基于融合边缘优化的煤矿图像语义分割方法
Images semantic segmentation method based on fusion edge optimization
-
摘要: 由于煤矿井下环境恶劣，使得煤矿井下视频获取的图像严重降质，而现有的基于深度学习的语义分割模型在图片清晰化后存在边缘分割模糊的问题，提出了一种采用融合边缘优化模块处理边界信息并运用门控卷积层连接传统特征提取模块并行处理信息的方法；为监督学习轮廓信息，采用二元交叉熵损失函数提高学习效果，并与常规分支的损失函数共同优化模型分割效果。试验结果表明：对已完成清晰化的煤矿井下图像进行语义分割任务时，基于融合边缘优化模块的方法与其他方法相比整体语义分割精度得到提升并且边缘分割精度更高。Abstract: Due to the poor underground environment, which makes the images of underground video in coal mines seriously degraded. However, the existing semantic segmentation model based on deep learning has the problem of fuzzy edge segmentation after image sharpness. A new method is proposed, which uses the fusion edge optimization module to process the boundary information and uses the gated convolution layer to connect the traditional feature extraction module to process the information in parallel. In order to supervise the learning of contour information, the binary cross entropy loss function was used to improve the learning effect, and the segmentation effect was optimized together with the loss function of conventional branches. The experimental results show that compared with other methods, the method based on the fusion edge optimization module improves the overall semantic segmentation accuracy and edge segmentation accuracy when the semantic segmentation task of the clarified coal mine image is performed.
-
-
[1] 田丽军.煤矿监控中火灾图像分割方法研究[J].煤炭技术，2011，30（7）：83-85. TIAN Lijun. Research on fires image segmentation technology in coal mine surveillance[J]. Coal Technology, 2011, 30（7）: 83-85.
[2] 李忠杰，胡文涛，胡宁.图像分割技术在煤矿生产中的应用[J].价值工程，2012，31（11）：151-152. LI Zhongjie, HU Wentao, HU Ning. Image segmentation techniques applied in coal production[J]. Value Engineering, 2012, 31（11）: 151-152.
[3] 王羽，金婵，汪丽华，等.基于SEM图像灰度水平的页岩孔隙分割方法研究[J].岩矿测试，2016，35（6）：595. WANG Yu, JIN Chan, WANG Lihua, et al. Pore segmentation methods based on gray scale of scanning electron microscopy images[J]. Rock & Mineral Analysis, 2016, 35（6）:595-602.
[4] 韩斌，吴一全，倪康.利用改进CV模型分割煤矿井下早期火灾图像[J].中国矿业大学学报，2018，47（2）：429-435. HAN Bin, WU Yiquan, NI Kang. Segmentation of early fire image of mine using improved CV model[J]. Journal of China University of Mining & Technology, 2018, 47（2）: 429-435.
[5] F Yu, Koltun V. Multi-Scale Context Aggregation by Dilated Convolutions[C]// International Conference on Lear-ning Representations (ICLR). ResearchGate, 2016. [6] Chen L C, Papandreou G, Kokkinos I, et al. Semantic Image Segmentation with Deep Convolutional Nets and Fully Con-nected CRFs[J]. Computer Science, 2014（4）: 357-361. [7] Liu J W, Li H E, Luo X L. Learning technique of probabilistic graphical models: A review[J]. Acta Automatica Sinica, 2014, 40（6）: 1025-1044. [8] Chen L C, Papandreou G, Kokkinos I, et al. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40（4）: 834-848. [9] Chen L C, Papandreou G, Kokkinos I, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 40（4）: 834-848. [10] Yang M, Yu K, Zhang C, et al. Denseaspp for semantic segmentation in street scenes[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 2018: 3684-3692. [11] Badrinarayanan V, Kendall A, Cipolla R. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation[J/OL]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017: DOI: 10.17863/CAM.17966. [12] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentationn[C]//International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015: 234-241. [13] Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation[C]//Proceedings of the IEEE international conference on computer vision. IEEE, 2015: 1520-1528. [14] Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmenta-tion[C]//Proceedings of the European conference on computer vision （ECCV）. ResearchGate, 2018: 801-818. [15] Kunfeng W, Chao G, Yanjie D. Research progress and Prospect of generative countermeasure network Gan[J]. Acta automatica Sinica, 2017, 43（3）: 321-332. [16] 张嘉祺，赵晓丽，董晓亚，等.面向图像语义分割的生成对抗网络模型[J].传感器与微系统，2019，38（8）：50-53. ZHANG Jiaqi, ZHAO Xiaoli, DONG Xiaoya, et al. Generative adversarial network model for image semantic segmentation[J]. Transducer and Microsystem Technologies, 2019, 38（8）: 50-53.
[17] Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 2017: 2881-2890. [18] Lin G, Milan A, Shen C, et al. Refinenet: Multi-path refinement networks for high-resolution semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 2017: 1925-1934. [19] Nekrasov V, Shen C, Reid I. Light-Weight RefineNet for Real-Time Semantic Segmentation[J/OL]. arXiv:1810.03272, 2018. -
期刊类型引用(5)
1. 李帅，王志飞，李樊，杜呈欣，王浩东，杨博璇. 基于机器视觉的高速铁路站车联动控制技术. 科学技术与工程. 2025(02): 773-779 . 
百度学术
2. 黄东东，何芳芳，桂益龙. 基于边缘计算的全封闭圆形煤场储量自动测绘方法. 自动化技术与应用. 2025(02): 127-131 . 百度学术
3. 李涛，邹英杰，范洪冬，吝涛. 基于DBD-Net的InSAR矿区开采沉陷盆地检测方法. 煤矿安全. 2024(04): 177-186 . 本站查看
4. 徐芳. 基于最小生成树的数字图像层次化分割方法研究. 重庆科技学院学报(自然科学版). 2023(01): 74-78 . 百度学术
5. 季亮. 基于改进SOLOv2的煤矿图像实例分割方法. 工矿自动化. 2023(11): 115-120 . 百度学术
其他类型引用(4)
计量
- 文章访问数: 32
- HTML全文浏览量: 0
- PDF下载量: 12
- 被引次数: 9
下载:
