HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection
This work addresses efficient anomaly monitoring for surveillance systems, presenting an incremental improvement over existing lightweight detectors.
The paper tackled real-time anomaly behavior detection on resource-constrained hardware by introducing HGO-YOLO, achieving 87.4% mAP@0.5 and 81.1% recall at 56 FPS with 4.3 GFLOPs, outperforming YOLOv8n in accuracy and efficiency.
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.