DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment

2021-01-01
Hastürk, Özgür
Erkmen, Aydan Müşerref
Simultaneous localization and mapping (SLAM) problem has been extensively studied by researchers in the field of robotics, however, conventional approaches in mapping assume a static environment. The static assumption is valid only in a small region, and it limits the application of visual SLAM in dynamic environments. The recently proposed state-of-the-art SLAM solutions for dynamic environments use different semantic segmentation methods such as mask R-CNN and SegNet; however, these frameworks are based on a sparse mapping framework (ORBSLAM). In addition, segmentation process increases the computational power, which makes these SLAM algorithms unsuitable for real-time mapping. Therefore, there is no effective dense RGB-D SLAM method for real-world unstructured and dynamic environments. In this study, we propose a novel real-time dense SLAM method for dynamic environments, where 3D reconstruction error is manipulated for identification of static and dynamic classes having generalized Gaussian distribution. Our proposed approach requires neither explicit object tracking nor object classifier, which makes it robust to any type of moving object and suitable for real-time mapping. Our method eliminates the repeated views and uses consistent data that enhance the performance of volumetric fusion. For completeness, we compare our proposed method using different types of high dynamic dataset, which are publicly available, to demonstrate the versatility and robustness of our approach. Experiments show that its tracking performance is better than other dense and dynamic SLAM approaches.
International Journal of Advanced Robotic Systems

Suggestions

Real time dense SLAM in unstructured dynamic cluttered 3D environments
Hastürk, Özgür; Erkmen, Aydan Müşerref; Department of Electrical and Electronics Engineering (2022-2-3)
SLAM problem has been extensively studied by researchers in the field of robotics , however, conventional approaches in mapping assume a static environment. The static assumption is valid only in a small region, it limits the application of visual SLAM in dynamic environments. Recently proposed state of art SLAM solutions for dynamic environment use different semantic segmentation methods such as Mask RCNN and SegNet; however, these frameworks are based on a sparse mapping framework (ORBSLAM) Our proposed a...
Conditional Random Fields for Land Use/Land Cover Classification and Complex Region Detection
Can, Gulcan; Firat, Orhan; Yarman Vural, Fatoş Tunay (2012-11-09)
Developing a complex region detection algorithm that is aware of its contextual relations with several classes necessitates statistical frameworks that can encode contextual relations rather than simple rule-based applications or heuristics. In this study, we present a conditional random field (CRF) model that is generated over the results of a robust local discriminative classifier in order to reveal contextual relations of complex objects and land use/land cover (LULC) classes. The proposed CRF model enco...
Performance Evaluation of the Grid-based FastSLAM in V-RFP Using MATLAB
Azak, Salim (2018-02-24)
This paper presents a Simultaneous Localization and Mapping (SLAM) application that is developed in V-REP robot simulation program by using Grid-Based FastSLAM method. In this work, the SLAM problem in an unknown indoor environment is solved with the Pioneer 3 DX mobile robot equipped with a laser range finder. Control scripts are developed in the Lua and FastSLAM scripts using MATLAB that is linked to the simulation platform by means of the Remote API feature of the V-REP. In order to evaluate of the perfo...
Power-Law Distribution of Long-Term Experimental Data in Swarm Robotics
Arvin, Farshad; Attar, Abdolrahman; Turgut, Ali Emre; Yue, Shigang (2015-06-02)
Bio-inspired aggregation is one of the most fundamental behaviours that has been studied in swarm robotic for more than two decades. Biology revealed that the environmental characteristics are very important factors in aggregation of social insects and other animals. In this paper, we study the effects of different environmental factors such as size and texture of aggregation cues using real robots. In addition, we propose a mathematical model to predict the behaviour of the aggregation during an experiment.
Immersive design environments for performative architectural design: a BIM-based approach.
Akın, Şahin; Gürsel Dino, İpek; Department of Architecture (2020)
In architectural design processes, the use of shared, simulated, and synchronized virtual environments and computational methods becomes widespread. Virtual reality immerses users in a three-dimensional digital environment and has the potential to make them involve actively in the act of design. Daylighting is an essential concept in architectural design, but its assessment and integration to the design process can be complicated. The use of Building Information Modelling (BIM) tools is identified as a crit...
Citation Formats
Ö. Hastürk and A. M. Erkmen, “DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment,” International Journal of Advanced Robotic Systems, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85107562788&origin=inward.