Abstract:
The current advancements in the technology of cameras especially the integration of stereo cameras into smart phones has brought ease to the process of reconstructing 3D models from different images, such broad subject could be integrated with many fields like medicine which shows the importance of studying this sub-topic of image processing. Different algorithms and techniques has been studied before for this problem where each technique has pros and cons which makes studying the previous works viable to improve or extend solutions. In this research, a general analysis of using stereo-vision will be discussed alongside with integrating the common reconstruction process with Depth-First-Search algorithm (DFS) in order to segment the object of interest from the background. The main principle of proposed method is built upon is the restriction of the angles used to photograph the object of interest, it will be limited to either 2views denoting Front, and Back views, and 4-views consisting of Front, Back, Right, and Left views where the user has to supply these orthographic views rather than taking pictures of different angles where the program has to correlate between these images to produce a 3D model. The main goal of this paper is to show that limiting the number of input images while locking the views where shots could be taken from allows using a simple algorithm for reconstruction. To make this goal achievable, orthographic views and stereo cameras have been identified as suitable choices to simplify the reconstruction algorithm.
Page(s):
2924-2936
DOI:
DOI not available
Published:
Journal: Journal of Theoretical and Applied Information Technology, Volume: 98, Issue: 15, Year: 2020