Jul 2026· 2026 5th International Conference on Energy and Electrical Power Systems (ICEEPS)· pp. 890-894· 0 citations· 10 references
Abstract
In power grid construction and live-work sites, machinery operating near energized equipment poses severe safety risks. Traditional supervision lacks accurate real-time ranging and proactive hazard identification. To address this, we propose an edge information fusion-based safety control system featuring a simplified distance estimation method and an adaptive hierarchical warning strategy. The proposed distance estimation detects targets, computes the Euclidean pixel distance between bounding box centers, applies scale normalization, and maps it to spatial distance using a calibration factor—eliminating the need for precise camera calibration. Additionally, a dynamic four-level alert mechanism adjusts safety thresholds based on voltage and equipment type while suppressing false alarms. Experiments demonstrate a mean absolute error of 8.6 cm (meeting the <10 cm engineering requirement) and a 0.17 s dynamic refresh time. The warning strategy achieves a 95.2% recall with a 3.8% false alarm rate. Validated in real-world applications, this approach provides robust algorithmic support for intelligent video safety terminals.
Manual supervision of cranes, aerial work platforms, and other machinery operating near energized equipment is vulnerable to visual occlusion, while fixed distance thresholds cannot reflect dynamic motion trends. This paper proposes a safetydistance detection and dynamic-warning method based on 3D pointcloud perception...
Shu Huang, Feng-Pei Xi, Hong-Yan Zhang et al.· 2026 6th International Confe...· 0 citations
Heavy construction machinery is essential for power infrastructure construction and maintenance, making safety distance measurement crucial for ensuring operational safety. Existing methods, which rely on target space mapping, face challenges such as error accumulation and limited accuracy. Motivated by this, this pa...
Fuqi Ma, Ming-Yang Qi, Rong Jia et al.· High Voltage· 0 citations
This paper presents an AI framework employing automated visual analysis to verify personal protective equipment (PPE) compliance in complex construction and industrial settings. Within the framework of engineering automation, robust semantic modeling of worker safety configurations is essential for enabling real-time h...
Azimjon Akhtamov, Jeong Hwan Ryu, Young-ho Park et al.· Scientific Reports· 0 citations
This paper presents a calibrated hybrid edge framework for elevator safety warning. The framework combines interpretable safety rules, robust statistical anomaly scoring, one-class anomaly-detection baselines, temporal persistence, and structured event logging on a Raspberry Pi platform. The prototype integrates accele...
Zhe Zhang, Yuan-Bing Ouyang, Le-Tian Wei et al.· International Conference on...· 0 citations
A helmet-aware cross-modal identity-consistent tracking framework as an edge-deployable perception module for intelligent power-system operation and maintenance and results indicate that domain-aware helmet modeling, reliability-aware fusion, and memory-based association jointly improve identity continuity under realis...
Ling-Wen Meng, Guo-Bang Ban, Jin-Tong Ma et al.· Energy Engineering· 0 citations
An early-warning framework that combines rule constraints, machine-learning estimation, probability calibration, graded response, and feedback-based updating is proposed that is intended to support earlier intervention while retaining the authority of safety codes and the decision responsibility of on-site personnel.
Y.-F. Zhou, J. Shao, Chang-Xian Bai et al.· Advanced Electromagnetics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
