[1]侯枘辰,刘 瑜,廉 华,等.用于草坪场景理解的轻量化图像分割算法[J].计算机技术与发展,2020,30(10):59-63.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 011]
　HOU Rui-chen,LIU Yu,LIAN Hua,et al.Lightweight Image Segmentation for Lawn Scene Understanding[J].,2020,30(10):59-63.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 011]
点击复制

用于草坪场景理解的轻量化图像分割算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年10期
页码:
59-63
栏目:
智能、算法、系统工程
出版日期:
2020-10-10

文章信息/Info

Title:
Lightweight Image Segmentation for Lawn Scene Understanding
文章编号:
1673-629X(2020)10-0059-05
作者:
侯枘辰; 刘 瑜; 廉 华; 巩彦丽
浙江理工大学 机械与自动控制学院,浙江 杭州 310018
Author(s):
HOU Rui-chen; LIU Yu; LIAN Hua; GONG Yan-li
(Faculty of Mechanical Engineering & Automation,Zhejiang Sci-Tech University,Hangzhou 310018,China
关键词:
图像分割; 深度学习; 深度可分离卷积; RefineNet; 卷积神经网络
Keywords:
image segmentation; deep learning; deep separable convolution; RefineNet; convolutional neural network
分类号:
TP391. 4
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 10. 011
摘要:
为提高割草机器人作业过程中视觉感知模块的识别准确率,提出了使用图像分割算法进行草坪场景的理解识别。图像分割算法的计算量非常大,运行时依赖高性能的 GPU,而割草机器人的硬件条件较差,因此设计了一种兼顾分割准确率和运行速度的轻量化深度卷积神经网络。 网络采用编码-解码的结构,在编码网络部分,采用轻量化的特征提取模型,将深度可分离卷积的思想融入特征提取模型中,代替传统的卷积方式;在解码网络部分,基于 RefineNet 模块减少参数量,融合编码器的高分辨率特征和低分辨率特征。 使用 PASAL VOC2012 分割数据集进行预训练,构建草坪场景数据集进行微调和测试评估。 结果表明:提出的算法结构在保持较高准确率的前提下,网络的参数量有大幅度的减少,运行速率有大幅度提高,在机器人草坪场理解任务上有更好的综合性能。
Abstract:
In order to improve the recognition accuracy of visual perception module of the lawn mower,an image segmentation algorithm is proposed for recognizing and understanding lawn scenes. Image segmentation algorithm requires a large amount of computation,and its operation depends? ? ?on high-performance GPU,while the hardware condition of g lawn mower is poor. Therefore,a lightweight depth convolutional neural network with both segmentation accuracy and running speed is designed. The network adopts a encoding-decoding structure. In the part of encoding network,? ?a lightweight feature extraction model is adopted. The idea of deep separable convolution is integrated into feature extraction model to replace the traditional convolution method. In the part of decoding network,the parameters of RefineNet decoding module are reduced,fusing the high-resolution and low-resolution features of encoder. The PASAL VOC2012 segmentation dataset is used for pre-training,and the lawn scene dataset is construc-ted for fine-tuning and test evaluation. The results show that on the premise of maintaining high accuracy,the proposed algorithm structure can greatly reduce the number of network parameters and improve the speed of operation,which has better comprehensive performance in lawn scene understanding tasks of the lawn mower.

相似文献/References:

[1]蒋璐璐 王适 王宝成 李慧敏 李鑫慧.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010,(01):36.
　JIANG Lu-lu,WANG Shi,WANG Bao-cheng,et al.Segmentation of Remote Sensing Image Based on an Improved Labeling Watershed Algorithm[J].,2010,(10):36.
[2]张少娴 俞琼.基于时空相关性预测的运动估计的优化[J].计算机技术与发展,2010,(01):100.
　ZHANG Shao-xian,YU Qiong.An Optimization Method for Spatiotemporal Predictive Motion Estimation[J].,2010,(10):100.
[3]王兴 冯子亮.基于自适应初始值的FCM聚类图像分割[J].计算机技术与发展,2010,(03):101.
　WANG Xing,FENG Zi-liang.An Image Segmentation Algorithm Based on Adaptive Initialization FCM Clustering[J].,2010,(10):101.
[4]何小娜 逄焕利.基于二维直方图和改进蚁群聚类的图像分割[J].计算机技术与发展,2010,(03):128.
　HE Xiao-na,PANG Huan-li.Image Segmentation Based on Improved Ant Colony Clustering and Two- Dimensional Histogram[J].,2010,(10):128.
[5]宋淑娜 李金霞 胡学坤 高尚.一种自适应模糊阈值区间的图像分割方法[J].计算机技术与发展,2010,(05):121.
　SONG Shu-na,LI Jin-xia,HU Xue-kun,et al.A Method of Adaptive Fuzzy Threshold Region for Image Segmentation[J].,2010,(10):121.
[6]来磊 卢文科 邓开连.基于二维Tsallis交叉熵直线型图像阈值分割方法[J].计算机技术与发展,2010,(06):105.
　LAI Lei,LU Wen-ke,DENG Kai-lian.New Image Thresholding Segmentation Methods Based on Two-Dimensional Tsallis Cross-Entropy Liner-Type[J].,2010,(10):105.
[7]黄长专 王彪 杨忠.图像分割方法研究[J].计算机技术与发展,2009,(06):76.
　HUANG Chang-zhuan,WANG Biao,YANG Zhong.A Study on Image Segmentation Techniques[J].,2009,(10):76.
[8]李光耀 聂诗良.基于小波分解和模糊聚类的图像分割方法[J].计算机技术与发展,2009,(06):121.
　LI Guang-yao,NIE Shi-liang.Image Segment Algorithm Based on Wavelet Decomposition and Fuzzy Clustering Theory[J].,2009,(10):121.
[9]吴亚 汪继文.水平集图像分割中重新初始化规避的探索[J].计算机技术与发展,2009,(09):69.
　WU Ya,WANG Ji-wen.Avoidance of Re- Initialization in Level Set Image Segmentation[J].,2009,(10):69.
[10]李鑫环 陈立潮 赵红艳 赵勇.基于多小波分析与SOFM的MR图像分割算法研究[J].计算机技术与发展,2009,(09):104.
　LI Xin-huan,CHEN Li-chao,ZHAO Hong-yan,et al.Research on MR Image Segmentation Based on Multi- wavelet Analysis and SOFM[J].,2009,(10):104.
[11]张 婧,张 策*,张 茹,等.图像分割述评:基本概貌、典型算法及比较分析[J].计算机技术与发展,2024,34(01):1.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 001]
　ZHANG Jing,ZHANG Ce*,ZHANG Ru,et al.Review of Image Segmentation:Basic Overview,Typical Algorithms and Comparative Analysis[J].,2024,34(10):1.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 001]

更新日期/Last Update: 2020-10-10