Haoyu Li¹, Jiayi Wang¹, Zhaoyu Wu¹, Shuo Yan¹, Ziqi Zhang¹, Yang Gao^2,3, Genwang Peng^2,3, Zhiwei Cao^2,*

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077736 - 18 May 2026

Abstract Key components of rail transit systems, such as tracks and vehicle bodies, are prone to developing various types and manifestations of defects during long-term operation. These defects not only accelerate component aging and failure but also pose serious threats to train operational safety. Among existing intelligent detection methods, they mostly rely solely on visible light images demonstrate limited robustness in complex scenarios. This limitation stems from their high dependence on ambient lighting conditions, rendering them insufficient to meet practical railway inspection requirements. While mainstream multimodal detection methods incorporate the complementary strengths of heterogeneous data sources,… More >

Luis Sánchez Calderón^*, David Valverde Burneo, Walter Hurtares Orrala

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077137 - 18 May 2026

Abstract Accurate characterization of live load histories remains critical for structural safety and efficient design; however, traditional codes often overestimate in-service loads. This study introduced an AI-driven framework integrating YOLOv8 object detection and DeepFace gender classification with continuous video surveillance to monitor live loads in academic buildings. Gender classification used local anthropometric data (77 kg males, 61 kg females) for precise load estimation, with privacy ensured via local processing and anonymized metadata only. Observed peaks were substantially below Eurocode and IBC provisions, confirming code conservatism. Uncertainty propagation from detector errors (recall 0.57, ±0.02 Kn/m²) minimally impacted projections. More >

Jianping Wu¹, Nian Li^2,*, Libin Dong³, Ping Zhang⁴

Journal on Artificial Intelligence, Vol.8, pp. 259-271, 2026, DOI:10.32604/jai.2026.075753 - 12 May 2026

Abstract This paper presents a static fusion framework that enhances object detection by integrating camera and LiDAR-based detection results. The proposed method focuses on associating 2D candidate bounding boxes from a camera detector with 3D candidate boxes from a LiDAR detector using an Intersection over Union (IoU)-based matching approach. To enhance the quality of 2D detection, we refine the baseline Cascade R-CNN detector by incorporating a dual self-attention mechanism into both the backbone and the region proposal network (RPN), resulting in the DA-Cascade R-CNN. This enhancement strengthens the network’s ability to detect small or distant objects More >

Wenfeng Wang^1,*, Wenjie Fan¹, Fang Dong¹, Bin Zeng¹, Wenxin Yu¹, Xiangping Deng²

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.078416 - 08 May 2026

Abstract Unmanned Aerial Vehicle (UAV) image object detection has been widely applied in many fields. However, compared with ordinary natural images, UAV images often exhibit complex backgrounds, a predominance of small objects, and significant variations in target scales, which cause traditional detection algorithms to easily suffer from missed or false detections with insufficient accuracy. To address these issues, this paper proposes a novel UAV image object detection algorithm named DMA-YOLO based on the YOLOv8s model, incorporating a deep diverse branch block and multi-scale auxiliary feature. First, a DF-C2f module integrating a deep diverse branch block and… More >

Duane G. Noé¹, Ku-Chin Lin², Chang-Lin Chuang³, Yung-Tsung Cheng^3,*

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.077838 - 08 May 2026

Abstract Steel manufacturing requires high-throughput and high-reliability surface inspection to minimize safety risks, scrap rates, and downstream quality reductions. Conventional rule-based vision and manual inspection are often impeded in real production environments by variable illumination, complex textures, subtle defect morphology, and stringent latency constraints imposed by production-line operation. Deep learning (DL) has become a dominant paradigm for the detection and classification of defects when inspecting steel, but many previous studies have performed broad architectural overviews without explicitly connecting model and pipeline choices to deployment-critical factors such as processing speed, hardware availability, annotation cost, and robustness during… More >

Lijuan Huang^1,2, Zhixian Liu³, Xinyu Zhou⁴, Jinping Liu^4,*, Kunyi Zheng⁴, Yimei Yang^2,4,*

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.077655 - 08 May 2026

Abstract Many occluded and ambiguous ground truths exist in object detection, making detectors unable to obtain optimal training samples. In this article, we revisit the suboptimal sample issue in label assignment for object detection and propose a novel detector-agnostic strategy, termed FSS, to address it. FSS reformulates label assignment as the process of selecting high-quality sub-optimal samples and progressively transforming them into optimal ones. Specifically, for each candidate, we estimate the probability of being an optimal sample by jointly considering localization quality and classification confidence, thereby constructing an instance-wise probability matrix. Based on the spatial distribution More >

Tianzhe Jiao, Yuming Chen, Xiaoyue Feng, Chaopeng Guo, Jie Song^*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.1, 2026, DOI:10.32604/cmes.2026.080595 - 27 April 2026

Abstract Knowledge distillation bridges the performance gap between camera-based and LiDAR-based 3D detectors by leveraging the precise geometric information from LiDAR. However, cross-modal knowledge transfer remains challenging due to the inherent modality heterogeneity between LiDAR and camera data, which often leads to instability during training. In this work, we find that these instabilities are closely related to distribution mismatch in the cross-modal feature space and noisy teacher signals. To address this issue, we propose a novel distribution-aware cross-modal distillation framework, named DA-T3D. Specifically, we first explicitly model the LiDAR teacher’s Bird’s-Eye-View (BEV) feature distribution and use… More >

Yuxiao Shi¹, Jinglin Zhang², Yuxia Li^2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.1, 2026, DOI:10.32604/cmes.2026.078601 - 27 April 2026

Abstract Traffic light detection and fault identification using images from road traffic cameras are important for intelligent traffic management and urban safety monitoring. However, images collected in real traffic environments show clear differences in camera view, lighting conditions, weather, and background complexity. As a result, traffic lights vary greatly in scale, spatial location, and appearance, which reduces detection accuracy in complex scenes. To deal with this problem, this paper presents a multi-scene traffic light detection and fault identification framework based on dual-attention image fusion. Large-scale road camera data from the Chengdu Traffic Management Bureau are used,… More >

Sang-Hyun Lee^*, Qingtao Meng

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077207 - 09 April 2026

Abstract Accurate and timely detection of rice leaf diseases is critical for ensuring global food security and maximizing agricultural yields. However, existing deep learning methods often struggle to balance the high accuracy required for detecting multi-scale lesions in complex field environments with the computational efficiency necessary for edge device deployment. This paper proposes You Only Look Once for Lightweight Detection (YOLOv11-LD), a lightweight object detection model for multi-scale rice leaf disease detection in real paddy field environments. The model is built on YOLOv11n and integrates a Re-parameterized Vision Transformer (RepViT) backbone, a Bidirectional Feature Pyramid Network… More >

Sudhir Kumar Pandey¹, Jian-Xun Mi^1,*, Zahid Ullah², Mona Jamjoom³

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.074811 - 09 April 2026

Abstract Adversarial examples in object detection frequently fail to transfer between different models because attacks overfit to the source model’s architecture and feature space. We propose AugTrans, a framework that addresses this limitation through input-space regularization. Our key innovation is a multi-stage augmentation pipeline that incorporates object-level semantic awareness into transformation design. The pipeline comprises three novel components: dynamic object-centric rotation with adaptive scheduling, multi-box aware resizing based on ground-truth annotations, and composite noise injection. These transformations are integrated within the Expectation over Transformation (EOT) framework. By optimizing perturbations to remain effective across semantically meaningful transformations, our… More >