高级检索
高 涵,赵培培,于 正,等. 基于特征增强与Transformer的煤矿输送带异物检测[J]. 煤炭科学技术,2024,52(7):199−208. doi: 10.12438/cst.2023-1336
引用本文: 高 涵,赵培培,于 正,等. 基于特征增强与Transformer的煤矿输送带异物检测[J]. 煤炭科学技术,2024,52(7):199−208. doi: 10.12438/cst.2023-1336
GAO Han,ZHAO Peipei,YU Zheng,et al. Coal mine conveyor belt foreign object detection based on feature enhancement and Transformer[J]. Coal Science and Technology,2024,52(7):199−208. doi: 10.12438/cst.2023-1336
Citation: GAO Han,ZHAO Peipei,YU Zheng,et al. Coal mine conveyor belt foreign object detection based on feature enhancement and Transformer[J]. Coal Science and Technology,2024,52(7):199−208. doi: 10.12438/cst.2023-1336

基于特征增强与Transformer的煤矿输送带异物检测

Coal mine conveyor belt foreign object detection based on feature enhancement and Transformer

  • 摘要: 输送带是煤矿井下最重要的运输设备之一,在输送工作中会因锚杆、槽钢、大块矸石等异物混入造成输送带撕裂、落煤口阻塞等重大安全事故,严重影响运输效率,甚至威胁工人生命安全。为了解决现有输送带异物检测算法存在的对细长物体表征能力弱、弱语义特征提取能力差等问题,设计了一种基于低层级特征增强与Transformer机制的异物检测算法 (Feature Enhancement and Transformer YOLO, FET–YOLO)。首先,针对现有检测网络难以提取细长物体特征的问题,引入可变形卷积以提升网络对细长异物的形状特性的适应性,并使用MobileViT模块增加图像中异物与背景的区分度,以提取出更符合细长异物的多样性特征,削弱背景噪声的干扰;其次,构建低层级特征增强模块(Low-Level Feature Enhancement Module, LFEM),提升异物弱语义特征在检测网络中的表达能力,以降低漏检、错检的概率;最后,引入鬼影混洗卷积(GSConv)减少因特征图尺寸变化造成的信息丢失,保证网络高效提取特征的同时,减少模型参数量。利用煤矿井下输送带工作视频制作训练集和验证集,并将提出的算法与现有的3种输送带检测算法对比,实验结果表明:所提出的算法可以更好的解决输送带异物目标检测中细长物体检测效果差、弱语义特征提取困难的问题,具有更高的检测精度、同时符合输送带检测场景对检测实时性的要求,对于分辨率大小为640×640的图像mAP@0.5可达0.875,mAP@0.5:0.95可达0.543,检测速度为75 fps。

     

    Abstract: Conveyor belt is one of the most important transportation equipment in underground coal mines. Anchor rod, channel steel, large gangue, and other foreign objects that are mixed with the conveyor belt during conveying operations cause the belt to tear, clog the coal drop opening, and cause other serious safety incidents. They seriously affect the efficiency of transportation and even threaten the lives of workers. Aiming at the existing conveyor belt foreign object detection algorithm’s problems such as weak characterization of slender objects and poor weak semantic feature extraction, a foreign object detection algorithm based on low-level feature enhancement with Transformer is designed, notated as FET–YOLO. Firstly, to address the problem that existing detection networks have difficulty in extracting features of elongated objects, deformable convolution is introduced to enhance the network’s adaptability to the shape characteristics of elongated foreign objects, and the MobileViT module is used to increase the differentiation between the foreign objects and the background in the image, in order to extract features that are more consistent with the diversity of the elongated foreign objects and to weaken the interference of background noise.Secondly, constructing a low-level feature enhancement module LFEM, to improve the representation of weak semantic features of foreign objects in the detection network in order to reduce the probability of wrong detection.Finally, the introduction of gsconv reduces the information loss due to changes in the size of the feature map and ensures that the network extracts features efficiently while reducing the number of model parameters. The training set and validation set are produced by using the video of conveyor belt work in an underground coal mine. The proposed algorithm is compared to three other conveyor belt detection algorithms, and the experimental results show that the proposed algorithm can better solve the problems of poor detection of elongated objects and difficulty in weak semantic feature extraction in conveyor belt foreign object target detection, with higher detection accuracy. For images with a resolution size of 640×640, the performance metrics mAP@0.5 can be up to 0.875, mAP@0.5:0.95 can be up to 0.543, and the detection speed is 75 fps.

     

/

返回文章
返回