AE-IA-SSD: an attention-enhanced point-based detectors for 3D LiDAR point clouds

Le Dong; Xiangjun Yu; Bo Sun

doi:10.1117/12.3034317

13 June 2024 AE-IA-SSD: an attention-enhanced point-based detectors for 3D LiDAR point clouds

Le Dong, Xiangjun Yu, Bo Sun

Proceedings Volume 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024); 1318035 (2024) https://doi.org/10.1117/12.3034317
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 2024, Guangzhou, China

Abstract

We study the efficient method of extracting crucial information from LiDAR point clouds for 3D Object Detection. Some prior works have demonstrated the importance of downsampling algorithms for 3D Object Detection, that is, the results of downsampling determine the performance of the algorithm to a large extent. Inspired by this, we introduce AE-IA-SSD, an efficient, single-stage, point-based 3D detector. We propose an importance-aware downsampling strategy by incorporating an attention mechanism at the subsampling layer to refine the selection process of keypoints. Specifically, a learnable attention module is used to dynamically weight the importance of each point at the secondary sampling stage, guided by local and global context, which enables the allocation of computational resources to point cloud regions that are more relevant to the object detection task, resulting in a significant improvement in detection accuracy while maintaining or even reducing computational footprint. Additionally, to improve the efficiency of the algorithm, We designed AE-IASSD using an encoder-only architecture to streamline its structure for efficiency. We evaluated our method on the widely used KITTI dataset, demonstrating substantial improvements over prior models.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Le Dong, Xiangjun Yu, and Bo Sun "AE-IA-SSD: an attention-enhanced point-based detectors for 3D LiDAR point clouds", Proc. SPIE 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 1318035 (13 June 2024); https://doi.org/10.1117/12.3034317

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available