RGB-D Segmentation Applications in 3D Reconstruction Problem Based on Depth Map Data

Student: Bobrov Roman

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Final Grade: 7

Year of Graduation: 2017

RGB-D segmentation often serves as an auxiliary tool in object recognition, detection and tracking, classification, and other relevant problems. Depending on the problem, you may need to distinguish, for example, a flat surface on the image to evaluate room geometry, to determine the location of the “background” in the frame and the to extract one person from the crowd. Finally, in most cases, the use of segmentation reduces the dimensionality of the data to supply input to other algorithms. This paper discusses the algorithms of image segmentation and applies some heuristics to improve the quality of the resulting image partitions. Comparative analysis of algorithms in terms of segmentation quality and speed is given.

Full text (added May 28, 2017)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses