FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

05/17/2021
by   Yi Wei, et al.
6

In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as supervision signals. However, annotating large datasets requires huge human efforts, especially for 3D area. To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations. Our method consists of two stages: coarse 3D segmentation and 3D bounding box estimation. For the first stage, a context-aware adaptive region growing algorithm is designed to segment objects based on 2D bounding boxes. Leveraging predicted segmentation masks, we develop an anti-noise approach to estimate 3D bounding boxes in the second stage. Finally 3D pseudo labels generated by our method are utilized to train a 3D detector. Independent of any 3D groundtruth, FGR reaches comparable performance with fully supervised methods on the KITTI dataset. The findings indicate that it is able to accurately detect objects in 3D space with only 2D bounding boxes and sparse point clouds.

READ FULL TEXT

page 1

page 3

page 5

page 6

07/28/2020

Weakly Supervised 3D Object Detection from Point Clouds

A crucial task in scene understanding is 3D object detection, which aims...
03/29/2022

MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator

Manually annotating 3D point clouds is laborious and costly, limiting th...
04/02/2021

Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation

We address the problem of weakly-supervised semantic segmentation (WSSS)...
04/25/2022

Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night

Provident detection of other road users at night has the potential for i...
03/25/2020

Safety-Aware Hardening of 3D Object Detection Neural Network Systems

We study how state-of-the-art neural networks for 3D object detection us...
04/09/2019

Embryo staging with weakly-supervised region selection and dynamically-decoded predictions

To optimize clinical outcomes, fertility clinics must strategically sele...
07/13/2018

TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

This work provides a simple approach to discover tight object bounding b...

Code Repositories

FGR

[ICRA 2021] FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection


view repo