Full text

Turn on search term navigation

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

SWIR imaging bears considerable advantages over visible-light (color) and thermal images in certain challenging propagation conditions. Thus, the SWIR imaging channel is frequently used in multi-spectral imaging systems (MSIS) for long-range surveillance in combination with color and thermal imaging to improve the probability of correct operation in various day, night and climate conditions. Integration of deep-learning (DL)-based real-time object detection in MSIS enables an increase in efficient utilization for complex long-range surveillance solutions such as border or critical assets control. Unfortunately, a lack of datasets for DL-based object detection models training for the SWIR channel limits their performance. To overcome this, by using the MSIS setting we propose a new cross-spectral automatic data annotation methodology for SWIR channel training dataset creation, in which the visible-light channel provides a source for detecting object types and bounding boxes which are then transformed to the SWIR channel. A mathematical image transformation that overcomes differences between the SWIR and color channel and their image distortion effects for various magnifications are explained in detail. With the proposed cross-spectral methodology, the goal of the paper is to improve object detection in SWIR images captured in challenging outdoor scenes. Experimental tests for two object types (cars and persons) using a state-of-the-art YOLOX model demonstrate that retraining with the proposed automatic cross-spectrally created SWIR image dataset significantly improves average detection precision. We achieved excellent improvements in detection performance in various variants of the YOLOX model (nano, tiny and x).

Details

Title
Deep Learning Based SWIR Object Detection in Long-Range Surveillance Systems: An Automated Cross-Spectral Approach
Author
Pavlović, Miloš S 1 ; Milanović, Petar D 1   VIAFID ORCID Logo  ; Stanković, Miloš S 2   VIAFID ORCID Logo  ; Perić, Dragana B 3 ; Popadić, Ilija V 3   VIAFID ORCID Logo  ; Perić, Miroslav V 3   VIAFID ORCID Logo 

 School of Electrical Engineering, University of Belgrade, Bul. Kralja Aleksandara 73, 11120 Belgrade, Serbia; [email protected]; Vlatacom Institute of High Technologies, Milutina Milankovica 5, 11070 Belgrade, Serbia; [email protected] (M.S.S.); [email protected] (D.B.P.); [email protected] (I.V.P.); [email protected] (M.V.P.) 
 Vlatacom Institute of High Technologies, Milutina Milankovica 5, 11070 Belgrade, Serbia; [email protected] (M.S.S.); [email protected] (D.B.P.); [email protected] (I.V.P.); [email protected] (M.V.P.); Faculty of Technical Sciences, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia 
 Vlatacom Institute of High Technologies, Milutina Milankovica 5, 11070 Belgrade, Serbia; [email protected] (M.S.S.); [email protected] (D.B.P.); [email protected] (I.V.P.); [email protected] (M.V.P.) 
First page
2562
Publication year
2022
Publication date
2022
Publisher
MDPI AG
e-ISSN
14248220
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2649099752
Copyright
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.