Keywords
Instance segmentation
YOLOv11
Submitted : 2026-06-23
Accepted : 2026-07-08
Published : 2026-07-23
Abstract
Tire quality is vital for vehicle safety, but finding surface defects automatically is hard. Current systems often fail to spot tiny flaws hidden inside complex tread patterns. Also, because defects vary in size and blend into the dark rubber, standard models usually output broken or messy segmentation masks. To solve this, we built YOLO11-SPMB, a new instance segmentation network based on YOLO11. We designed it specifically for tire inspection. First, we added a Multi-Scale Adaptive Feature Fusion (MS-AFF) module to the network. It filters out the repeating noise from normal treads so tiny defects can stand out. Second, we created a Boundary Enhancement and Imbalance Calibration (BE-IC) strategy. It uses a boundary Dice loss to keep the mask edges smooth and whole. At the same time, it adjusts class weights to help the model catch rare but major damage, fixing the data imbalance problem. Tests on our custom dataset show the model works very well. YOLO11-SPMB achieves a mAP@0.5:0.95 of 0.702, a mIoU of 0.782, and a recall of 0.928. It also runs at 60 frames per second (FPS), making it fast and accurate enough for real factory production lines.
References
Zuo Y, Wang J, Song J, 2021, Application of YOLO Object Detection Network in Weld Surface Defect Detection. 2021 IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 704–710.
Xikun X, Changjiang L, Meng X, 2021, Application of Attention YOLOV4 Algorithm in Metal Defect Detection. 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT), 465–468.
Mišković M, et al., 2021, Automated Defect Detection From Ultrasonic Images Using Deep Learning. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 68(9): 3126–3134.
Huang W, Wei P, Zhang M, 2021, PCB Defect Detection Using Deep Learning Methods. 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD), 1–6.
Sun S, Liu W, Cui R, 2022, YOLO Based Bridge Surface Defect Detection Using Decoupled Prediction. 2022 7th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), 117–122.
Zhang Y, Zhang Z, Fu K, et al., 2022, Adaptive Defect Detection for 3-D Printed Lattice Structures Based on Improved Faster R-CNN. IEEE Transactions on Instrumentation and Measurement, 71: 1–9.
Li J, et al., 2022, Surface Defect Detection Based on Improved YOLOv3-Tiny Algorithm. 2022 7th International Conference on Image, Vision and Computing (ICIVC), 1–6.
Ren X, He X, 2023, An Enhanced Instance Segmentation Network for Surface Defect Detection. 2023 9th International Conference on Computer and Communications (ICCC), 2098–2103.
Chen D, Xie S, Xie Y, 2023, A Contour-Based Instance Segmentation Method for Copper Tube. 2023 China Automation Congress (CAC), 7864–7869.
Shen M, Cai F, Xie J, 2023, A Multi-Scale Defect Detection for Steel Surface Based on Improved Faster R-CNN. 2023 China Automation Congress (CAC), 7448–7453.
Malik P, Lakshakar H, Hazra J, 2023, Aircraft Defect Localization and Detection Using Object Detection Techniques. 2023 3rd International Conference on Applied Electromagnetics, Signal Processing, & Communication (AESPC), 1–6.
Haobo Y, 2024, A Survey of Industrial Surface Defect Detection Based on Deep Learning. 2024 International Conference on Cyber-Physical Social Intelligence (ICCSI), 1–6.
Raj A, Ahlawat P, 2024, Refined YOLOv8 for Enhanced Small Object Detection in PCB Defect. 2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies (INSPECT), 1–6.
Yu L, Yan P, 2024, YOLOv8-LSD: A Steel Surface Defect Detection Algorithm Based on YOLOv8. 2024 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), 1394–1399.
Wang C, Yeh I, Liao H, 2024, YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6222–6232.
Sun H, Yao G, Zhu S, 2025, SOD-YOLOv10: Small Object Detection in Remote Sensing Images Based on YOLOv10. IEEE Geoscience and Remote Sensing Letters, 22: 1–5.
Mishra A, Narendra M, Sinha A, et al., 2025, Dynamic Backbone Optimization of YOLOv10 for Real-Time Object Detection in UAV-Based Search and Rescue Missions. IEEE Access, 13: 195975–195986.
Dang Z, Wang X, 2025, FD-YOLO11: A Feature-Enhanced Deep Learning Model for Steel Surface Defect Detection. IEEE Access, 13: 63981–63993.
Shen P, Mei K, Cao H, 2025, LDDFSF-YOLO11: A Lightweight Insulator Defect Detection Method Focusing on Small-Sized Features. IEEE Access, 13: 90273–90292.
Selvam P, Rajasekar R, Gunasundari C, 2025, YOLO-DefXpert: An Advanced Defect Detection on PCB Surfaces Using Improved YOLOv11 Algorithm. IEEE Access, 13: 143085–143101.