An algorithm for estimating the number of objects in a selected area of space based on ordinary photos.

There are many areas of activity where the problem of counting objects in three-dimensional space appears. It is often the case that the primary source of information in such a situation are photos or digital videos. In mathematical language, a two-dimensional photo can somewhat be treated as a projection of a selected space area. The significant issue in such a situation is that the counted objects in the image may overlap many times, which may cause some objects to obscure others. This approach addresses this issue by using appropriate statistical estimations of the amount of obscured objects based on computer image analysis. The proposed algorithm has already been initially used to count the number of birds in digital photos and films. [ABSTRACT FROM AUTHOR]

Copyright of Procedia Computer Science is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)