A Study on Application of Self-supervised Learning for Multispectral Pedestrian Detection
- 1 May 2025
- journal article
- Published by Institute of Control, Robotics and Systems in Journal of Institute of Control, Robotics and Systems
- Vol. 31 (5) , 526-535
Abstract
Pedestrian detection has long been a prominent area of focus in computer vision due to its extensive applications, particularly in the development of autonomous driving systems. While color image-based pedestrian detection has achieved significant progress, its vulnerability to illumination changes has prompted more research into multispectral pedestrian detection, which leverages both visible and infrared modalities for robust detection in varying lighting conditions. Despite advances in multispectral detection models, research on applying self-supervised learning for feature representation in this area remains limited. In this study, we extend existing self-supervised learning approaches for color image data to multispectral pedestrian detection. By pre-training with self-supervised learning methods and fine-tuning, we evaluate their extensibility to the multispectral domain. Experimental results demonstrate that self-supervised learning enhances multispectral pedestrian detection, especially in nighttime conditions, outperforming models pretrained only on color modalities. Furthermore, we analyze the framework of self-supervised learning method that perform well on multispectral data, providing insights into which framework elements enhance multispectral pedestrian detection. This study underscores the potential of self-supervised learning in multispectral pedestrian detection and its role in advancing detection robustness for critical applications such as autonomous driving.Keywords
Funding Information
- Ministry of Science and ICT, South Korea
- Institute for Information & communication Technology Planning & evaluation (IITP-2025-RS-2022-00156345, IITP-2025-RS-2024-00437494)
- National Research Foundation of Korea (NRF-2023M3C1C1A01098408)
This publication has 26 references indexed in Scilit:
- Dense Contrastive Learning for Self-Supervised Visual Pre-Training2021
- End-to-End Object Detection with Transformers2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Cross-modality interactive attention network for multispectral pedestrian detectionInformation Fusion, 2019
- Aggregated Residual Transformations for Deep Neural Networks2017
- CityPersons: A Diverse Dataset for Pedestrian Detection2017
- SSD: Single Shot MultiBox Detector2016
- Deep Residual Learning for Image Recognition2016
- Multispectral pedestrian detection: Benchmark dataset and baseline2015
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013