OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments
With the rapid development of autonomous driving and robotics applications in recent years, visual Simultaneous Localization and Mapping (SLAM) has become a hot research topic. The majority of visual SLAM systems relies on the assumption of scene rigidity, which may not always hold true in real appl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/18/7921 |
| _version_ | 1797576993501347840 |
|---|---|
| author | Yimeng Chang Jun Hu Shiyou Xu |
| author_facet | Yimeng Chang Jun Hu Shiyou Xu |
| author_sort | Yimeng Chang |
| collection | DOAJ |
| description | With the rapid development of autonomous driving and robotics applications in recent years, visual Simultaneous Localization and Mapping (SLAM) has become a hot research topic. The majority of visual SLAM systems relies on the assumption of scene rigidity, which may not always hold true in real applications. In dynamic environments, SLAM systems, without accounting for dynamic objects, will easily fail to estimate the camera pose. Some existing methods attempt to address this issue by simply excluding the dynamic features lying in moving objects. But this may lead to a shortage of features for tracking. To tackle this problem, we propose OTE-SLAM, an object tracking enhanced visual SLAM system, which not only tracks the camera motion, but also tracks the movement of dynamic objects. Furthermore, we perform joint optimization of both the camera pose and object 3D position, enabling a mutual benefit between visual SLAM and object tracking. The results of experiences demonstrate that the proposed approach improves the accuracy of the SLAM system in challenging dynamic environments. The improvements include a maximum reduction in both absolute trajectory error and relative trajectory error by 22% and 33%, respectively. |
| first_indexed | 2024-03-10T22:01:38Z |
| format | Article |
| id | doaj.art-a6a40ec0ed8f492ead5f6238d1562b87 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T22:01:38Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a6a40ec0ed8f492ead5f6238d1562b872023-11-19T12:56:06ZengMDPI AGSensors1424-82202023-09-012318792110.3390/s23187921OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic EnvironmentsYimeng Chang0Jun Hu1Shiyou Xu2School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen 518107, ChinaSchool of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen 518107, ChinaSchool of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen 518107, ChinaWith the rapid development of autonomous driving and robotics applications in recent years, visual Simultaneous Localization and Mapping (SLAM) has become a hot research topic. The majority of visual SLAM systems relies on the assumption of scene rigidity, which may not always hold true in real applications. In dynamic environments, SLAM systems, without accounting for dynamic objects, will easily fail to estimate the camera pose. Some existing methods attempt to address this issue by simply excluding the dynamic features lying in moving objects. But this may lead to a shortage of features for tracking. To tackle this problem, we propose OTE-SLAM, an object tracking enhanced visual SLAM system, which not only tracks the camera motion, but also tracks the movement of dynamic objects. Furthermore, we perform joint optimization of both the camera pose and object 3D position, enabling a mutual benefit between visual SLAM and object tracking. The results of experiences demonstrate that the proposed approach improves the accuracy of the SLAM system in challenging dynamic environments. The improvements include a maximum reduction in both absolute trajectory error and relative trajectory error by 22% and 33%, respectively.https://www.mdpi.com/1424-8220/23/18/7921visual SLAMobject trackingdynamic environments |
| spellingShingle | Yimeng Chang Jun Hu Shiyou Xu OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments Sensors visual SLAM object tracking dynamic environments |
| title | OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments |
| title_full | OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments |
| title_fullStr | OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments |
| title_full_unstemmed | OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments |
| title_short | OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments |
| title_sort | ote slam an object tracking enhanced visual slam system for dynamic environments |
| topic | visual SLAM object tracking dynamic environments |
| url | https://www.mdpi.com/1424-8220/23/18/7921 |
| work_keys_str_mv | AT yimengchang oteslamanobjecttrackingenhancedvisualslamsystemfordynamicenvironments AT junhu oteslamanobjecttrackingenhancedvisualslamsystemfordynamicenvironments AT shiyouxu oteslamanobjecttrackingenhancedvisualslamsystemfordynamicenvironments |