A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes
In various dynamic scenes, there are moveable objects such as pedestrians, which may challenge simultaneous localization and mapping (SLAM) algorithms. Consequently, the localization accuracy may be degraded, and a moving object may negatively impact the constructed maps. Maps that contain semantic...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/11/1363 |
id |
doaj-742d115865324511877b6e8867d7ce09 |
---|---|
record_format |
Article |
spelling |
doaj-742d115865324511877b6e8867d7ce092020-11-25T00:25:58ZengMDPI AGRemote Sensing2072-42922019-06-011111136310.3390/rs11111363rs11111363A Computationally Efficient Semantic SLAM Solution for Dynamic ScenesZemin Wang0Qian Zhang1Jiansheng Li2Shuming Zhang3Jingbin Liu4State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Economics and Management, Hubei University of Technology, Wuhan 430079, ChinaInstitute of Surveying and Mapping, Information Engineering University, Zhengzhou 450000, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaIn various dynamic scenes, there are moveable objects such as pedestrians, which may challenge simultaneous localization and mapping (SLAM) algorithms. Consequently, the localization accuracy may be degraded, and a moving object may negatively impact the constructed maps. Maps that contain semantic information of dynamic objects impart humans or robots with the ability to semantically understand the environment, and they are critical for various intelligent systems and location-based services. In this study, we developed a computationally efficient SLAM solution that is able to accomplish three tasks in real time: (1) complete localization without accuracy loss due to the existence of dynamic objects and generate a static map that does not contain moving objects, (2) extract semantic information of dynamic objects through a computionally efficient approach, and (3) eventually generate semantic maps, which overlay semantic objects on static maps. The proposed semantic SLAM solution was evaluated through four different experiments on two data sets, respectively verifying the tracking accuracy, computational efficiency, and the quality of the generated static maps and semantic maps. The results show that the proposed SLAM solution is computationally efficient by reducing the time consumption for building maps by 2/3; moreover, the relative localization accuracy is improved, with a translational error of only 0.028 m, and is not degraded by dynamic objects. Finally, the proposed solution generates static maps of a dynamic scene without moving objects and semantic maps with high-precision semantic information of specific objects.https://www.mdpi.com/2072-4292/11/11/1363visual SLAMindoor positioning3D reconstructionsemantic mapmulti-sensor integrated positioning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zemin Wang Qian Zhang Jiansheng Li Shuming Zhang Jingbin Liu |
spellingShingle |
Zemin Wang Qian Zhang Jiansheng Li Shuming Zhang Jingbin Liu A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes Remote Sensing visual SLAM indoor positioning 3D reconstruction semantic map multi-sensor integrated positioning |
author_facet |
Zemin Wang Qian Zhang Jiansheng Li Shuming Zhang Jingbin Liu |
author_sort |
Zemin Wang |
title |
A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes |
title_short |
A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes |
title_full |
A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes |
title_fullStr |
A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes |
title_full_unstemmed |
A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes |
title_sort |
computationally efficient semantic slam solution for dynamic scenes |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-06-01 |
description |
In various dynamic scenes, there are moveable objects such as pedestrians, which may challenge simultaneous localization and mapping (SLAM) algorithms. Consequently, the localization accuracy may be degraded, and a moving object may negatively impact the constructed maps. Maps that contain semantic information of dynamic objects impart humans or robots with the ability to semantically understand the environment, and they are critical for various intelligent systems and location-based services. In this study, we developed a computationally efficient SLAM solution that is able to accomplish three tasks in real time: (1) complete localization without accuracy loss due to the existence of dynamic objects and generate a static map that does not contain moving objects, (2) extract semantic information of dynamic objects through a computionally efficient approach, and (3) eventually generate semantic maps, which overlay semantic objects on static maps. The proposed semantic SLAM solution was evaluated through four different experiments on two data sets, respectively verifying the tracking accuracy, computational efficiency, and the quality of the generated static maps and semantic maps. The results show that the proposed SLAM solution is computationally efficient by reducing the time consumption for building maps by 2/3; moreover, the relative localization accuracy is improved, with a translational error of only 0.028 m, and is not degraded by dynamic objects. Finally, the proposed solution generates static maps of a dynamic scene without moving objects and semantic maps with high-precision semantic information of specific objects. |
topic |
visual SLAM indoor positioning 3D reconstruction semantic map multi-sensor integrated positioning |
url |
https://www.mdpi.com/2072-4292/11/11/1363 |
work_keys_str_mv |
AT zeminwang acomputationallyefficientsemanticslamsolutionfordynamicscenes AT qianzhang acomputationallyefficientsemanticslamsolutionfordynamicscenes AT jianshengli acomputationallyefficientsemanticslamsolutionfordynamicscenes AT shumingzhang acomputationallyefficientsemanticslamsolutionfordynamicscenes AT jingbinliu acomputationallyefficientsemanticslamsolutionfordynamicscenes AT zeminwang computationallyefficientsemanticslamsolutionfordynamicscenes AT qianzhang computationallyefficientsemanticslamsolutionfordynamicscenes AT jianshengli computationallyefficientsemanticslamsolutionfordynamicscenes AT shumingzhang computationallyefficientsemanticslamsolutionfordynamicscenes AT jingbinliu computationallyefficientsemanticslamsolutionfordynamicscenes |
_version_ |
1725346775748837376 |