Abstract
Recent advancements in deep learning require a large amount of the annotated training data containing various terms and conditions of the environment. Thus, developing and testing algorithms for the navigation of mobile robots can be expensive and time-consuming. Motivated by the aforementioned problems, this article presents a photorealistic simulator for the computer vision community working with omnidirectional vision systems. Built using unity, the simulator integrates sensors, mobile robots, and elements of the indoor environment and allows one to generate synthetic photorealistic data sets with automatic ground truth annotations. With the aid of the proposed simulator, two practical applications are studied, namely extrinsic calibration of the vision system and three-dimensional reconstruction of the indoor environment. For the proposed calibration and reconstruction techniques, the processes themselves are simple, robust, and accurate. Proposed methods are evaluated experimentally with data generated by the simulator. The proposed simulator and supporting materials are available online: http://www.ilabit.org .
Highlights
The indoor reconstruction is a crucial technique in computer vision (CV), contributing to various applications such as virtual and augmented reality,[1,2] layout recovery,[3,4] and mobile navigation.[5,6,7]
Maximum absolute error (AE) presented in Table 2 relates to the index of the particular experiment, which is presented in brackets
It is worthwhile mentioning that the reconstruction method proposed in the article allows one to obtain the 3D model of the indoor scene within the visible region of the laser beam associated with the walls in the fisheye image
Summary
The indoor reconstruction is a crucial technique in computer vision (CV), contributing to various applications such as virtual and augmented reality,[1,2] layout recovery,[3,4] and mobile navigation.[5,6,7] Perception and sensing become an important part of the reconstruction of unknown environments. Reconstruction methods can be based on passive or active sensing techniques; each method has its own relative merits. Passive vision systems do not rely on energy being emitted into the scene.[8,9,10,11,12,13] This type of sensing technique operates similar to human vision and the hardware. They do, suffer from particular difficulties, such as point extraction in nontextured environments, correspondence problem, low accuracy, and speed.[14] the reconstruction of indoor environments with simple corridors can be time-consuming and not as accurate as expected
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
