Fan Yingbo, Mao Shanjun, Li Mei, Wu Zheng, Kang Jitong
Institute of Remote Sensing and Geographic Information Systems, Peking University, No. 5 Summer Palace Road, Beijing 100871, China.
Sensors (Basel). 2024 Mar 14;24(6):1866. doi: 10.3390/s24061866.
With the continuous development of deep learning, the application of object detection based on deep neural networks in the coal mine has been expanding. Simultaneously, as the production applications demand higher recognition accuracy, most research chooses to enlarge the depth and parameters of the network to improve accuracy. However, due to the limited computing resources in the coal mining face, it is challenging to meet the computation demands of a large number of hardware resources. Therefore, this paper proposes a lightweight object detection algorithm designed specifically for the coal mining face, referred to as CM-YOLOv8. The algorithm introduces adaptive predefined anchor boxes tailored to the coal mining face dataset to enhance the detection performance of various targets. Simultaneously, a pruning method based on the L1 norm is designed, significantly compressing the model's computation and parameter volume without compromising accuracy. The proposed algorithm is validated on the coal mining dataset DsLMF+, achieving a compression rate of 40% on the model volume with less than a 1% drop in accuracy. Comparative analysis with other existing algorithms demonstrates its efficiency and practicality in coal mining scenarios. The experiments confirm that CM-YOLOv8 significantly reduces the model's computational requirements and volume while maintaining high accuracy.
随着深度学习的不断发展，基于深度神经网络的目标检测在煤矿中的应用不断拓展。同时，由于生产应用对识别精度要求更高，大多数研究选择增大网络深度和参数来提高精度。然而，由于采煤工作面的计算资源有限，满足大量硬件资源的计算需求具有挑战性。因此，本文提出了一种专门为采煤工作面设计的轻量级目标检测算法，即CM-YOLOv8。该算法引入了针对采煤工作面数据集定制的自适应预定义锚框，以提高对各种目标的检测性能。同时，设计了一种基于L1范数的剪枝方法，在不损失精度的情况下显著压缩模型的计算量和参数量。所提算法在煤矿数据集DsLMF+上进行了验证，在模型体积上实现了40%的压缩率，精度下降不到1%。与其他现有算法的对比分析表明了其在采煤场景中的有效性和实用性。实验证实，CM-YOLOv8在保持高精度的同时，显著降低了模型的计算需求和体积。
