HL-YOLO: Improving Vehicle Damage Detection with Heterogeneous Convolutions and Large-Kernel Attention

Gardado en:
Detalles Bibliográficos
Publicado en:World Electric Vehicle Journal vol. 16, no. 12 (2025), p. 640-660
Autor Principal: Li, Weijun
Outros autores: Xie Huawei, Lin Peiteng, Huang, Liyan
Publicado:
MDPI AG
Materias:
Acceso en liña:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!

MARC

LEADER 00000nab a2200000uu 4500
001 3286358120
003 UK-CbPIL
022 |a 2032-6653 
024 7 |a 10.3390/wevj16120640  |2 doi 
035 |a 3286358120 
045 2 |b d20250101  |b d20251231 
100 1 |a Li, Weijun 
245 1 |a HL-YOLO: Improving Vehicle Damage Detection with Heterogeneous Convolutions and Large-Kernel Attention 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Accurate vehicle damage detection is essential in intelligent transportation systems, insurance claim assessment, and automotive maintenance. Although conventional detection models demonstrate strong performance, they still struggle to capture fine-grained details and long-range dependencies, which can constrain their effectiveness in real-world applications. To address these limitations, we propose HL-YOLO, an enhanced YOLO11-based architecture that integrates Heterogeneous Convolutions (HetConv) to improve feature extraction diversity and Large-Kernel Attention (LSKA) to strengthen contextual representation. Model evaluation results on a vehicle damage dataset demonstrate that HL-YOLO consistently outperforms the YOLO11 baseline, achieving relative improvements of 2.5% in precision, 5.8% in recall, 3.9% in mAP50, and 3.1% in mAP50–95. These results underscore the model’s robustness in identifying complex damage types, ranging from scratches and dents to accident-induced damage. Although inference latency increased moderately due to the added architectural complexity, the overall accuracy gains confirm the effectiveness of HL-YOLO in scenarios where detection reliability is prioritized over real-time speed. The proposed model shows strong potential for deployment in insurance automation, intelligent traffic monitoring, and vehicle after-service systems, providing a reliable framework for accurate vehicle damage assessment. 
653 |a Accuracy 
653 |a Datasets 
653 |a Deep learning 
653 |a Inclusion 
653 |a Computer vision 
653 |a Insurance 
653 |a Neural networks 
653 |a Effectiveness 
653 |a Damage detection 
653 |a Design 
653 |a Architecture 
653 |a Damage assessment 
653 |a Complexity 
653 |a Insurance claims 
653 |a Object recognition 
653 |a Localization 
653 |a Real time 
653 |a Intelligent transportation systems 
653 |a Semantics 
653 |a Vehicles 
700 1 |a Xie Huawei 
700 1 |a Lin Peiteng 
700 1 |a Huang, Liyan 
773 0 |t World Electric Vehicle Journal  |g vol. 16, no. 12 (2025), p. 640-660 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3286358120/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3286358120/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3286358120/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch