A Versatile Method for Depth Data Error Estimation in RGB-D Sensors
We propose a versatile method for estimating the RMS error of depth data provided by generic 3D sensors with the capability of generating RGB and depth (D) data of the scene, i.e., the ones based on techniques such as structured light, time of flight and stereo. A common checkerboard is used, the co...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/9/3122 |
| _version_ | 1798038410680598528 |
|---|---|
| author | Elizabeth V. Cabrera Luis E. Ortiz Bruno M. F. da Silva Esteban W. G. Clua Luiz M. G. Gonçalves |
| author_facet | Elizabeth V. Cabrera Luis E. Ortiz Bruno M. F. da Silva Esteban W. G. Clua Luiz M. G. Gonçalves |
| author_sort | Elizabeth V. Cabrera |
| collection | DOAJ |
| description | We propose a versatile method for estimating the RMS error of depth data provided by generic 3D sensors with the capability of generating RGB and depth (D) data of the scene, i.e., the ones based on techniques such as structured light, time of flight and stereo. A common checkerboard is used, the corners are detected and two point clouds are created, one with the real coordinates of the pattern corners and one with the corner coordinates given by the device. After a registration of these two clouds, the RMS error is computed. Then, using curve fittings methods, an equation is obtained that generalizes the RMS error as a function of the distance between the sensor and the checkerboard pattern. The depth errors estimated by our method are compared to those estimated by state-of-the-art approaches, validating its accuracy and utility. This method can be used to rapidly estimate the quality of RGB-D sensors, facilitating robotics applications as SLAM and object recognition. |
| first_indexed | 2024-04-11T21:39:50Z |
| format | Article |
| id | doaj.art-ef3b9f8276854cf1b8441732ffcc44a3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:39:50Z |
| publishDate | 2018-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ef3b9f8276854cf1b8441732ffcc44a32022-12-22T04:01:37ZengMDPI AGSensors1424-82202018-09-01189312210.3390/s18093122s18093122A Versatile Method for Depth Data Error Estimation in RGB-D SensorsElizabeth V. Cabrera0Luis E. Ortiz1Bruno M. F. da Silva2Esteban W. G. Clua3Luiz M. G. Gonçalves4Natalnet Associate Laboratories, Federal University of Rio Grande do Norte, Campus Universitário, Natal RN 59.078-970, BrazilNatalnet Associate Laboratories, Federal University of Rio Grande do Norte, Campus Universitário, Natal RN 59.078-970, BrazilNatalnet Associate Laboratories, Federal University of Rio Grande do Norte, Campus Universitário, Natal RN 59.078-970, BrazilInstitute of Computing, Fluminense Federal University, Campus Praia Vermelha, Niteroi RJ 24.310-346, BrazilNatalnet Associate Laboratories, Federal University of Rio Grande do Norte, Campus Universitário, Natal RN 59.078-970, BrazilWe propose a versatile method for estimating the RMS error of depth data provided by generic 3D sensors with the capability of generating RGB and depth (D) data of the scene, i.e., the ones based on techniques such as structured light, time of flight and stereo. A common checkerboard is used, the corners are detected and two point clouds are created, one with the real coordinates of the pattern corners and one with the corner coordinates given by the device. After a registration of these two clouds, the RMS error is computed. Then, using curve fittings methods, an equation is obtained that generalizes the RMS error as a function of the distance between the sensor and the checkerboard pattern. The depth errors estimated by our method are compared to those estimated by state-of-the-art approaches, validating its accuracy and utility. This method can be used to rapidly estimate the quality of RGB-D sensors, facilitating robotics applications as SLAM and object recognition.http://www.mdpi.com/1424-8220/18/9/3122RGB-D sensorsaccuracyRMS error |
| spellingShingle | Elizabeth V. Cabrera Luis E. Ortiz Bruno M. F. da Silva Esteban W. G. Clua Luiz M. G. Gonçalves A Versatile Method for Depth Data Error Estimation in RGB-D Sensors Sensors RGB-D sensors accuracy RMS error |
| title | A Versatile Method for Depth Data Error Estimation in RGB-D Sensors |
| title_full | A Versatile Method for Depth Data Error Estimation in RGB-D Sensors |
| title_fullStr | A Versatile Method for Depth Data Error Estimation in RGB-D Sensors |
| title_full_unstemmed | A Versatile Method for Depth Data Error Estimation in RGB-D Sensors |
| title_short | A Versatile Method for Depth Data Error Estimation in RGB-D Sensors |
| title_sort | versatile method for depth data error estimation in rgb d sensors |
| topic | RGB-D sensors accuracy RMS error |
| url | http://www.mdpi.com/1424-8220/18/9/3122 |
| work_keys_str_mv | AT elizabethvcabrera aversatilemethodfordepthdataerrorestimationinrgbdsensors AT luiseortiz aversatilemethodfordepthdataerrorestimationinrgbdsensors AT brunomfdasilva aversatilemethodfordepthdataerrorestimationinrgbdsensors AT estebanwgclua aversatilemethodfordepthdataerrorestimationinrgbdsensors AT luizmggoncalves aversatilemethodfordepthdataerrorestimationinrgbdsensors AT elizabethvcabrera versatilemethodfordepthdataerrorestimationinrgbdsensors AT luiseortiz versatilemethodfordepthdataerrorestimationinrgbdsensors AT brunomfdasilva versatilemethodfordepthdataerrorestimationinrgbdsensors AT estebanwgclua versatilemethodfordepthdataerrorestimationinrgbdsensors AT luizmggoncalves versatilemethodfordepthdataerrorestimationinrgbdsensors |