高级检索
王茂森,鲍久圣,鲍周洋,等. 融合金字塔结构与注意力机制的煤矿井下巡检机器人PT目标检测算法[J]. 煤炭科学技术,2024,52(6):206−215. doi: 10.12438/cst.2023-1071
引用本文: 王茂森,鲍久圣,鲍周洋,等. 融合金字塔结构与注意力机制的煤矿井下巡检机器人PT目标检测算法[J]. 煤炭科学技术,2024,52(6):206−215. doi: 10.12438/cst.2023-1071
WANG Maosen,BAO Jiusheng,BAO Zhouyang,et al. Research on mine underground inspection robot target detection algorithm based on pyramid structure and attention mechanism coupling[J]. Coal Science and Technology,2024,52(6):206−215. doi: 10.12438/cst.2023-1071
Citation: WANG Maosen,BAO Jiusheng,BAO Zhouyang,et al. Research on mine underground inspection robot target detection algorithm based on pyramid structure and attention mechanism coupling[J]. Coal Science and Technology,2024,52(6):206−215. doi: 10.12438/cst.2023-1071

融合金字塔结构与注意力机制的煤矿井下巡检机器人PT目标检测算法

Research on mine underground inspection robot target detection algorithm based on pyramid structure and attention mechanism coupling

  • 摘要: 近年来,煤矿机器人已成为现代煤机装备领域的研究热点,多数煤矿的主煤流运输系统基本实现了连续化、机械化和自动化,因此对主运输巷道内的安全监控与巡检效率提出了更高的要求,而精准的目标检测是实现煤矿井下智能化安全监控的必要保障,但现有的目标检测算法应用于复杂恶劣的煤矿井下巷道环境,存在目标检测精度较低的问题。面向井下低照明、环境杂乱的特殊工况检测需求,制作了井下巷道环境内目标物数据集,完成数据集标注并展开多维度分析;提出一种基于金字塔结构与注意力机制融合的PT目标检测算法,利用注意力机制模块替换金字塔结构中的卷积模块,在控制特征计算量的同时提高对全局特征的提取能力,实现目标物局部特征与全局特征融合的提取效果,提高了图像中目标感兴趣区域特征的表达能力。最后,面向煤矿井下巡检机器人应用场景,将提出的PT算法与传统经典的Faster R-CNN、YOLOv4算法进行对比分析。结果表明:所提出的PT目标检测算法能够有效识别复杂环境下巷道内目标物,相较于主流的Faster R-CNN、YOLOv4目标检测网络,PT算法有更好的综合识别能力,识别煤矿人员的准确率分别提升了2.90%和4.30%,识别井下障碍的准确率分别提升0.20%和4.80%,识别矿井裂缝的准确率分别提升了4.40%和8.60%,识别井下设备的准确率分别提升了3.00%和8.70%。因此,PT目标检测算法能够更好地适应井下环境,目标检测算法较其他算法能够获得更高的准确率与检测速度,可为井下巷道安控系统建设提供理论依据与技术支撑。

     

    Abstract: In recent years, coal mine robots have become a research hotspot in the field of modern coal machine equipment, and the main coal flow transportation system of most coal mines has basically realized continuity, mechanization and automation, which also puts forward higher requirements for safety monitoring and inspection efficiency in the main transportation roadway, and accurate target detection is a necessary guarantee for intelligent safety monitoring in coal mines, but the existing object detection algorithm is applied to complex and harsh coal mine underground roadway environment, and there is a problem of low target detection accuracy. Aiming at the special working condition detection requirements of low lighting and chaotic environment in the downhole, the target data set in the underground roadway environment was produced, and the dataset annotation was completed and multi-dimensional analysis was carried out. A PT target detection algorithm based on the fusion of pyramid structure and attention mechanism is proposed, and the attention mechanism module is used to replace the convolution module in the pyramid structure, which improves the extraction ability of global features while controlling the amount of feature calculation, realizes the extraction effect of the fusion of local features and global features of the target, and improves the expression ability of the features of the target area of interest in the image. Finally, for the application scenario of underground inspection robot in coal mine, the proposed PT algorithm is compared with the traditional Faster R-CNN and YOLOv4 algorithms. Compared with the mainstream Faster R-CNN and YOLOv4 target detection networks, the PT algorithm has better comprehensive recognition capabilities, and the accuracy of identifying coal mine personnel is increased by 2.90% and 4.30%, the accuracy of identifying underground obstacles is increased by 0.20% and 4.80%, and the accuracy of identifying mine cracks is increased by 4.40% and 8.60%, respectively. The accuracy rate of identifying downhole equipment was improved by 3.00% and 8.70%, respectively. Therefore, the PT target detection algorithm can better adapt to the underground environment, and the target detection algorithm can obtain higher accuracy and detection speed than other algorithms, which can provide theoretical basis and technical support for the construction of underground roadway security control system.

     

/

返回文章
返回