The underground object detection method with a self-attention mechanism

Renjie Li; Qinghua Liu; Shihang Li

doi:10.1117/12.3007478

30 August 2023 The underground object detection method with a self-attention mechanism

Renjie Li, Qinghua Liu, Shihang Li

Proceedings Volume 12797, Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023); 127970P (2023) https://doi.org/10.1117/12.3007478
Event: 2nd International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), 2023, Qingdao, China

Abstract

To solve the problem that the few measured B-Scan annotated data obtained from the ground-penetrating radar are difficult to train in a large-scale model, we propose an underground target classification and detection method that requires only a small number of data sets and a short training time. This method integrates the self-attention mechanism and network layer skip connection into the SegNet model called GPRSNet, completes pixel-to-pixel classification prediction, and finally performs target localization based on the classification results. The results show that the method can still classify and label underground targets with only a small number of labeled data sets. Due to the use of real measurement data for model training, the method can be effectively used in practical applications to detect targets in ground penetrating radar images.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Renjie Li, Qinghua Liu, and Shihang Li "The underground object detection method with a self-attention mechanism", Proc. SPIE 12797, Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), 127970P (30 August 2023); https://doi.org/10.1117/12.3007478

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Target detection

Object detection

Education and training

Ground penetrating radar

Roads

Feature extraction

Image segmentation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years