In response to the challenges associated with the misassembly, omission, and low manual inspection efficiency in automobile wiring harness relay assemblies, a novel online detection system has been engineered. This system consists of a mobile-based visual imaging system and an improved YOLOv5-based detection algorithm that tracks human movement to acquire images and videos. The system is coupled with deep learning for real-time detection and recognition for error-proofing the installation process of automotive wiring harness relays. This innovation aims to facilitate error-proof inspection during the assembly process of automotive wiring harness relays. The YOLOv5s model is augmented with an Adaptive Spatial Feature Fusion (ASFF) module, enhancing multi-scale feature integration capabilities. A Global Context Network (GCNet) is incorporated into the C3 module to emphasize target information from a global perspective. Additionally, the replacement of standard Convolution (Conv) modules with Global Sparse Convolution (GSConv) modules in the Neck section effectively reduces computational costs while sustaining overall performance efficacy. The experimental results show that the detection system achieved a comprehensive accuracy rate of 99.2% and an F1 score of 99.29. The system possesses high accuracy and stability, enabling flexible and intelligent target detection applications in the automotive industry.
In this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of automotive parts passing through the scanning portal in real time. By integrating deep learning, the system enables real-time monitoring and identification, thereby preventing misdetections and missed detections of automotive parts, in this way promoting intelligent automotive part recognition and detection. Our system introduces the A2C2f-SA module, which achieves an efficient feature attention mechanism while maintaining a lightweight design. Additionally, Dynamic Space-to-Depth (Dynamic S2D) is employed to improve convolution and replace the stride convolution and pooling layers in the baseline network, helping to mitigate the loss of fine-grained information and enhancing the network’s feature extraction capability. To improve real-time performance, a GFL-MBConv lightweight detection head is proposed. Furthermore, adaptive frequency-aware feature fusion (Adpfreqfusion) is hybridized at the end of the neck network to effectively enhance high-frequency information lost during downsampling, thereby improving the model’s detection accuracy for target objects in complex backgrounds. On-site tests demonstrate that the system achieves a comprehensive accuracy of 97.3% and an average vehicle detection time of 7.59 s, exhibiting not only high precision but also high detection efficiency. These results can make the proposed system highly valuable for applications in the automotive industry.
Conventional vehicle character recognition methods often treat detection and recognition as separate processes, resulting in limited feature interaction and potential error propagation. To address this issue, this paper proposes a structure-aware self-supervised Masked Autoencoder (CharSAM-MAE) framework, combined with an independent region extraction preprocessing stage. A YOLOv8n detector is employed solely to crop the region of interest (ROI) from full-frame vehicle images using 50 single bounding-box annotated samples. After cropping, the detector is discarded, and subsequent self-supervised pre-training and recognition are fully executed using MAE without any involvement of YOLO model parameters or labeled data. CharSAM-MAE incorporates a structure-aware masking strategy and a region-weighted reconstruction loss during pre-training to improve both local structural representation and global feature modeling. During fine-tuning, a multi-head attention-enhanced CTC decoder (A-CTC) is applied to mitigate issues such as sparse characters, adhesion, and long-sequence instability. The framework is trained on 13,544 ROI images, with only 5% of labeled data used for supervised fine-tuning. Experimental results demonstrate that the proposed method achieves 99.25% character accuracy, 88.6% sequence accuracy, and 0.85% character error rate, outperforming the PaddleOCR v5 baseline (98.92%, 85.2%, and 1.15%, respectively). These results verify the effectiveness of structure-aware self-supervised learning and highlight the applicability of the proposed method for industrial character recognition with minimal annotation requirements.