The detection method based on anchor-free not only reduces the training cost of object detection, but also avoids the imbalance problem caused by an excessive number of anchors. However, these methods only pay attention to the impact of the detection head on the detection performance, thus ignoring the impact of feature fusion on the detection performance. In this article, we take pedestrian detection as an example and propose a one-stage network Cascaded Cross-layer Fusion Network (CCFNet) based on anchor-free. It consists of Cascaded Cross-layer Fusion module (CCF) and novel detection head. Among them, CCF fully considers the distribution of high-level information and low-level information of feature maps under different stages in the network. First, the deep network is used to remove a large amount of noise in the shallow features, and finally, the high-level features are reused to obtain a more complete feature representation. Secondly, for the pedestrian detection task, a novel detection head is designed, which uses the global smooth map (GSMap) to provide global information for the center map to obtain a more accurate center map. Finally, we verified the feasibility of CCFNet on the Caltech and CityPersons datasets.
9 August 2025 in Journal of Circuits, Systems and Computers
Rail light-strip morphology reflects the wheel-rail contact condition. Reliable automatic analysis remains difficult. The strip is narrow and has weak boundaries, while specular reflection, rail-head texture and trackside background interfere with color inspection images. This study proposes a segmentation-guided geometric method for rail light-strip abnormality analysis. An improved SegFormer jointly segments the background, rail-head and light-strip regions. A boundary detail enhancement module refines weak rail-head and light-strip contours. Focal Loss emphasizes minority and hard boundary pixels. The rail-head mask provides the geometric reference for extracting the light-strip centerline, eccentricity, width sequence and connected-component morphology. The predicted masks are ordered using the corrected mileage record. Every 1000 original-resolution rows then form a consecutive 1 m detection unit. When a geometric rule is triggered, the method reports that unit’s 1 m mileage interval together with its eccentricity, width-change or local-integrity measurement. The model achieves 95.67% mean Intersection over Union (mIoU) on 3520 annotated images. It detects 845 of 876 positive units, with 96.46% recall, 89.23% precision and 92.70% F1-score. The resulting records identify abnormal 1 m mileage intervals and report the corresponding eccentricity, width-change, or local-integrity measurements for targeted manual review.
To measure the cross-view spacing between adjacent fastener bolts in railway turnouts, this study develops a dual-DLP-sensor structured-light measurement system without overlapping fields of view. A bridge-type calibration device is used to rapidly update the extrinsic parameters of the two DLP sensors. In a unified coordinate frame, the system integrates two-dimensional region-of-interest candidate generation, local three-dimensional geometric fitting, cross-view pairing, and measurement validity assessment to output bolt-spacing results. Experiments were conducted on 23 pairs of adjacent bolts with 15 repeated measurements using two DLP sensors. Under normal conditions, the mean absolute error, root mean square error, and average standard deviation were 0.261 mm, 0.290 mm, and 0.062 mm, respectively. Compared with fixed extrinsic parameters without updating, the bridge-based extrinsic update reduced the mean absolute error from 1.500 mm to 0.261 mm. The results indicate that the proposed task-driven dual-DLP-sensor measurement system can achieve stable cross-view spacing measurement with explicit validity criteria under non-overlapping fields of view, repeated deployment, and varying on-site data quality.