Quantization to accelerate inference in multimodal 3D object detection

Billy Geerhart; Venkat R. Dasari; Brian Rapp; Peng Wang; Ju Wang; Christopher X. Payne

doi:10.1117/12.3013702

6 June 2024 Quantization to accelerate inference in multimodal 3D object detection

Billy Geerhart, Venkat R. Dasari, Brian Rapp, Peng Wang, Ju Wang, Christopher X. Payne

Proceedings Volume 13058, Disruptive Technologies in Information Sciences VIII; 1305807 (2024) https://doi.org/10.1117/12.3013702
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

The Label-Diffusion-LIDAR-Segmentation (LDLS) algorithm uses multi-modal data for enhanced inference of environmental categories. The algorithm segments the Red-Green-Blue (RGB) channels and maps the results to the LIDAR point cloud using matrix calculations to reduce noise. Recent research has developed custom optimization techniques using quantization to accelerate the 3D object detection using LDLS in robotic systems. These optimizations achieve a 3x speedup over the original algorithm, making it possible to deploy the algorithm in real-world applications. The optimizations include quantization for the segmentation inference as well as matrix optimizations for the label diffusion. We will present our results, compare them with the baseline, and discuss their significance in achieving real-time object detection in resource-constrained environments.

Conference Presentation

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

Citation Download Citation

Billy Geerhart, Venkat R. Dasari, Brian Rapp, Peng Wang, Ju Wang, and Christopher X. Payne "Quantization to accelerate inference in multimodal 3D object detection", Proc. SPIE 13058, Disruptive Technologies in Information Sciences VIII, 1305807 (6 June 2024); https://doi.org/10.1117/12.3013702

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