Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Image Processing & Communications

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: CAMShift algorithm

Sortuj według:

Ogranicz wyniki do:

The use of image processing methods to improve the detection of user’s hand in vision based games used in neurological rehabilitation

Gospodarek K.

Image Processing & Communications

2017

Vol. 22, no. 2

5--14

Vision based games is a type of software that can become a promising, modern neurorehabilitation tool. This paper presents the possibilities offered for the implementation of this kind of software by the open source vision library. The methods and functions related to the aspect of image processing and analysis are presented in terms of their usefulness In creating programs based on the analysis of the images acquired from the camera. On the basis of the issues contained in the paper, the functionality of the library is presented in terms of the possibilities related primarily to the processing of video sequences, detection, tracking and analysis of the movement of objects. As part of the work, the software that meets the requirements for modern neurorehablitation games has been implemented. Its main part is responsible for the identification of the current position of the user's hand and is based on the image captured from the webcam. Whereas the tasks set for the user used among others supporting visual-motor coordination. The main subject of the research was the analysis of the impact of the applied methods of initial image processing on the correctness of the chosen tracking algorithm. It was proposed and experimentally examined the impact of operations such as morphological transformations or apply an additional mask on a functioning of the CamShift algorithm. And hence on the functioning of the whole game which analyzing the user's hand movement.

A practical eye tracking algorithm

Wang H., Wang Q., Ren M., Yang J.

Image Processing & Communications

2008

Vol. 13, no 1-2

35-45

A practical eye tracking algorithm is proposed in this paper. It tracks human face and eyes simultaneously to realize an integration of direct and indirect eye tracking. On one hand, human face is detected by Adaboost face detector, an eye localization approach is designed to localize the eye windows in the detected face area, for eye tracking, multi-visual features which are represented with statistic histograms are extracted from the eye window, and also be fused in particle filter (PF) tracking framework; On the other hand, CAMShift algorithm is also exploited to track the face area, and the eye detection approach is still used to detect reliable eye windows, so as to correct PF tracker. Experimental results show that the proposed algorithm is good at handling illumination changes, sudden face rotation, camera jitter, and partial occlusion. It also can recover from tracking failures in time, which improves the tracking performance in sustainable and robustness.