Multi-category Segmentation of Orchard Scene Based on Improved DeepLab V3 +

被引：0

作者：

Liu H. ^{[1
]}

Jiang J. ^{[1
]}

Shen Y. ^{[1
]}

Jia W. ^{[2
]}

Zeng X. ^{[1
]}

Zhuang Z. ^{[1
]}

机构：

[1] School of Electrical and Information Engineering, Jiangsu University, Zhenjiang

[2] School of Agricultural Engineering, Jiangsu University, Zhenjiang

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2022年 / 53卷 / 11期

关键词：

DeepLab V3 +; hybrid dilated convolution; orchard; receptive field; semantic segmentation; spray robot;

D O I：

10.6041/j.issn.1000-1298.2022.11.025

中图分类号：

学科分类号：

摘要：

Real-time detection of orchard environment is an important prerequisite to ensure the accurate operation of orchard spray robot. An improved DeepLab V3 + semantic segmentation model was proposed for multi-category segmentation in orchard scene. For deployment on the orchard spray robot, the lightweight MobileNet V2 network was used to replace the original Xception network to reduce the network parameters, and ReLU6 activation function was applied in atrous spatial pyramid pooling (ASPP) module to reduce the loss of accuracy when deployed in mobile devices. In addition, hybrid dilated convolution (HDC) was combined to replace the void convolution in the original network. The dilated rates in ASPP were prime to each other to reduce the grid effect of dilated convolution. The RGB images of orchard scene were collected by using visual sensor, and eight common targets were selected to make the dataset, such as fruit trees, pedestrians and sky. On this dataset, DeepLab V3 + before and after improvement was trained, verified and tested based on Pytorch. The results showed that the mean pixel accuracy and mean intersection over union of the improved Deeplab V3 + model were 62. 81% and 56. 64%, respectively, which were 5. 52 percentage points and 8. 75 percentage points higher than before improvement. Compared with the original model, the parameters were reduced by 88. 67% . The segmentation time of a single image was 0. 08 s, which was 0. 09 s less than the original model. In particular, the accuracy of tree segmentation reached 95. 61%, which was 1. 31 percentage points higher than before improvement. This method can provide an effective decision for precision spraying and safe operation of the spraying robot, and it was practical. © 2022 Chinese Society of Agricultural Machinery. All rights reserved.

引用

页码：255 / 261

页数：6

共 24 条

[1] BIAN Yongliang, LI Jianping, XUE Chunlin, Et al., Analysis on status quo and prospects of intelligent development of air-feed sprayer in orchard, Journal of Northeast Agricultural University, 51, 2, pp. 86-94, (2020)
[2] JIN Y C, LIU J Z, XU Z J, Et al., Development status and trend of agricultural robot technology[J], International Journal of Agricultural and Biological Engineering, 14, 4, pp. 1-19, (2021)
[3] WANG Ning, ZHAI Changyuan, ZHAO Chunjiang, WANG Ning, Et al., Research progress on precision control methods of air-assisted spraying in orchards, Transactions of the CSAE, 34, 10, pp. 1-15, (2018)
[4] JIANG Shijie, MA Hengtao, YANG Shenghui, Et al., Target detection and tracking system for orchard spraying robots, Transactions of the CSAE, 37, 9, pp. 31-39, (2021)
[5] NAN Yulong, ZHANG Huichun, XU Youlin, Et al., Research progress on profiling target spray and its control technology in agriculture and forestry, World Forestry Research, 31, 4, pp. 54-58, (2018)
[6] 10, 9, pp. 80-82, (2020)
[7] SUN Jun, ZHANG Yuechun, MAO Hanping, Et al., Responses analysis of lettuce leaf pollution in cadmium stress based on computer vision, Transactions of the Chinese Society for Agricultural Machinery, 49, 3, pp. 166-172, (2018)
[8] QIAN Liang, Research on precise pesticide platform based on DSP and machine vision [ J ], Journal of Agricultural Mechanization Research, 43, 11, pp. 120-124, (2021)
[9] YUAN Hongbo, ZHAO Nudong, CHENG Man, Review of weeds recognition based on image processing, Transactions of the Chinese Society for Agricultural Machinery, 51, pp. 323-334, (2020)
[10] XIONG Juntao, LIU Bolin, ZHONG Zhuo, Et al., Litchi flower and leaf segmentation and recognition based on deep semantic segmentation, Transactions of the Chinese Society for Agricultural Machinery, 52, 6, pp. 252-258, (2021)

← 1 2 3 →