Addressing the limitations of current railway track foreign object detection techniques, which suffer from inadequate real-time performance and diminished accuracy in detecting small objects, this paper introduces an innovative vision-based perception methodology harnessing the power of deep learning. Central to this approach is the construction of a railway boundary model utilizing a sophisticated track detection method, along with an enhanced UNet semantic segmentation network to achieve autonomous segmentation of diverse track categories. By employing equal interval division and row-by-row traversal, critical track feature points are precisely extracted, and the track linear equation is derived through the least squares method, thus establishing an accurate railway boundary model. We optimized the YOLOv5s detection model in four aspects: incorporating the SE attention mechanism into the Neck network layer to enhance the model’s feature extraction capabilities, adding a prediction layer to improve the detection performance for small objects, proposing a linear size scaling method to obtain suitable anchor boxes, and utilizing Inner-IoU to refine the boundary regression loss function, thereby increasing the positioning accuracy of the bounding boxes. We conducted a detection accuracy validation for railway track foreign object intrusion using a self-constructed image dataset. The results indicate that the proposed semantic segmentation model achieved an MIoU of 91.8%, representing a 3.9% improvement over the previous model, effectively segmenting railway tracks. Additionally, the optimized detection model could effectively detect foreign object intrusions on the tracks, reducing missed and false alarms and achieving a 7.4% increase in the mean average precision (IoU = 0.5) compared to the original YOLOv5s model. The model exhibits strong generalization capabilities in scenarios involving small objects. This proposed approach represents an effective exploration of deep learning techniques for railway track foreign object intrusion detection, suitable for use in complex environments to ensure the operational safety of rail lines.

The identification of safflower filament targets and the precise localization of picking points are fundamental prerequisites for achieving automated filament retrieval. In light of challenges such as severe occlusion of targets, low recognition accuracy, and the considerable size of models in unstructured environments, this paper introduces a novel lightweight YOLO-SaFi model. The architectural design of this model features a Backbone layer incorporating the StarNet network; a Neck layer introducing a novel ELC convolution module to refine the C2f module; and a Head layer implementing a new lightweight shared convolution detection head, Detect_EL. Furthermore, the loss function is enhanced by upgrading CIoU to PIoUv2. These enhancements significantly augment the model’s capability to perceive spatial information and facilitate multi-feature fusion, consequently enhancing detection performance and rendering the model more lightweight. Performance evaluations conducted via comparative experiments with the baseline model reveal that YOLO-SaFi achieved a reduction of parameters, computational load, and weight files by 50.0%, 40.7%, and 48.2%, respectively, compared to the YOLOv8 baseline model. Moreover, YOLO-SaFi demonstrated improvements in recall, mean average precision, and detection speed by 1.9%, 0.3%, and 88.4 frames per second, respectively. Finally, the deployment of the YOLO-SaFi model on the Jetson Orin Nano device corroborates the superior performance of the enhanced model, thereby establishing a robust visual detection framework for the advancement of intelligent safflower filament retrieval robots in unstructured environments.

Addressing the limitation of existing object detection methods in accurately distinguishing the hazard level posed by foreign objects on railway tracks, this study proposes an intrusion warning approach for foreign object detection and risk assessment on railway surfaces. This method integrates MobileNetv3 with Transformer to detect foreign objects on railway tracks, constructing a novel backbone feature extraction network, MobileNetV3-CATr, aimed at reducing model complexity. Furthermore, a BiFPN-Lite module is introduced to fuse more target features without increasing complexity, with YOLO Head utilized to output the type information of foreign objects on the track surface. An improved track detection method is adopted toextact the railway tracks, using least squares to establish a track linear equation and delineate risk level zones. Key points of foreign objects within the image positions are selected to evaluate the intrusion risk level. Verification of detection accuracy for foreign object intrusions on railway tracks is conducted on a self-constructed image dataset. The results demonstrate that the proposed detection model can effectively identify foreign object intrusions on tracks, mitigating issues such as missed and false alarms. It achieves a 3.7% improvement in mean average precision ( mAP ) compared to the baseline model. Additionally, the refined Unet semantic segmentation network A_MIoU attains an accuracy of 90.53%, representing a 2.65% enhancement over its predecessor, with better extracted track edge integrity. The proposed risk assessment method determines different intrusion risk levels based on the location of the intruding objects, thereby assisting relevant personnel in adopting appropriate actions to enhance the safe operation of trains.

Foreign object intrusion in railway perimeter areas poses significant risks to train operation safety. To address the limitation of current visual detection technologies that overly focus on target identification while lacking quantitative risk assessment, this paper proposes a railway intrusion risk quantification method integrating track semantic segmentation and spatiotemporal features. An improved BiSeNetV2 network is employed to accurately extract track regions, while physical-constrained risk zones are constructed based on railway structure gauge standards. The lateral spatial distance of intruding objects is precisely calculated using track gauge prior knowledge. A lightweight detection architecture is designed, adopting ShuffleNetV2 as the backbone to reduce computational complexity, with an incorporated Dilated Transformer module to enhance global context awareness and sparse feature extraction, significantly improving detection accuracy for small-scale objects. The comprehensive risk assessment formula integrates object category weights, lateral risk coefficients in intrusion zones, longitudinal distance decay factors, and dynamic velocity compensation. Experimental results demonstrate that the proposed method achieves 84.9% mean average precision (mAP) on our proprietary dataset, outperforming baseline models by 3.3%. By combining lateral distance detection with multidimensional risk indicators, the method enables quantitative intrusion risk assessment and graded early warning, providing data-driven decision support for active train protection systems and substantially enhancing intelligent safety protection capabilities.

To address the issues of easy loss and inaccurate localization of distant small targets in railway LiDAR point cloud foreign object detection, this paper proposes a 3D object detection method named RailMASDet. The method constructs a cross-scale semantic spatial feature reassembly strategy. By employing transposed restoration of deep features and aligned compression of shallow features, it resolves the problem of spatial detail loss of distant targets in deep BEV feature maps. Furthermore, a railway-oriented channel modulation strategy based on existing channel attention mechanisms is introduced. By jointly exploiting global average and maximum statistics, the strategy adaptively enhances object-sensitive responses and suppresses structured-background interference in railway BEV features. Meanwhile, a foreground probability-driven non-Euclidean distance sampling paradigm is established, embedding point-level foreground priors into the distance metric function to shift keypoint sampling from uniform coverage to semantically guided targeted focusing. On the OSDaR23 dataset, RailMASDet achieves AP _0.7 of 80.59% for pedestrians and 70.05% for car, and an mAP _0.5 of 76.56%, outperforming the baseline model by 4.95, 3.78, and 3.21 percentage points, respectively. The average center localization error of detection boxes is 0.86 m, which is 57.5% lower than that of the baseline. The inference latency is 276.5 ms per frame, demonstrating reasonable computational efficiency. Ablation studies and visualization analyses validate the individual contributions of the three modules and their synergistic enhancement effects, confirming that the proposed method can effectively solve the problems of small target loss and insufficient localization accuracy in railway foreign object detection, thereby demonstrating its potential for long-range foreign object detection in sparse railway LiDAR scenes.

Existing railway obstacle detection methods primarily focus on object localization and classification, while lacking the capability to directly support operational risk assessment. To address this limitation, this paper proposes a risk-aware railway obstacle detection framework that integrates track segmentation and lateral distance estimation. The proposed framework jointly optimizes obstacle detection and track segmentation through shared feature learning, and estimates the lateral distance between detected obstacles and track boundaries based on the extracted track geometry. Railway clearance constraints are further incorporated for obstacle risk-level determination, thereby establishing an end-to-end pipeline from obstacle detection to operational risk assessment. Consequently, an end-to-end pipeline is established to classify obstacle risk levels in railway environments. To validate the proposed framework, a dedicated RN-rail-Object dataset is constructed, and comprehensive ablation studies, comparative experiments, and edge deployment evaluations are conducted. Experimental results demonstrate that the proposed method achieves 89.2% mAP for obstacle detection, 93.7% mIoU and 97.1% Dice for track segmentation, while maintaining an inference speed of 214.6 FPS on the RTX A4000 platform. Furthermore, edge deployment demonstrates the feasibility of integrating obstacle detection, track extraction, and geometry-based risk assessment on an edge computing platform, with representative scenarios illustrating the identification of different obstacle risk states. The proposed framework provides an interpretable geometry-based approach for extending conventional obstacle detection toward railway risk-aware perception, showing potential for intelligent railway inspection, early warning, and safety-oriented operation and maintenance.