Skip to content

Similar papers

Open access Oct 2026

CMRN-DETR: a context-guided and feature-aware model for detecting small-scale defects in insulators

The proposed insulator defect detection model CMRN-detection transformer (DETR) based on real-time-DETR, which enables rapid detection of visible defects on insulator surfaces using visible-light images and adopts Normalized Wasserstein Distance to optimize the regression loss function.

Tai-Fei Zhao, Jing Liu, Heng-Fei Qiao et al. · 0 citations
Open access 2026

Insulator Defect Detection by Fusing Fine-Grained Features and Contextual Information

Insulator defect detection is a key task in uncrewed aerial vehicle (UAV) inspection of transmission lines. Defects in real inspection images commonly exhibit small scale, weak texture, blurred boundaries, and strong background interference, leaving existing detectors insufficient in fine-detail feature representation...

Dong-Qi Zhang, Qian Xiao, Z. Idrus et al. · 0 citations
Sep 2026

LKDT-YOLO: multi-scale hardware detection in stacking environments based on dynamic transformer

The proposed LKDT-YOLO is an advanced framework integrating three key innovations: a Dynamic Allocation-Partially Transformer Block that fuses locally ambiguous features with global contextual representations; an SPPF module with Large Scale Separable Kernel Attention (LSSKA) employing dynamic spatial attention to enha...

Xin-Jun Liu, Jia-Peng Gao, Kai Wang et al. · 0 citations
Open access Aug 2026

Insulator-DETR: A Detection Transformer Tailored for Insulator Defect Inspection Based on UAV Remote Sensing

Reliable inspection of insulator defects from unmanned aerial vehicle (UAV) remote sensing imagery is essential for the safe operation of power transmission systems. However, the task remains challenging due to fine-grained defect patterns, thin structures, large-scale variations, and complex backgrounds in aerial scen...

Yaping Yan, Weizhong Yuan, Hao Xie · 0 citations
Open access Sep 2026

Dual-path attention with adaptive energy-guided interaction for real-time industrial defect detection

Detecting industrial defects presents formidable challenges, as anomalies often appear as tiny, low-contrast objects on complex surfaces with varied orientations. This work introduces two lightweight attention modules that strengthen feature discrimination while incurring minimal computational overhead. Our lightweight...

Jing-Juan Guo, Yu-Feng Li, Meng-Qiang Yi et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.