Study on traffic scene semantic segmentation method based on convolutional neural network
In order to improve the semantic segmentation accuracy of traffic scene,a segmentation method was proposed based on RGB-D image and convolutional neural network.Firstly,on the basis of semi-global stereo matching algorithm,the disparity map was obtained,and the sample library was established by fusi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2018-04-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018053/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539424770326528 |
|---|---|
| author | Linhui LI Bo QIAN Jing LIAN Weina ZHENG Yafu ZHOU |
| author_facet | Linhui LI Bo QIAN Jing LIAN Weina ZHENG Yafu ZHOU |
| author_sort | Linhui LI |
| collection | DOAJ |
| description | In order to improve the semantic segmentation accuracy of traffic scene,a segmentation method was proposed based on RGB-D image and convolutional neural network.Firstly,on the basis of semi-global stereo matching algorithm,the disparity map was obtained,and the sample library was established by fusing the disparity map D and RGB image into the four-channel RGB-D image.Then,with two different structures,the networks were trained by using two different learning rate adjustment strategy respectively.Finally,the traffic scene semantic segmentation test was carried out with RGB-D image as the input,and the results were compared with the segmentation method based on RGB image.The experimental results show that the proposed traffic scene segmentation algorithm based on RGB-D image can achieve higher semantic segmentation accuracy than that based on RGB image. |
| format | Article |
| id | doaj-art-6611fb1ccb4c4ed7b78dbb12b434293b |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2018-04-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-6611fb1ccb4c4ed7b78dbb12b434293b2025-01-14T07:14:36ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2018-04-013912313059717710Study on traffic scene semantic segmentation method based on convolutional neural networkLinhui LIBo QIANJing LIANWeina ZHENGYafu ZHOUIn order to improve the semantic segmentation accuracy of traffic scene,a segmentation method was proposed based on RGB-D image and convolutional neural network.Firstly,on the basis of semi-global stereo matching algorithm,the disparity map was obtained,and the sample library was established by fusing the disparity map D and RGB image into the four-channel RGB-D image.Then,with two different structures,the networks were trained by using two different learning rate adjustment strategy respectively.Finally,the traffic scene semantic segmentation test was carried out with RGB-D image as the input,and the results were compared with the segmentation method based on RGB image.The experimental results show that the proposed traffic scene segmentation algorithm based on RGB-D image can achieve higher semantic segmentation accuracy than that based on RGB image.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018053/deep learningconvolutional neural networktraffic scenesemantic segmentationdisparity map |
| spellingShingle | Linhui LI Bo QIAN Jing LIAN Weina ZHENG Yafu ZHOU Study on traffic scene semantic segmentation method based on convolutional neural network Tongxin xuebao deep learning convolutional neural network traffic scene semantic segmentation disparity map |
| title | Study on traffic scene semantic segmentation method based on convolutional neural network |
| title_full | Study on traffic scene semantic segmentation method based on convolutional neural network |
| title_fullStr | Study on traffic scene semantic segmentation method based on convolutional neural network |
| title_full_unstemmed | Study on traffic scene semantic segmentation method based on convolutional neural network |
| title_short | Study on traffic scene semantic segmentation method based on convolutional neural network |
| title_sort | study on traffic scene semantic segmentation method based on convolutional neural network |
| topic | deep learning convolutional neural network traffic scene semantic segmentation disparity map |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018053/ |
| work_keys_str_mv | AT linhuili studyontrafficscenesemanticsegmentationmethodbasedonconvolutionalneuralnetwork AT boqian studyontrafficscenesemanticsegmentationmethodbasedonconvolutionalneuralnetwork AT jinglian studyontrafficscenesemanticsegmentationmethodbasedonconvolutionalneuralnetwork AT weinazheng studyontrafficscenesemanticsegmentationmethodbasedonconvolutionalneuralnetwork AT yafuzhou studyontrafficscenesemanticsegmentationmethodbasedonconvolutionalneuralnetwork |