Robust SLAM Algorithm in Dynamic Environment Using Optical Flow

Author(s):  
Yiying Ma ◽  
Yingmin Jia
2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Xiong Zhao ◽  
Tao Zuo ◽  
Xinyu Hu

Most of the current visual Simultaneous Localization and Mapping (SLAM) algorithms are designed based on the assumption of a static environment, and their robustness and accuracy in the dynamic environment do not behave well. The reason is that moving objects in the scene will cause the mismatch of features in the pose estimation process, which further affects its positioning and mapping accuracy. In the meantime, the three-dimensional semantic map plays a key role in mobile robot navigation, path planning, and other tasks. In this paper, we present OFM-SLAM: Optical Flow combining MASK-RCNN SLAM, a novel visual SLAM for semantic mapping in dynamic indoor environments. Firstly, we use the Mask-RCNN network to detect potential moving objects which can generate masks of dynamic objects. Secondly, an optical flow method is adopted to detect dynamic feature points. Then, we combine the optical flow method and the MASK-RCNN for full dynamic points’ culling, and the SLAM system is able to track without these dynamic points. Finally, the semantic labels obtained from MASK-RCNN are mapped to the point cloud for generating a three-dimensional semantic map that only contains the static parts of the scenes and their semantic information. We evaluate our system in public TUM datasets. The results of our experiments demonstrate that our system is more effective in dynamic scenarios, and the OFM-SLAM can estimate the camera pose more accurately and acquire a more precise localization in the high dynamic environment.


2021 ◽  
Vol 12 (1) ◽  
pp. 49
Author(s):  
Abira Kanwal ◽  
Zunaira Anjum ◽  
Wasif Muhammad

A simultaneous localization and mapping (SLAM) algorithm allows a mobile robot or a driverless car to determine its location in an unknown and dynamic environment where it is placed, and simultaneously allows it to build a consistent map of that environment. Driverless cars are becoming an emerging reality from science fiction, but there is still too much required for the development of technological breakthroughs for their control, guidance, safety, and health related issues. One existing problem which is required to be addressed is SLAM of driverless car in GPS denied-areas, i.e., congested urban areas with large buildings where GPS signals are weak as a result of congested infrastructure. Due to poor reception of GPS signals in these areas, there is an immense need to localize and route driverless car using onboard sensory modalities, e.g., LIDAR, RADAR, etc., without being dependent on GPS information for its navigation and control. The driverless car SLAM using LIDAR and RADAR involves costly sensors, which appears to be a limitation of this approach. To overcome these limitations, in this article we propose a visual information-based SLAM (vSLAM) algorithm for GPS-denied areas using a cheap video camera. As a front-end process, features-based monocular visual odometry (VO) on grayscale input image frames is performed. Random Sample Consensus (RANSAC) refinement and global pose estimation is performed as a back-end process. The results obtained from the proposed approach demonstrate 95% accuracy with a maximum mean error of 4.98.


2021 ◽  
Vol 11 (4) ◽  
pp. 1828
Author(s):  
Yakun Wu ◽  
Li Luo ◽  
Shujuan Yin ◽  
Mengqi Yu ◽  
Fei Qiao ◽  
...  

The Simultaneous Localization and Mapping (SLAM) algorithm is a hotspot in robot application research with the ability to help mobile robots solve the most fundamental problems of “localization” and “mapping”. The visual semantic SLAM algorithm fused with semantic information enables robots to understand the surrounding environment better, thus dealing with complexity and variability of real application scenarios. DS-SLAM (Semantic SLAM towards Dynamic Environment), one of the representative works in visual semantic SLAM, enhances the robustness in the dynamic scene through semantic information. However, the introduction of deep learning increases the complexity of the system, which makes it a considerable challenge to achieve the real-time semantic SLAM system on the low-power embedded platform. In this paper, we realized the high energy-efficiency DS-SLAM algorithm on the Field Programmable Gate Array (FPGA) based heterogeneous platform through the optimization co-design of software and hardware with the help of OpenCL (Open Computing Language) development flow. Compared with Intel i7 CPU on the TUM dataset, our accelerator achieves up to 13× frame rate improvement, and up to 18× energy efficiency improvement, without significant loss in accuracy.


2019 ◽  
Vol 52 (15) ◽  
pp. 394-399 ◽  
Author(s):  
Fethi Demim ◽  
Abdelghani Boucheloukh ◽  
Abdelkrim Nemra ◽  
Elhaouari Kobzili ◽  
Mustapha Hamerlain ◽  
...  

2021 ◽  
Author(s):  
Xiaochuang Huo ◽  
Lei Zhang ◽  
Mingce Guo ◽  
Xiangrui Wu

Author(s):  
Fethi Demim ◽  
Abdelkrim Nemra ◽  
Abdelghani Boucheloukh ◽  
Kahina Louadj ◽  
Mustapha Hamerlain ◽  
...  

Robotica ◽  
2021 ◽  
pp. 1-26
Author(s):  
Lhilo Kenye ◽  
Rahul Kala

Summary Most conventional simultaneous localization and mapping (SLAM) approaches assume the working environment to be static. In a highly dynamic environment, this assumption divulges the impediments of a SLAM algorithm that lack modules that distinctively attend to dynamic objects despite the inclusion of optimization techniques. This work exploits such environments and reduces the effects of dynamic objects in a SLAM algorithm by separating features belonging to dynamic objects and static background using a generated binary mask image. While the features belonging to the static region are used for performing SLAM, the features belonging to non-static segments are reused instead of being eliminated. The approach employs deep neural network or DNN-based object detection module to obtain bounding boxes and then generates a lower resolution binary mask image using depth-first search algorithm over the detected semantics, characterizing the segmentation of the foreground from the static background. In addition, the features belonging to dynamic objects are tracked into consecutive frames to obtain better masking consistency. The proposed approach is tested on both publicly available dataset as well as self-collected dataset, which includes both indoor and outdoor environments. The experimental results show that the removal of features belonging to dynamic objects for a SLAM algorithm can significantly improve the overall output in a dynamic scene.


Sign in / Sign up

Export Citation Format

Share Document