Scholarlink

<p>Detecting anomalous events in real-time video surveillance is challenging due to cluttered backgrounds, overlapping objects, low-light conditions, and complex spatio-temporal variations. To address these issues, this paper proposes SpatioGuard-YOLO, an integrated framework that combines adaptive contrast enhancement, efficient object detection, and multi-scale spatial feature learning for robust video anomaly detection. A Dynamic Contrast Enhancer is introduced to improve visibility under adverse lighting conditions, while a novel Spatially Expanded Neural Network captures both global contextual information and fine-grained local details without compromising real-time performance. The proposed framework is evaluated on a real-time CCTV surveillance dataset designed for anomaly detection in pedestrian-restricted pathways, demonstrating strong generalization under diverse environmental conditions. By integrating these components with a YOLO-based detection pipeline, the proposed framework effectively reduces false detections in complex surveillance environments. Experimental results demonstrate that SpatioGuard-YOLO achieves high detection accuracy, exceeding 99% overall performance and outperforming existing state-of-the-art methods, confirming its effectiveness and reliability for real-world video surveillance applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Spatio-temporal anomaly detection for real-time video surveillance using SpatioGuard-YOLO framework

  • 期刊论文

  • 发表日期：

    2026年5月29日

查看全文
  • Sreedevi R. Krishnan,
  • P Amudha

摘要

Detecting anomalous events in real-time video surveillance is challenging due to cluttered backgrounds, overlapping objects, low-light conditions, and complex spatio-temporal variations. To address these issues, this paper proposes SpatioGuard-YOLO, an integrated framework that combines adaptive contrast enhancement, efficient object detection, and multi-scale spatial feature learning for robust video anomaly detection. A Dynamic Contrast Enhancer is introduced to improve visibility under adverse lighting conditions, while a novel Spatially Expanded Neural Network captures both global contextual information and fine-grained local details without compromising real-time performance. The proposed framework is evaluated on a real-time CCTV surveillance dataset designed for anomaly detection in pedestrian-restricted pathways, demonstrating strong generalization under diverse environmental conditions. By integrating these components with a YOLO-based detection pipeline, the proposed framework effectively reduces false detections in complex surveillance environments. Experimental results demonstrate that SpatioGuard-YOLO achieves high detection accuracy, exceeding 99% overall performance and outperforming existing state-of-the-art methods, confirming its effectiveness and reliability for real-world video surveillance applications.