重庆理工大学学报（自然科学版）2018，Vol.32Issue(2)：166-173,8.DOI:10.3969/j.issn.1674-8425(z).2018.02.023
基于全卷积深度学习模型的可抓取物品识别
Fully Convolutional Deep Learning Model Based Graspable Object etection
摘要
Abstract
Most of the traditional industrial robots collected environmental information information through the image sensor,and used the particle filter or the conditional random field and other algorithms to extract the feature of the pixel blocks for the grabbed object detection.These methods was lack of the consideration of global information and structural information,deviation existed in the feature of the pixel block.In this research,taking Cornell Grasping Data set as experimental sample and applying fully convolutional networks based on pixels,we proposed an improvement model of fully convolutional networks for graspable object detection.The advantage of the model is predicting the category probability of each pixel by a learning way and spliting the output image into background and foreground.And then it gets the position and category of the graspable object.Since the full convolutional model did not limit the size of the input and output images,it overcame the shortcomings of the convolutional deep learning model,while the full convolutional model considered the global information and structural information.Experiments showed that our improvement fully convolutional deep learning model archived 6.2%higher than the fully convolutional deep learning model(fcn-8x). The proposed method can be used in other foreground segmentation perception tasks.关键词
深度学习模型/全卷积网络/物品识别/工业机器人Key words
deep learning model/fully convolutional network/object detection/industrial robot分类
计算机与自动化引用本文复制引用
皮思远,唐洪,肖南峰..基于全卷积深度学习模型的可抓取物品识别[J].重庆理工大学学报（自然科学版）,2018,32(2):166-173,8.基金项目
国家自然科学基金资助项目(61573145) （61573145）
广东省公益研究与能力建设专项资金资助项目(2014B010104001) （2014B010104001）
广东省省自然科学基金资助项目(2015A030308018) （2015A030308018）
