Next Article in Journal
Edge-FLGuard: A Federated Learning Framework for Real-Time Anomaly Detection in 5G-Enabled IoT Ecosystems
Previous Article in Journal
Polyamine and Isoamylamine Levels in Peripheral Blood Cells and Plasma as Biomarkers of Structural and Functional Alterations in Acute Myocardial Infarction and Chronic Heart Failure Patients
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

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

by
Kuan-Chieh Wang
,
Chao-Li Meng
*,
Chyi-Ren Dow
and
Bonnie Lu
*
Department of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, Taiwan
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2025, 15(12), 6459; https://doi.org/10.3390/app15126459 (registering DOI)
Submission received: 1 May 2025 / Revised: 5 June 2025 / Accepted: 6 June 2025 / Published: 8 June 2025

Abstract

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.
Keywords: pedestrian; recognition; loop learning; automatic labeling; zebra crossing; computer vision pedestrian; recognition; loop learning; automatic labeling; zebra crossing; computer vision

Share and Cite

MDPI and ACS Style

Wang, K.-C.; Meng, C.-L.; Dow, C.-R.; Lu, B. Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling. Appl. Sci. 2025, 15, 6459. https://doi.org/10.3390/app15126459

AMA Style

Wang K-C, Meng C-L, Dow C-R, Lu B. Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling. Applied Sciences. 2025; 15(12):6459. https://doi.org/10.3390/app15126459

Chicago/Turabian Style

Wang, Kuan-Chieh, Chao-Li Meng, Chyi-Ren Dow, and Bonnie Lu. 2025. "Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling" Applied Sciences 15, no. 12: 6459. https://doi.org/10.3390/app15126459

APA Style

Wang, K.-C., Meng, C.-L., Dow, C.-R., & Lu, B. (2025). Pedestrian-Crossing Detection Enhanced by CyclicGAN-Based Loop Learning and Automatic Labeling. Applied Sciences, 15(12), 6459. https://doi.org/10.3390/app15126459

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop