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

2021-01-01
Hastürk, Özgür
Erkmen, Aydan Müşerref
Show full item record
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
255
views
139
downloads
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.
3D reconstruction, Dynamic mapping, localization, visual SLAM
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85107562788&origin=inward
https://hdl.handle.net/11511/91103
International Journal of Advanced Robotic Systems
Department of Electrical and Electronics Engineering, Article

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...
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...
GMDH: An R Package for Short Term Forecasting via GMDH-Type Neural Network Algorithms
DAĞ, OSMAN; Yozgatlıgil, Ceylan (2016-08-01)
Group Method of Data Handling (GMDH)-type neural network algorithms are the heuristic self organization method for the modelling of complex systems. GMDH algorithms are utilized for a variety of purposes, examples include identification of physical laws, the extrapolation of physical fields, pattern recognition, clustering, the approximation of multidimensional processes, forecasting without models, etc. In this study, the R package GMDH is presented to make short term forecasting through GMDH-type neural n...
GMDH-type neural network algorithms for short term forecasting
Dağ, Osman; Yozgatlıgil, Ceylan; Department of Statistics (2015)
Group Method of Data Handling (GMDH) - type neural network algorithms are the heuristic self-organization method for modelling the complex systems. GMDH algorithms are utilized for the variety of purposes, which are identification of physical laws, extrapolation of physical fields, pattern recognition, clustering, approximation of multidimensional processes, forecasting without models and so on. In this study, GMDH - type neural network algorithms were applied to make forecasts for time series data sets. We...
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.
METU IIS - Integrated Information Service open@metu.edu.tr