Scholarlink

<p>Accurate, real-time object detection on resource-constrained hardware is critical for anomaly behavior monitoring. We introduce HGO-YOLO, a lightweight detector that combines GhostHGNetv2 with an optimized parameter-sharing head (OptiConvDetect) to deliver an outstanding accuracy–efficiency trade-off. By embedding GhostConv into the HGNetv2 backbone with multi-scale residual fusion, the receptive field is enlarged while redundant computation is reduced by 50%. OptiConvDetect shares a partial-convolution layer for the classification and regression branches, cutting detection-head FLOPs by 41% without accuracy loss. On three anomaly datasets (fall, fight, smoke), HGO-YOLO attains 87.4% mAP@0.5 and 81.1% recall at 56 FPS on a single CPU with just 4.3 GFLOPs and 4.6&#xa0;MB—surpassing YOLOv8n by + 3.0% mAP, − 51.7% FLOPs, and 1.7 × speed. Real-world tests on a Jetson Orin Nano further confirm a stable throughput gain of 42 FPS<b>.</b></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

HGO-YOLO: advancing anomaly behavior detection with hierarchical features and lightweight optimized detection

  • 期刊论文

  • 发表日期：

    2025年6月27日

查看全文
  • Qizhi Zheng,
  • Zhongze Luo,
  • Meiyan Guo,
  • Xinzhu Wang,
  • Renqimuge Wu,
  • Qiu Meng,
  • Guanghui Dong

摘要

Accurate, real-time object detection on resource-constrained hardware is critical for anomaly behavior monitoring. We introduce HGO-YOLO, a lightweight detector that combines GhostHGNetv2 with an optimized parameter-sharing head (OptiConvDetect) to deliver an outstanding accuracy–efficiency trade-off. By embedding GhostConv into the HGNetv2 backbone with multi-scale residual fusion, the receptive field is enlarged while redundant computation is reduced by 50%. OptiConvDetect shares a partial-convolution layer for the classification and regression branches, cutting detection-head FLOPs by 41% without accuracy loss. On three anomaly datasets (fall, fight, smoke), HGO-YOLO attains 87.4% mAP@0.5 and 81.1% recall at 56 FPS on a single CPU with just 4.3 GFLOPs and 4.6 MB—surpassing YOLOv8n by + 3.0% mAP, − 51.7% FLOPs, and 1.7 × speed. Real-world tests on a Jetson Orin Nano further confirm a stable throughput gain of 42 FPS.