking Multiple Object Tracking object-detection Object Detection

M3DSSD: Monocular 3D Single Stage Object Detector

2021-03-24 · CVPR 2021 1 · Shujie Luo, Hang Dai, Ling Shao, Yong Ding

In this paper, we propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. Current anchor-based monocular 3D object detection methods suffer from feature mis…

3D Object Detection Depth Estimation Depth Prediction Monocular 3D Object Detection+3

MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts

2023-02-21 · Zizhang Wu, Yuanzhu Gan, Lei Wang, Guilian Chen 외

Monocular 3D object detection reveals an economical but challenging task in autonomous driving. Recently center-based monocular methods have developed rapidly with a great trade-off between speed and accuracy, where they…

3D Object Detection Autonomous Driving Depth Estimation Monocular 3D Object Detection+3

Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

2019-04-02 · CVPR 2019 6 · Jason Ku, Alex D. Pon, Steven L. Waslander

We present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction. First, using the fundamental relations of a pinhole camera model, detections from a mature 2D object detector …

3D Object Detection Monocular 3D Object Detection Object object-detection+2

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

2021-04-22 · Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin

Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. It is much more challenging than conventional 2D cases due to its inherent ill-posed property, which is mai…

3D Object Detection Autonomous Driving Monocular 3D Object Detection Object+2