Improved Visual SLAM Algorithm Based on Dynamic Scenes
This work presents a novel RGB-D dynamic simultaneous localization and mapping (SLAM) method that improves accuracy, stability, and efficiency of localization while relying on deep learning in a dynamic environment, in contrast to traditional static scene-based visual SLAM methods. Based on the clas...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/22/10727 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267345130356736 |
|---|---|
| author | Jinxing Niu Ziqi Chen Tao Zhang Shiyu Zheng |
| author_facet | Jinxing Niu Ziqi Chen Tao Zhang Shiyu Zheng |
| author_sort | Jinxing Niu |
| collection | DOAJ |
| description | This work presents a novel RGB-D dynamic simultaneous localization and mapping (SLAM) method that improves accuracy, stability, and efficiency of localization while relying on deep learning in a dynamic environment, in contrast to traditional static scene-based visual SLAM methods. Based on the classic framework of traditional visual SLAM, we propose a method that replaces the traditional feature extraction method with a convolutional neural network approach, aiming to enhance the accuracy of feature extraction and localization, as well as to improve the algorithm’s ability to capture and represent the characteristics of the entire scene. Subsequently, the semantic segmentation thread was utilized in a target detection network combined with geometric methods to identify potential dynamic areas in the image and generate masks for dynamic objects. Finally, the standard deviation of the depth information of potential dynamic points was calculated to identify true dynamic feature points, to guarantee that static feature points were used for position estimation. We performed experiments based on the public datasets to validate the feasibility of the proposed algorithm. The experimental results indicate that the improved SLAM algorithm, which boasts a reduction in absolute trajectory error (ATE) by approximately 97% compared to traditional static visual SLAM and about 20% compared to traditional dynamic visual SLAM, also exhibited a 68% decrease in computation time compared to well-known dynamic visual SLAM, thereby possessing absolute advantages in both positioning accuracy and operational efficiency. |
| format | Article |
| id | doaj-art-663c05a8aa94404c8a89eb15e18544e0 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-663c05a8aa94404c8a89eb15e18544e02025-08-20T01:53:49ZengMDPI AGApplied Sciences2076-34172024-11-0114221072710.3390/app142210727Improved Visual SLAM Algorithm Based on Dynamic ScenesJinxing Niu0Ziqi Chen1Tao Zhang2Shiyu Zheng3School of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaThis work presents a novel RGB-D dynamic simultaneous localization and mapping (SLAM) method that improves accuracy, stability, and efficiency of localization while relying on deep learning in a dynamic environment, in contrast to traditional static scene-based visual SLAM methods. Based on the classic framework of traditional visual SLAM, we propose a method that replaces the traditional feature extraction method with a convolutional neural network approach, aiming to enhance the accuracy of feature extraction and localization, as well as to improve the algorithm’s ability to capture and represent the characteristics of the entire scene. Subsequently, the semantic segmentation thread was utilized in a target detection network combined with geometric methods to identify potential dynamic areas in the image and generate masks for dynamic objects. Finally, the standard deviation of the depth information of potential dynamic points was calculated to identify true dynamic feature points, to guarantee that static feature points were used for position estimation. We performed experiments based on the public datasets to validate the feasibility of the proposed algorithm. The experimental results indicate that the improved SLAM algorithm, which boasts a reduction in absolute trajectory error (ATE) by approximately 97% compared to traditional static visual SLAM and about 20% compared to traditional dynamic visual SLAM, also exhibited a 68% decrease in computation time compared to well-known dynamic visual SLAM, thereby possessing absolute advantages in both positioning accuracy and operational efficiency.https://www.mdpi.com/2076-3417/14/22/10727visual SLAMdynamic environmentfeature extractionobject detection |
| spellingShingle | Jinxing Niu Ziqi Chen Tao Zhang Shiyu Zheng Improved Visual SLAM Algorithm Based on Dynamic Scenes Applied Sciences visual SLAM dynamic environment feature extraction object detection |
| title | Improved Visual SLAM Algorithm Based on Dynamic Scenes |
| title_full | Improved Visual SLAM Algorithm Based on Dynamic Scenes |
| title_fullStr | Improved Visual SLAM Algorithm Based on Dynamic Scenes |
| title_full_unstemmed | Improved Visual SLAM Algorithm Based on Dynamic Scenes |
| title_short | Improved Visual SLAM Algorithm Based on Dynamic Scenes |
| title_sort | improved visual slam algorithm based on dynamic scenes |
| topic | visual SLAM dynamic environment feature extraction object detection |
| url | https://www.mdpi.com/2076-3417/14/22/10727 |
| work_keys_str_mv | AT jinxingniu improvedvisualslamalgorithmbasedondynamicscenes AT ziqichen improvedvisualslamalgorithmbasedondynamicscenes AT taozhang improvedvisualslamalgorithmbasedondynamicscenes AT shiyuzheng improvedvisualslamalgorithmbasedondynamicscenes |