Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot
In view of terrain classification of the autonomous multi-legged walking robots, two synthetic classification methods for terrain classification, Simple Linear Iterative Clustering based Support Vector Machine (SLIC-SVM) and Simple Linear Iterative Clustering based SegNet (SLIC-SegNet), are proposed...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/9/2808 |
| _version_ | 1798039405432143872 |
|---|---|
| author | Yaguang Zhu Kailu Luo Chao Ma Qiong Liu Bo Jin |
| author_facet | Yaguang Zhu Kailu Luo Chao Ma Qiong Liu Bo Jin |
| author_sort | Yaguang Zhu |
| collection | DOAJ |
| description | In view of terrain classification of the autonomous multi-legged walking robots, two synthetic classification methods for terrain classification, Simple Linear Iterative Clustering based Support Vector Machine (SLIC-SVM) and Simple Linear Iterative Clustering based SegNet (SLIC-SegNet), are proposed. SLIC-SVM is proposed to solve the problem that the SVM can only output a single terrain label and fails to identify the mixed terrain. The SLIC-SegNet single-input multi-output terrain classification model is derived to improve the applicability of the terrain classifier. Since terrain classification results of high quality for legged robot use are hard to gain, the SLIC-SegNet obtains the satisfied information without too much effort. A series of experiments on regular terrain, irregular terrain and mixed terrain were conducted to present that both superpixel segmentation based synthetic classification methods can supply reliable mixed terrain classification result with clear boundary information and will put the terrain depending gait selection and path planning of the multi-legged robots into practice. |
| first_indexed | 2024-04-11T21:53:26Z |
| format | Article |
| id | doaj.art-cdade438b4e043a8851b14aa6c271300 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:53:26Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cdade438b4e043a8851b14aa6c2713002022-12-22T04:01:10ZengMDPI AGSensors1424-82202018-08-01189280810.3390/s18092808s18092808Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged RobotYaguang Zhu0Kailu Luo1Chao Ma2Qiong Liu3Bo Jin4Key Laboratory of Road Construction Technology and Equipment of MOE, Chang’an University, Xi’an 710064, ChinaKey Laboratory of Road Construction Technology and Equipment of MOE, Chang’an University, Xi’an 710064, ChinaKey Laboratory of Road Construction Technology and Equipment of MOE, Chang’an University, Xi’an 710064, ChinaKey Laboratory of Road Construction Technology and Equipment of MOE, Chang’an University, Xi’an 710064, ChinaState Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310028, ChinaIn view of terrain classification of the autonomous multi-legged walking robots, two synthetic classification methods for terrain classification, Simple Linear Iterative Clustering based Support Vector Machine (SLIC-SVM) and Simple Linear Iterative Clustering based SegNet (SLIC-SegNet), are proposed. SLIC-SVM is proposed to solve the problem that the SVM can only output a single terrain label and fails to identify the mixed terrain. The SLIC-SegNet single-input multi-output terrain classification model is derived to improve the applicability of the terrain classifier. Since terrain classification results of high quality for legged robot use are hard to gain, the SLIC-SegNet obtains the satisfied information without too much effort. A series of experiments on regular terrain, irregular terrain and mixed terrain were conducted to present that both superpixel segmentation based synthetic classification methods can supply reliable mixed terrain classification result with clear boundary information and will put the terrain depending gait selection and path planning of the multi-legged robots into practice.http://www.mdpi.com/1424-8220/18/9/2808boundary informationlegged robotsuperpixel segmentationterrain classification |
| spellingShingle | Yaguang Zhu Kailu Luo Chao Ma Qiong Liu Bo Jin Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot Sensors boundary information legged robot superpixel segmentation terrain classification |
| title | Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot |
| title_full | Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot |
| title_fullStr | Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot |
| title_full_unstemmed | Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot |
| title_short | Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot |
| title_sort | superpixel segmentation based synthetic classifications with clear boundary information for a legged robot |
| topic | boundary information legged robot superpixel segmentation terrain classification |
| url | http://www.mdpi.com/1424-8220/18/9/2808 |
| work_keys_str_mv | AT yaguangzhu superpixelsegmentationbasedsyntheticclassificationswithclearboundaryinformationforaleggedrobot AT kailuluo superpixelsegmentationbasedsyntheticclassificationswithclearboundaryinformationforaleggedrobot AT chaoma superpixelsegmentationbasedsyntheticclassificationswithclearboundaryinformationforaleggedrobot AT qiongliu superpixelsegmentationbasedsyntheticclassificationswithclearboundaryinformationforaleggedrobot AT bojin superpixelsegmentationbasedsyntheticclassificationswithclearboundaryinformationforaleggedrobot |