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

06/19/2019
by   Eskil Jörgensen, et al.
10

Three-dimensional object detection from a single view is a challenging task which, if performed with good accuracy, is an important enabler of low-cost mobile robot perception. Previous approaches to this problem suffer either from an overly complex inference engine or from an insufficient detection accuracy. To deal with these issues, we present SS3D, a single-stage monocular 3D object detector. The framework consists of (i) a CNN, which outputs a redundant representation of each relevant object in the image with corresponding uncertainty estimates, and (ii) a 3D bounding box optimizer. We show how modeling heteroscedastic uncertainty improves performance upon our baseline, and furthermore, how back-propagation can be done through the optimizer in order to train the pipeline end-to-end for additional accuracy. Our method achieves SOTA accuracy on monocular 3D object detection, while running at 20 fps in a straightforward implementation. We argue that the SS3D architecture provides a solid framework upon which high performing detection systems can be built, with autonomous driving being the main application in mind.

READ FULL TEXT

page 1

page 6

page 8

research
02/24/2020

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

Estimating 3D orientation and translation of objects is essential for in...
research
12/22/2022

Monocular 3D Object Detection using Multi-Stage Approaches with Attention and Slicing aided hyper inference

3D object detection is vital as it would enable us to capture objects' s...
research
11/21/2019

RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving

In this paper, we strive for solving the ambiguities arisen by the astou...
research
03/17/2015

3D Object Class Detection in the Wild

Object class detection has been a synonym for 2D bounding box localizati...
research
03/30/2021

Delving into Localization Errors for Monocular 3D Object Detection

Estimating 3D bounding boxes from monocular images is an essential compo...
research
04/22/2021

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

Monocular 3D object detection is an important task for autonomous drivin...
research
05/16/2019

Monocular Plan View Networks for Autonomous Driving

Convolutions on monocular dash cam videos capture spatial invariances in...

Please sign up or login with your details

Forgot password? Click here to reset