Lightweight semantic segmentation for digital workshop objects

被引：0

作者：

Yi J. ^{[1
]}

Chen G. ^{[1
]}

Ru Q. ^{[2
]}

Li M. ^{[1
]}

机构：

[1] College of Nuclear Technology and Automation Engineering, Chengdu University of Technology, Chengdu

[2] College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2023年 / 29卷 / 03期

关键词：

digital workshop; lightweight; MobileNetv2; real-time; semantic segmentation;

D O I：

10.13196/j.cims.2023.03.021

中图分类号：

学科分类号：

摘要：

To meet the real-time demand of manufacturing in the digital workshop, a lightweight semantic segmentation network named Multi Pyramid Pooling Segmentation Network (MPPSNet) that satisfied both accuracy and real-time was proposed, which realized the semantic segmentation for the goal of digital workshop. The improved MobileNetv2 was used as the encoder of semantic segmentation network in MPPSNet, which effectively reduced the amount of network parameters and improved the real-time performance of the overall network operation; the multi-pyramid pooling network was used as the decoder of the segmentation network, which could integrate multiple layers of feature information and improve the accuracy of the network. Tests found that the semantic segmentation effect of MPPSNet was better than that of FCN8 and BiSeNet in VOC20 12data set. In the self-building object semantic segmentation data set of the digital workshop, the Mean Intersection over Unions ( MIoU) of segmenting human, machine tool, and mobile robot of workshop objects reached 7 1.8% in MPPSNet and the parameter amount of the entire network was 2.55M, which could meet the accurate and real-time requirements of segmenting workshop objects. © 2023 CIMS. All rights reserved.

引用

页码：920 / 929

页数：9

共 28 条

[1] WANG Xinzhu, LI Jun, LI Hongjian, Et al., Obstacle detection based on 3D laser scanner and range image for intelligent vehicle[J], Journal of Jilin University : Engineering and Technology Edition, 46, 2, pp. 360-365, (2016)
[2] CHEN Yong, HUANG Xiyue, YANG Shanggang, Research and development of automotive collision avoidance system[J], Computer Simulation, 23, 12, pp. 239-243, (2006)
[3] HASCH J, TOPAK E, SCHNABEL R, Et al., Millimeter-wave technology for automotive radar sensors in the 77 GHz frequency band, IEEE Transactions on Microwave Theory & Techniques, 60, 3, pp. 845-860, (2013)
[4] WANG Rongben, LI Linhui, GUO Lie, Et al., Stereo vision based cross-country environmental perception technique [J], Journal of Jilin University: Engineering and Technology Edition, 38, 3, pp. 520-524, (2008)
[5] WANG Haltao, SONG Lihua, XIANG Tingling, Et al., Newd-evelopment direction of artificial intelligence-human cyber physical ternary fusion intelligence [J], Computer Science, 47, 11, pp. 17-22, (2020)
[6] LIU Tingyu, ZHONG Jle, LIU Yang, Et al., Intelligent small object detection approach for fast modeling of digital twin of global human working activities [J], Computer Integrated Manufacturing Systems, 25, 6, pp. 1463-1473, (2019)
[7] LI Chunlin, XIE Gang, WANG Yin, Et al., Defect detection of polaroid based on YOLOv3-Tiny-D algorithm [J], Computer Integrated Manufacturing Systems, 28, 3, pp. 787-797, (2022)
[8] LONG J, SHELHAMER E, DARRELL T., Fully convolution networks for semantic segmentation [C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)
[9] BADRINARAYANAN V, KENDALL A, CIPOLLA R, Et al., SegNet : A deep convolutional encoder-decoder architecture for image segmentation [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 12, pp. 2481-1495, (2017)
[10] CHAURASIA A, CULURCIELLO E., LinkNet: Exploiting encoder representations for efficient semantic segmentation, Proceedings of the Visual Communications and Image Processing, (2017)

← 1 2 3 →