HGO-YOLO在低功耗设备上实现高精度异常行为检测，速度更快、计算量更低。
HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection
- 用改进的GhostHGNetv2和共享卷积头减少冗余计算
- 在三组数据集上达到87.4% [email protected]和81.1%召回率
- 适合部署在边缘设备，如Jetson Orin Nano
在资源受限硬件上实现精准、实时的目标检测对异常行为监控至关重要。我们提出HGO-YOLO，一种轻量级检测器，结合GhostHGNetv2与优化的参数共享检测头（OptiConvDetect），实现优异的精度-效率平衡。通过在HGNetv2骨干网络中嵌入GhostConv并引入多尺度残差融合，感受野扩大同时冗余计算减少50%。OptiConvDetect在分类与回归分支间共享部分卷积层，使检测头计算量降低41%且不损失精度。在三个异常行为数据集（跌倒、打斗、烟雾）上，HGO-YOLO在单个CPU上实现56 FPS，仅需4.3 GFLOPs和4.6 MB内存，达到87.4% [email protected]和81.1%召回率，优于YOLOv8n（+3.0% mAP，-51.7% FLOPs，1.7×加速）。在Jetson Orin Nano上的真实测试进一步验证其稳定达42 FPS吞吐量提升。
原文摘要 · Abstract (English)
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% [email protected] 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。