SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

02/24/2020
by   Zechen Liu, et al.
0

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird's eye view evaluation. The code will be made publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 8

research
04/16/2019

Objects as Points

Detection identifies objects as axis-aligned boxes in an image. Most suc...
research
06/19/2019

Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss

Three-dimensional object detection from a single view is a challenging t...
research
11/30/2020

Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation

Monocular 3D object detection is a promising research topic for the inte...
research
08/31/2020

Reinforced Axial Refinement Network for Monocular 3D Object Detection

Monocular 3D object detection aims to extract the 3D position and proper...
research
07/19/2018

Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks

We consider the task of estimating the 3D orientation of an object of kn...
research
07/05/2020

A Systematic Evaluation of Object Detection Networks for Scientific Plots

Are existing object detection methods adequate for detecting text and vi...

Please sign up or login with your details

Forgot password? Click here to reset