Mine operation vehicle detection method and system based on deep learning

• Main Authors: LI LIGANG, LI SHUXUE, BAI DI, WANG GUOCAI, WEI SHENGJIE, WU ZHENYU, CHENG SHU-KWAN, TIAN WENMING
• Format: Patent
• Language: Chinese; English
• Published: 05.01.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses a deep learning-based mine operation vehicle detection method and system. The method comprises the steps of collecting and marking a mine operation vehicle detection data set; constructing and training a mine operation vehicle detection network model; and using the trained mine operation vehicle detection network model to detect an operation vehicle target in real time, automatically making a decision and an alarm according to a detection result, and displaying the detection result on a monitoring interface in real time. According to the invention, a convolution combination module DCBL is designed in the YOLO v4 network, the difference of remote cross-layer connection fusion feature levels is reduced, and the operation speed of the system is improved by replacing common convolution with depth separable convolution. 本发明公开了一种基于深度学习的矿山作业车辆检测方法及系统，包括：采集并标注矿山作业车辆检测数据集；构建并训练矿山作业车辆检测网络模型；利用训练好的所述矿山作业车辆检测网络模型实时检测作业车辆目标，自动根据检测结果，做出决策和警告，并将检测结果实时显示在监控界面上。本发明在YOLO v4网络中设计了卷积组合模块DCBL，降低了远距离跨层连接融合特