KEYWORDS: Superposition, Multidimensional signal processing, Televisions, Algorithm development, Video surveillance, Cameras, Distortion, Image resolution, Detection and tracking algorithms, Video
We describe the algorithm of multidimensional signals superposition for improving quality images of a multicamera video surveillance system. The quality of images is defined by the resolution of a video surveillance system. The multicamera video system includes the camera with low resolution for surveying in all fields of view and includes the camera with high resolution for recognizing small objects in a video frame. The possibility of switching between the cameras can be provided by the homography superposition of multidimensional television signals. The developed algorithm of the homography superposition includes two stages of processing. The first stage is rough superposition by the feature points. The second stage is accurate superposition by the modified Lucas-Kanade algorithm. The feature of the first stage is longtime of processing. The reason for this is the huge amount of possible variants of superposition. The reduction of processing time is provided by a procedure of removing wrong variants of matching points. The developed algorithm has been tested on real multidimensional television signals and the result of superposition was satisfactory.
A multidimensional signal superposition is an important task in the television system. Such processing is applied for decreasing information storage improving the quality of television images and for solving intelligence tasks such as recognition and tracking by interest objects. The algorithm about homography parameters estimation for superposition multidimensional signals was shown in the current article. The algorithm includes several stages of processing. They are reference point recognition, automatic matching between datasets, calculation of the homography parameters. The matching between datasets bases on a method for compare images of the log-polar coordinate system. This method is invariant of the scale and rotation. Also, the research shows that the probability of points matching is characterized high value of the wrong decision if only one wrong reference point is used for analysis. To fix these disadvantages the decision method was developed. It bases by analyze the several reference algorithm that is approbation by real images. The superposition of multidimensional television signals is a pleasing solution by developing approaches.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.