Faculty of Electrical and Control Engineering, Liaoning Technical University

针对现有基于深度学习的电铲检测方法未能很好地平衡检测速度与检测精度的问题,提出了一种改进YOLOv7模型,并将其用于矿用电铲检测。该模型以YOLOv7模型为基础,在主干网络中采用轻量化GhostNet网络进行特征提取,在颈部网络中采用轻量级GSConv替换部分普通卷积,以减少模型参数量和计算量,提高模型检测速度;考虑到轻量化改进后模型参数量减少对特征信息提取能力的影响,在不增加计算量的前提下,对颈部网络进行进一步改进,在扩展高效层聚合网络(ELAN)中嵌入坐标注意力机制(CA),同时利用双向特征金字塔网络(BiFPN)改进路径聚合网络(PANet),以提高网络对特征信息的提取能力,进而有效提高模型检测精度。实验结果表明,与YOLOv7模型相比,改进YOLOv7模型的参数量减少了75.4%,每秒浮点运算次数减少了82.9%,检测速度提高了24.3%;相较于其他目标检测模型,改进YOLOv7模型在检测速度和检测精度方面取得了良好的平衡,满足在露天煤矿场景下对电铲进行实时、准确检测的需求,为嵌入到移动设备中提供了有利条件。

The existing deep learning based shovel detection methods fail to balance detection speed andprecision well. In order to solve the above problem, an improved YOLOv7 model is proposed and applied tomining shovel detection. This model is based on the YOLOv7 model, using a lightweight GhostNet network forfeature extraction in the backbone network. This model replaces some ordinary convolutions with lightweightGSConv in the neck network to reduce the number of model parameters and computation, and improve thedetection speed of the model. Considering the impact of reduced model parameters on feature informationextraction capability after lightweight improvement, the neck network is further improved without increasingcomputational complexity. The coordinate attention mechanism (CA) is embedded in the extended efficient layeraggregation network (ELAN). The bidirectional feature pyramid network (BiFPN) is used to improve pathaggregation network (PANet) to enhance the network's capability to extract feature information. Furthermore, iteffectively improves the precision of model detection. The experimental results show that compared with theYOLOv7 model, the improved YOLOv7 model reduces the number of parameters by 75.4%, reduces the numberof floating-point operations per second by 82.9%, and improves the detection speed by 24.3%. Compared with other object detection models, the improved YOLOv7 model achieves a good balance between detection speedand precision, meeting the demand for real-time and accurate detection of electric shovels in open-pit coal minescenarios. It provides favorable conditions for embedding into mobile devices.

辽宁省教育厅科学技术研究服务地方项目(LJ2019FL003)

宋立业,赵小萱,崔昊. 基于改进 YOLOv7 的矿用电铲检测算法[J]. 工矿自动化,2023,49(12):18-24, 32.

SONG Liye, ZHAO Xiaoxuan, CUI Hao. Mining shovel detection algorithm based on improved YOLOv7[J]. Journal of MineAutomation,2023,49(12):18-24, 32.