DYNAMIC KEYPOINT-BASED ALGORITHM OF OBJECT TRACKING

A. I. Morgacheva, V. A. Kulikov, V. P. Kosykh

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаярецензирование

Аннотация

The model of the observed object plays the key role in the task of object tracking. Models as a set of image parts, in particular, keypoints, is more resistant to the changes in shape, texture, angle of view, because local changes apply only to specific parts of the object. On the other hand, any model requires updating as the appearance of the object changes with respect to the camera. In this paper, we propose a dynamic (time-varying) model, based on a set of keypoints. To update the data this model uses the algorithm of rating keypoints and the decision rule, based on a Function of Rival Similarity (FRiS). As a result, at the test set of image sequences the improvement was achieved on average by 9.3% compared to the original algorithm. On some sequences, the improvement was 16% compared to the original algorithm.

Язык оригиналаанглийский
Название основной публикацииINTERNATIONAL WORKSHOP PHOTOGRAMMETRIC AND COMPUTER VISION TECHNIQUES FOR VIDEO SURVEILLANCE, BIOMETRICS AND BIOMEDICINE
РедакторыS Zheltov, Y Vizilter, Knyaz
ИздательCopernicus Gesellschaft mbH
Страницы79-82
Число страниц4
DOI
СостояниеОпубликовано - мая 2017
СобытиеInternational Workshop on Photogrammetric and Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine - Moscow
Продолжительность: 15 мая 201717 мая 2017

Серия публикаций

НазваниеInternational Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences
ИздательCOPERNICUS GESELLSCHAFT MBH
Том42-2
ISSN (печатное издание)2194-9034

Конференция

КонференцияInternational Workshop on Photogrammetric and Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine
ГородMoscow
Период15.05.201717.05.2017

Цитировать