Real time dense SLAM in unstructured dynamic cluttered 3D environments

Download

index.pdf

Date

2022-2-3

Author

Hastürk, Özgür

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

397
views

485
downloads

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 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 type of high dynamic dataset, which are publicly available, in order to demonstrate the versatility and robustness of our approach. Experiments shows that its tracking performance better than other dense and dynamic SLAM approaches.

Subject Keywords

Dynamic mapping, Visual SLAM, Localization, 3D reconstruction

URI

https://hdl.handle.net/11511/96323

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment Hastürk, Özgür; Erkmen, Aydan Müşerref (2021-01-01) 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 o...
Collaborative building control: a conceptual mixed-initiative framework Topak, Fatih; Pekeriçli, Mehmet Koray (Taylor & Francis, 2021-6-22) In the last two decades, automation systems have shown advanced developments and are widely adopted for various purposes in many fields. However, automation in buildings has not gained popularity and has a low acceptance level amongst the occupants. Decreased perceived control, ever-changing dynamic human needs, and standardized, one-size-fits-all approach in current automation systems lead to disharmony in human-machine coexistence. Although well-established continuous interaction between building control ...
Prediction of Nonlinear Drift Demands for Buildings with Recurrent Neural Networks Kocamaz, Korhan; Binici, Barış; Tuncay, Kağan (2021-09-08) Application of deep learning algorithms to the problems of structural engineering is an emerging research field. Inthis study, a deep learning algorithm, namely recurrent neural network (RNN), is applied to tackle a problemrelated to the assessment of reinforced concrete buildings. Inter-storey drift ratio profile of a structure is a quiteimportant parameter while conducting assessment procedures. In general, procedures require a series of timeconsuming nonlinear dynamic analysis. In this study, an extensiv...
Visual Object Tracking with Autoencoder Representations Besbinar, Beril; Alatan, Abdullah Aydın (2016-05-19) Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have recently improved the state of the art in many areas as a virtue of large labeled datasets, increase in the computational power of current hardware and unsupervised training methods. Although such a dataset may not be available for lots of application areas, the representations obtained by the well-designed networks that have a large representation capacity and trained with enough dat...
Vibration fatigue analysis of structures under broadband excitation Koçer, Bilge; Dağ, Serkan; Department of Mechanical Engineering (2010) The behavior of structures is totally different when they are exposed to fluctuating loading rather than static one which is a well known phenomenon in engineering called fatigue. When the loading is not static but dynamic, the dynamics of the structure should be taken into account since there is a high possibility to excite the resonance frequencies of the structure especially if the loading frequency has a wide bandwidth. In these cases, the structure’s response to the loading will not be linear. Therefor...

Citation Formats

Ö. Hastürk, “Real time dense SLAM in unstructured dynamic cluttered 3D environments,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.