Accurate 3D Object Detection using Energy-Based Models

12/08/2020
by   Fredrik K. Gustafsson, et al.
0

Accurate 3D object detection (3DOD) is crucial for safe navigation of complex environments by autonomous robots. Regressing accurate 3D bounding boxes in cluttered environments based on sparse LiDAR data is however a highly challenging problem. We address this task by exploring recent advances in conditional energy-based models (EBMs) for probabilistic regression. While methods employing EBMs for regression have demonstrated impressive performance on 2D object detection in images, these techniques are not directly applicable to 3D bounding boxes. In this work, we therefore design a differentiable pooling operator for 3D bounding boxes, serving as the core module of our EBM network. We further integrate this general approach into the state-of-the-art 3D object detector SA-SSD. On the KITTI dataset, our proposed approach consistently outperforms the SA-SSD baseline across all 3DOD metrics, demonstrating the potential of EBM-based regression for highly accurate 3DOD. Code is available at https://github.com/fregu856/ebms_3dod.

READ FULL TEXT
research
05/02/2021

RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users

Object detection using automotive radars has not been explored with deep...
research
09/15/2021

Two algorithms for vehicular obstacle detection in sparse pointcloud

One of the main components of an autonomous vehicle is the obstacle dete...
research
06/23/2022

Complementary datasets to COCO for object detection

For nearly a decade, the COCO dataset has been the central test bed of r...
research
03/26/2023

CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images

Modern object detectors take advantage of rectangular bounding boxes as ...
research
03/30/2017

DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling

We define the object detection from imagery problem as estimating a very...
research
03/01/2020

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

3D object detection is an essential task in autonomous driving and robot...
research
05/04/2020

How to Train Your Energy-Based Model for Regression

Energy-based models (EBMs) have become increasingly popular within compu...

Please sign up or login with your details

Forgot password? Click here to reset