Improving the accuracy and detection speed of bolt recognition under the complex background of the train underframe is crucial for the safety of train operation. To achieve efficient detection, a lightweight detection method based on SFCA-YOLOv8s is proposed. The underframe bolt images are captured by a self-designed track-based inspection robot, and a dataset is constructed by mixing simulated platform images with real train underframe bolt images. By combining the C2f module with ScConv lightweight convolution and replacing the Bottleneck structure with the Faster_Block structure, the SFC2f module is designed for feature extraction to improve detection accuracy and speed. It is compared with FasterNet, GhostNet, and MobileNetV3. Additionally, the CA attention mechanism is introduced, and MPDIoU is used as the loss function of YOLOv8s. LAMP scores are used to rank the model weight parameters, and unimportant weight parameters are pruned to achieve model compression. The compressed SFCA-YOLOv8s model is compared with models such as YOLOv5s, YOLOv7, and YOLOX-s in comparative experiments. The results indicate that the final model achieves an average detection accuracy of 93.3% on the mixed dataset, with a detection speed of 261 FPS. Compared with other classical deep learning models, the improved model demonstrates superior performance in detection effectiveness, robustness, and generalization. Even in the absence of sufficient real underframe bolt images, the algorithm enables the trained network to better adapt to real environments, improving bolt recognition accuracy and detection speed, thus providing technical references and theoretical support for subsequent related research.

As the safety requirements of elevator systems continue to rise, the detection of loose bolts and the high-precision segmentation of anti-loosening lines have become critical challenges in elevator landing door inspection. Traditional manual inspection and conventional visual detection often fail to meet the requirements of high precision and robustness under real-world conditions such as oil contamination and low illumination. This paper proposes two improved algorithms for detecting loose bolts and segmenting anti-loosening lines in elevator landing doors. For small-bolt detection, we introduce the DS-EMA model, an enhanced YOLOv8 variant that integrates depthwise-separable convolutions and an Efficient Multi-scale Attention (EMA) module. The DS-EMA model achieves a 2.8 percentage point improvement in mAP over the YOLOv8n baseline on our self-collected dataset, while reducing parameters from 3.0 M to 2.8 M and maintaining real-time throughput at 126 FPS. For anti-loosening-line segmentation, we develop an improved DeepLabv3+ by adopting a MobileViT backbone, incorporating a Global Attention Mechanism (GAM) and optimizing the ASPP dilation rate. The revised model increases the mean IoU to 85.8% (a gain of 5.4 percentage points) while reducing parameters from 57.6 M to 38.5 M. Comparative experiments against mainstream lightweight models, including YOLOv5n, YOLOv6n, YOLOv7-tiny, and DeepLabv3, demonstrate that the proposed methods achieve superior accuracy while balancing efficiency and model complexity. Moreover, compared with recent lightweight variants such as YOLOv9-tiny and YOLOv11n, DS-EMA achieves comparable mAP while delivering notably higher recall, which is crucial for safety inspection. Overall, the enhanced YOLOv8 and DeepLabv3+ provide robust and efficient solutions for elevator landing door safety inspection, delivering clear practical application value.