Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera
Mobile robots are of great help for automatic monitoring tasks in different environments. One of the first tasks that needs to be addressed when creating these kinds of robotic systems is modeling the robot environment. This work proposes a pipeline to build an enhanced visual model of a robot envir...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/4/493 |
| _version_ | 1811186432804388864 |
|---|---|
| author | Alejandro Rituerto Henrik Andreasson Ana C. Murillo Achim Lilienthal José Jesús Guerrero |
| author_facet | Alejandro Rituerto Henrik Andreasson Ana C. Murillo Achim Lilienthal José Jesús Guerrero |
| author_sort | Alejandro Rituerto |
| collection | DOAJ |
| description | Mobile robots are of great help for automatic monitoring tasks in different environments. One of the first tasks that needs to be addressed when creating these kinds of robotic systems is modeling the robot environment. This work proposes a pipeline to build an enhanced visual model of a robot environment indoors. Vision based recognition approaches frequently use quantized feature spaces, commonly known as Bag of Words (BoW) or vocabulary representations. A drawback using standard BoW approaches is that semantic information is not considered as a criteria to create the visual words. To solve this challenging task, this paper studies how to leverage the standard vocabulary construction process to obtain a more meaningful visual vocabulary of the robot work environment using image sequences. We take advantage of spatio-temporal constraints and prior knowledge about the position of the camera. The key contribution of our work is the definition of a new pipeline to create a model of the environment. This pipeline incorporates (1) tracking information to the process of vocabulary construction and (2) geometric cues to the appearance descriptors. Motivated by long term robotic applications, such as the aforementioned monitoring tasks, we focus on a configuration where the robot camera points to the ceiling, which captures more stable regions of the environment. The experimental validation shows how our vocabulary models the environment in more detail than standard vocabulary approaches, without loss of recognition performance. We show different robotic tasks that could benefit of the use of our visual vocabulary approach, such as place recognition or object discovery. For this validation, we use our publicly available data-set. |
| first_indexed | 2024-04-11T13:46:22Z |
| format | Article |
| id | doaj.art-98d5742e769b4c5ca571f6e4042b2ee4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:46:22Z |
| publishDate | 2016-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-98d5742e769b4c5ca571f6e4042b2ee42022-12-22T04:21:05ZengMDPI AGSensors1424-82202016-04-0116449310.3390/s16040493s16040493Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing CameraAlejandro Rituerto0Henrik Andreasson1Ana C. Murillo2Achim Lilienthal3José Jesús Guerrero4Instituto de Investigación en Ingeniería de Aragón, Deptartmento de Informática e Ingeniería de Sistemas, University of Zaragoza, Zaragoza 50018, SpainCentre for Applied Autonomous Sensor Systems, Deptartment of Technology, Örebro University, Örebro SE-70182, SwedenInstituto de Investigación en Ingeniería de Aragón, Deptartmento de Informática e Ingeniería de Sistemas, University of Zaragoza, Zaragoza 50018, SpainCentre for Applied Autonomous Sensor Systems, Deptartment of Technology, Örebro University, Örebro SE-70182, SwedenInstituto de Investigación en Ingeniería de Aragón, Deptartmento de Informática e Ingeniería de Sistemas, University of Zaragoza, Zaragoza 50018, SpainMobile robots are of great help for automatic monitoring tasks in different environments. One of the first tasks that needs to be addressed when creating these kinds of robotic systems is modeling the robot environment. This work proposes a pipeline to build an enhanced visual model of a robot environment indoors. Vision based recognition approaches frequently use quantized feature spaces, commonly known as Bag of Words (BoW) or vocabulary representations. A drawback using standard BoW approaches is that semantic information is not considered as a criteria to create the visual words. To solve this challenging task, this paper studies how to leverage the standard vocabulary construction process to obtain a more meaningful visual vocabulary of the robot work environment using image sequences. We take advantage of spatio-temporal constraints and prior knowledge about the position of the camera. The key contribution of our work is the definition of a new pipeline to create a model of the environment. This pipeline incorporates (1) tracking information to the process of vocabulary construction and (2) geometric cues to the appearance descriptors. Motivated by long term robotic applications, such as the aforementioned monitoring tasks, we focus on a configuration where the robot camera points to the ceiling, which captures more stable regions of the environment. The experimental validation shows how our vocabulary models the environment in more detail than standard vocabulary approaches, without loss of recognition performance. We show different robotic tasks that could benefit of the use of our visual vocabulary approach, such as place recognition or object discovery. For this validation, we use our publicly available data-set.http://www.mdpi.com/1424-8220/16/4/493visual vocabularycomputer visionbag of wordsroboticsplace recognitionenvironment description |
| spellingShingle | Alejandro Rituerto Henrik Andreasson Ana C. Murillo Achim Lilienthal José Jesús Guerrero Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera Sensors visual vocabulary computer vision bag of words robotics place recognition environment description |
| title | Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera |
| title_full | Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera |
| title_fullStr | Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera |
| title_full_unstemmed | Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera |
| title_short | Building an Enhanced Vocabulary of the Robot Environment with a Ceiling Pointing Camera |
| title_sort | building an enhanced vocabulary of the robot environment with a ceiling pointing camera |
| topic | visual vocabulary computer vision bag of words robotics place recognition environment description |
| url | http://www.mdpi.com/1424-8220/16/4/493 |
| work_keys_str_mv | AT alejandrorituerto buildinganenhancedvocabularyoftherobotenvironmentwithaceilingpointingcamera AT henrikandreasson buildinganenhancedvocabularyoftherobotenvironmentwithaceilingpointingcamera AT anacmurillo buildinganenhancedvocabularyoftherobotenvironmentwithaceilingpointingcamera AT achimlilienthal buildinganenhancedvocabularyoftherobotenvironmentwithaceilingpointingcamera AT josejesusguerrero buildinganenhancedvocabularyoftherobotenvironmentwithaceilingpointingcamera |