Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling

Pedestrian safety at crosswalks remains a critical concern as traffic accidents frequently result from drivers’ failure to yield, leading to severe injuries or fatalities. In response, various jurisdictions have enacted pedestrian priority laws to regulate driver behavior. Nevertheless, intersection...

Full description

Saved in:
Bibliographic Details
Main Authors: Kuan-Chieh Wang, Chao-Li Meng, Chyi-Ren Dow, Bonnie Lu
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/12/6459
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418305930002432
author Kuan-Chieh Wang
Chao-Li Meng
Chyi-Ren Dow
Bonnie Lu
author_facet Kuan-Chieh Wang
Chao-Li Meng
Chyi-Ren Dow
Bonnie Lu
author_sort Kuan-Chieh Wang
collection DOAJ
description Pedestrian safety at crosswalks remains a critical concern as traffic accidents frequently result from drivers’ failure to yield, leading to severe injuries or fatalities. In response, various jurisdictions have enacted pedestrian priority laws to regulate driver behavior. Nevertheless, intersections lacking clear traffic signage and environments with limited visibility continue to present elevated risks. The scarcity and difficulty of collecting data under such complex conditions pose significant challenges to the development of accurate detection systems. This study proposes a CyclicGAN-based loop-learning framework, in which the learning process begins with a set of manually annotated images used to train an initial labeling model. This model is then applied to automatically annotate newly generated synthetic images, which are incorporated into the training dataset for subsequent rounds of model retraining and image generation. Through this iterative process, the model progressively refines its ability to simulate and recognize diverse contextual features, thereby enhancing detection performance under varying environmental conditions. The experimental results show that environmental variations—such as daytime, nighttime, and rainy conditions—substantially affect the model performance in terms of F1-score. Training with a balanced mix of real and synthetic images yields an F1-score comparable to that obtained using real data alone. These results suggest that CycleGAN-generated images can effectively augment limited datasets and enhance model generalization. The proposed system may be integrated with in-vehicle assistance platforms as a supportive tool for pedestrian-crossing detection in data-scarce environments, contributing to improved driver awareness and road safety.
format Article
id doaj-art-cf2e84c8d4724bb094c3eac9dbcd008d
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-cf2e84c8d4724bb094c3eac9dbcd008d2025-08-20T03:32:28ZengMDPI AGApplied Sciences2076-34172025-06-011512645910.3390/app15126459Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic LabelingKuan-Chieh Wang0Chao-Li Meng1Chyi-Ren Dow2Bonnie Lu3Department of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, TaiwanDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, TaiwanDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, TaiwanDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, TaiwanPedestrian safety at crosswalks remains a critical concern as traffic accidents frequently result from drivers’ failure to yield, leading to severe injuries or fatalities. In response, various jurisdictions have enacted pedestrian priority laws to regulate driver behavior. Nevertheless, intersections lacking clear traffic signage and environments with limited visibility continue to present elevated risks. The scarcity and difficulty of collecting data under such complex conditions pose significant challenges to the development of accurate detection systems. This study proposes a CyclicGAN-based loop-learning framework, in which the learning process begins with a set of manually annotated images used to train an initial labeling model. This model is then applied to automatically annotate newly generated synthetic images, which are incorporated into the training dataset for subsequent rounds of model retraining and image generation. Through this iterative process, the model progressively refines its ability to simulate and recognize diverse contextual features, thereby enhancing detection performance under varying environmental conditions. The experimental results show that environmental variations—such as daytime, nighttime, and rainy conditions—substantially affect the model performance in terms of F1-score. Training with a balanced mix of real and synthetic images yields an F1-score comparable to that obtained using real data alone. These results suggest that CycleGAN-generated images can effectively augment limited datasets and enhance model generalization. The proposed system may be integrated with in-vehicle assistance platforms as a supportive tool for pedestrian-crossing detection in data-scarce environments, contributing to improved driver awareness and road safety.https://www.mdpi.com/2076-3417/15/12/6459pedestrianrecognitionloop learningautomatic labelingzebra crossingcomputer vision
spellingShingle Kuan-Chieh Wang
Chao-Li Meng
Chyi-Ren Dow
Bonnie Lu
Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling
Applied Sciences
pedestrian
recognition
loop learning
automatic labeling
zebra crossing
computer vision
title Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling
title_full Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling
title_fullStr Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling
title_full_unstemmed Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling
title_short Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling
title_sort pedestrian crossing detection enhanced by cyclicgan based loop learning and automatic labeling
topic pedestrian
recognition
loop learning
automatic labeling
zebra crossing
computer vision
url https://www.mdpi.com/2076-3417/15/12/6459
work_keys_str_mv AT kuanchiehwang pedestriancrossingdetectionenhancedbycyclicganbasedlooplearningandautomaticlabeling
AT chaolimeng pedestriancrossingdetectionenhancedbycyclicganbasedlooplearningandautomaticlabeling
AT chyirendow pedestriancrossingdetectionenhancedbycyclicganbasedlooplearningandautomaticlabeling
AT bonnielu pedestriancrossingdetectionenhancedbycyclicganbasedlooplearningandautomaticlabeling