Augmentation of Severe Weather Impact to Far-Infrared Sensor Images to Improve Pedestrian Detection System
Open Access
- 14 April 2021
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 10 (8) , 934
Abstract
Pedestrian detection is an essential task for computer vision and the automotive industry. Complex systems like advanced driver-assistance systems are based on far-infrared data sensors, used to detect pedestrians at nighttime, fog, rain, and direct sun situations. The robust pedestrian detector should work in severe weather conditions. However, only a few datasets include some examples of far-infrared images with distortions caused by atmospheric precipitation and dirt covering sensor optics. This paper proposes the deep learning-based data augmentation technique to enrich far-infrared images collected in good weather conditions by distortions, similar to those caused by bad weather. The six most accurate and fast detectors (TinyV3, TinyL3, You Only Look Once (YOLO)v3, YOLOv4, ResNet50, and ResNext50), performing faster than 15 FPS, were trained on 207,001 annotations and tested on 156,345 annotations, not used for training. The proposed data augmentation technique showed up to a 9.38 mean Average Precision (mAP) increase of pedestrian detection with a maximum of 87.02 mAP (YOLOv4). Proposed in this paper detectors’ Head modifications based on a confidence heat-map gave an additional boost of precision for all six detectors. The most accurate current detector, based on YOLOv4, reached up to 87.20 mAP during our experimental tests.Keywords
This publication has 49 references indexed in Scilit:
- Pedestrians’ detection in thermal bands – Critical surveyJournal of Electrical Systems and Information Technology, 2015
- Pedestrian Classification and Detection in Far Infrared Images2015
- Denoising Convolutional Neural Network2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Low Resolution Person Detection with a Moving Thermal Infrared Camera by Hot Spot Classification2014
- Night vision animal detection2014
- Quantifying Crash Risk under Inclement Weather with Radar Rainfall Data and Matched-Pair MethodJournal of Transportation Safety & Security, 2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- A Two-Stage Template Approach to Person Detection in Thermal Imagery2005