An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors
RGB-D sensors have been widely used in various areas of computer vision and graphics. A good descriptor will effectively improve the performance of operation. This article further analyzes the recognition performance of shape features extracted from multi-modality source data using RGB-D sensors. A...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/17/3/451 |
| _version_ | 1828747665108631552 |
|---|---|
| author | Zhong Liu Changchen Zhao Xingming Wu Weihai Chen |
| author_facet | Zhong Liu Changchen Zhao Xingming Wu Weihai Chen |
| author_sort | Zhong Liu |
| collection | DOAJ |
| description | RGB-D sensors have been widely used in various areas of computer vision and graphics. A good descriptor will effectively improve the performance of operation. This article further analyzes the recognition performance of shape features extracted from multi-modality source data using RGB-D sensors. A hybrid shape descriptor is proposed as a representation of objects for recognition. We first extracted five 2D shape features from contour-based images and five 3D shape features over point cloud data to capture the global and local shape characteristics of an object. The recognition performance was tested for category recognition and instance recognition. Experimental results show that the proposed shape descriptor outperforms several common global-to-global shape descriptors and is comparable to some partial-to-global shape descriptors that achieved the best accuracies in category and instance recognition. Contribution of partial features and computational complexity were also analyzed. The results indicate that the proposed shape features are strong cues for object recognition and can be combined with other features to boost accuracy. |
| first_indexed | 2024-04-14T04:46:33Z |
| format | Article |
| id | doaj.art-5b3cd52263f347bd960893755afb986f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T04:46:33Z |
| publishDate | 2017-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5b3cd52263f347bd960893755afb986f2022-12-22T02:11:27ZengMDPI AGSensors1424-82202017-02-0117345110.3390/s17030451s17030451An Effective 3D Shape Descriptor for Object Recognition with RGB-D SensorsZhong Liu0Changchen Zhao1Xingming Wu2Weihai Chen3School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaRGB-D sensors have been widely used in various areas of computer vision and graphics. A good descriptor will effectively improve the performance of operation. This article further analyzes the recognition performance of shape features extracted from multi-modality source data using RGB-D sensors. A hybrid shape descriptor is proposed as a representation of objects for recognition. We first extracted five 2D shape features from contour-based images and five 3D shape features over point cloud data to capture the global and local shape characteristics of an object. The recognition performance was tested for category recognition and instance recognition. Experimental results show that the proposed shape descriptor outperforms several common global-to-global shape descriptors and is comparable to some partial-to-global shape descriptors that achieved the best accuracies in category and instance recognition. Contribution of partial features and computational complexity were also analyzed. The results indicate that the proposed shape features are strong cues for object recognition and can be combined with other features to boost accuracy.http://www.mdpi.com/1424-8220/17/3/451shape descriptorcategory recognitioninstance recognitionRGB-D sensors |
| spellingShingle | Zhong Liu Changchen Zhao Xingming Wu Weihai Chen An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors Sensors shape descriptor category recognition instance recognition RGB-D sensors |
| title | An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors |
| title_full | An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors |
| title_fullStr | An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors |
| title_full_unstemmed | An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors |
| title_short | An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors |
| title_sort | effective 3d shape descriptor for object recognition with rgb d sensors |
| topic | shape descriptor category recognition instance recognition RGB-D sensors |
| url | http://www.mdpi.com/1424-8220/17/3/451 |
| work_keys_str_mv | AT zhongliu aneffective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT changchenzhao aneffective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT xingmingwu aneffective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT weihaichen aneffective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT zhongliu effective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT changchenzhao effective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT xingmingwu effective3dshapedescriptorforobjectrecognitionwithrgbdsensors AT weihaichen effective3dshapedescriptorforobjectrecognitionwithrgbdsensors |