基于HLNC-YOLO的密集养殖下湖羊行为识别方法

Method for Behavior Recognition of Hu Sheep in Intensive Farming Based on HLNC-YOLO

摘要:

湖羊的行为识别有助于其集约化和智能化养殖。在高密度饲养条件下，羊只间相互遮挡严重，导致现有行为识别方法易发生漏检与误检。为此，提出了一种高低频信息聚合的湖羊行为识别模型（HLNC-YOLO），用于识别密集养殖场景下的湖羊行为。采集养殖场湖羊站立、躺卧、进食和饮水4种典型行为图像，构建湖羊行为识别数据集HSBD（Hu sheep behavior dataset）。在YOLO v8主干网络中融入高低频信息聚合的C2F-HLAtt模块以感知被遮挡目标，引入辅助判断分支保留更多有效特征，采用基于定位框综合分数的负样本综合损失（Comprehensive score regression loss，CSLosss）降低次优框分数，提升被遮挡目标框的综合分数。在模型推理阶段使用综合分数衰减后处理算法（Soft comprehensive score non-maximal suppression，Soft-CS-NMS）筛选预测框。在HSBD数据集上进行测试，HLNC-YOLO的平均精度均值（mAP@50）为87.8%，内存占用量为17.4MB。较YOLO v8、YOLO v9、YOLO v10和Faster R-CNN平均精度均值分别提高7.1、2.2、4.6、11个百分点。研究表明，HLNC-YOLO实现了密集养殖湖羊行为的准确识别，具有泛化能力，可为智慧养殖提供技术支持。

Abstract:

Behavior recognition of Hu sheep contributes to their intensive and intelligent farming. Due to the generally high density of Hu sheep farming, severe occlusion occurs among different behaviors and even among sheep performing the same behavior, leading to missing and false detection issues in existing behavior recognition methods. A high-low frequency aggregated attention and negative sample comprehensive score loss and comprehensive score soft non-maximum suppression-YOLO (HLNC-YOLO) was proposed for identifying the behavior of Hu sheep, addressing the issues of missed and erroneous detections caused by occlusion between Hu sheep in intensive farming. Firstly, images of four typical behaviors—standing, lying, eating, and drinking—were collected from the sheep farm to construct the Hu sheep behavior dataset (HSBD). Next, to solve the occlusion issues, during the training phase, the C2F-HLAtt module was integrated, which combined high-low frequency aggregation attention, into the YOLO v8 Backbone to perceive occluded objects and introduce an auxiliary reversible branch to retain more effective features. Using comprehensive score regression loss (CSLoss) to reduce the scores of suboptimal boxes and enhance the comprehensive scores of occluded object boxes. Finally, the soft comprehensive score non-maximal suppression (Soft-CS-NMS) algorithm filtered prediction boxes during the inferencing. Testing on the HSBD, HLNC-YOLO achieved a mean average precision (mAP@50) of 87.8%, with a memory footprint of 17.4MB. This represented an improvement of 7.1, 2.2, 4.6, and 11 percentage points over YOLO v8, YOLO v9, YOLO v10, and Faster R-CNN, respectively. Research indicated that the HLNC-YOLO accurately identified the behavior of Hu sheep in intensive farming and possessed generalization capabilities, providing technical support for smart farming.