Abstract

Infrared imaging has emerged as a robust solution for urban object detection under low-light and adverse weather conditions, offering significant advantages over traditional visible-light cameras. However, challenges such as class imbalance, thermal noise, and computational constraints can significantly hinder model performance in practical settings. To address these issues, we evaluate multiple YOLO variants on the FLIR ADAS V2 dataset, ultimately selecting YOLOv8 as our baseline due to its balanced accuracy and efficiency. Building on this foundation, we present MS-YOLO (MobileNetv4 and SlideLoss based on YOLO), which replaces YOLOv8's CSPDarknet backbone with the more efficient MobileNetV4, reducing computational overhead by 1.5% while sustaining high accuracy. In addition, we introduce SlideLoss, a novel loss function that dynamically emphasizes under-represented and occluded samples, boosting precision without sacrificing recall. Experiments on the FLIR ADAS V2 benchmark show that MS-YOLO attains competitive mAP and superior precision while operating at only 6.7 GFLOPs. These results demonstrate that MS-YOLO effectively addresses the dual challenge of maintaining high detection quality while minimizing computational costs, making it well-suited for real-time edge deployment in urban environments.

Department(s)

Mathematics and Statistics

Second Department

Electrical and Computer Engineering

Third Department

Computer Science

Comments

Air Force Research Laboratory, Grant FA8650-18-C-7831

Keywords and Phrases

Infrared Object Detection; MobileNetV4; SlideLoss; YOLO Model

International Standard Serial Number (ISSN)

2161-4407; 2161-4393

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Jan 2025

Download

Full Text Link

Share

 
COinS