面向智能监控的轻量YOLOv10目标检测算法
Lightweight YOLOv10 Object Detection Algorithm for Intelligent Surveillance
为解决传统人工视频监控实时性不足,无法高效检测场景中短暂出现目标的问题,提出一种基于轻量化YOLOv10的智能监控检测算法。首先,利用深度可分离卷积替换标准卷积,减少网络参数,提高检测速度。其次,将主干网络中跨阶段部分双卷积融合瓶颈结构替换为高效多尺度注意力模块,提高网络对目标成像尺寸变化的感知能力。最后,使用辅助边界框优化损失,丰富监督信息,增强网络对小目标的检测性能。在交通监控数据集UA-DETRAC中的实验结果表明:该算法平均精度均值较Faster R-CNN、EfficientDet-D5、YOLOv8及YOLOv11分别高出13.5、10.9、1.7、0.4个百分点;检测速度达112 FPS,参数量仅2.2×106,为智能监控下目标检测任务提供技术支持。
To address the limitations of traditional manual video surveillance, such as insufficient real-time performance and inefficient detection of transient targets, an intelligent surveillance detection algorithm based on lightweight YOLOv10 is proposed. Firstly, depthwise separable convolutions are employed to replace standard convolutions, reducing network parameters while accelerating detection speed. Secondly, the cross-stage partial bottleneck structure with dual convolution fusion in the backbone network is substituted with an efficient multi-scale attention module, enhancing the network’s sensitivity to target scale variations. Finally, an auxiliary bounding box optimization loss is integrated to enrich supervision signals and improve small-target detection performance. Experimental evaluations on the UA-DETRAC traffic surveillance dataset demonstrate that the proposed algorithm achieves a higher mean average precision (mAP) by 13.5, 10.9, 1.7, and 0.4 percentage points compared to these of Faster R-CNN, EfficientDet-D5, YOLOv8, and YOLOv11, respectively. With a detection speed of 112 FPS and merely 2.2×106 parameters, this algorithm provides robust technical support for object detection tasks in intelligent surveillance systems.
智能监控 / 目标检测 / 深度学习 / YOLOv10模型 / 轻量化
intelligent surveillance / object detection / deep learning / YOLOv10 / lightweight
| [1] |
李炜,黄倩.嵌入式机房多功能模块智能监控系统设计[J].计算机测量与控制,2024,32(1):64-71. |
| [2] |
王均成,贺超,赵志源, |
| [3] |
胡戈飚,林志驰,郭政, |
| [4] |
张社荣,梁斌杰,马重刚, |
| [5] |
任安虎,李宇飞,陈洋.改进YOLOv8的高速公路交通异常事件检测[J].激光杂志,2025,46(1):84-90. |
| [6] |
李华,吴立舟,薛曦澄, |
| [7] |
李杰,李勇斌,郑娄, |
| [8] |
|
| [9] |
徐薪羽,沈通,吕佳.基于改进YOLOv8算法的钢材表面缺陷检测[J].自动化应用,2024(15):6-10. |
| [10] |
韩捷,郝方舟,刘晓, |
| [11] |
|
| [12] |
侯伟,陈雅,宋承继, |
| [13] |
梁天添,杨淞淇,钱振明.基于改进YOLOv8s的恶劣天气车辆行人检测方法[J].电子测量技术,2024,47(9):112-119. |
| [14] |
周秀珊,文露婷,介百飞, |
安徽省高等学校省级质量工程项目(2023JYXM1692)
安徽省教育厅2024年度重点项目(2024AH050101)
/
| 〈 |
|
〉 |