The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we explore the segmentation performance of four state-of-the-art unsupervised over-segmentation methods by evaluating the quality of over-segments. To achieve this goal, we design a novel real-time evaluating framework, this method is integrating the classical goodness methods and our proposed new discrepancy method based on real-time boundary extraction, which is able to suppress the...
Based on the analysis of Maxwell color triangle, a segmentation algorithm for traffic sign is presented. An characteristic segmentation formula is proposed for the red, yellow and blue traffic signs, and the criteria is presented to confirm the range of threshold group through a number of experiments. Accordingly, the traffic sign is segmented by region growth with maximum and minimum threshold group...
This paper presents a solution of image mosaics for vehicle monitoring system. Image mosaics technology is used to create a wider field of view on the monitor screen. This paper discusses a new image mosaics method which can meet the demands for the application of the vehicle monitoring system. The new method adopts Harris and SIFT algorithms' advantages and improves the processing time.
This paper proposes the method of video image mosaics in real-time based on Scale Invariant Feature Transform (SIFT) algorithm. The real-time processing is great significant for the video image mosaics. SIFT is the efficient method for extracting distinctive invariant features from images. But it costs so much computation time that it can't meet the real-time processing demand. Therefore, an improved...
In this paper, a quasi-automatic video matting approach which can preserve the temporal consistency of the alpha mattes is presented. “Quasi-automatic” means that it only needs a few user interactions on the first frame. A new algorithm which incorporates the Bayesian Estimation, Weighted Kernel Density Estimation (WKDE) and graph cut is presented to automatically and accurately segment each frame...
This paper presents a complete system for electronic panoramic mirror based on image mosaic. In recent years, there has been growing interest in using image mosaic. We propose a system based on image mosaic, which obtains the scenes of all directions at one time compared to the traditional panoramic mirror. The key progress is image registration. The Scale Invariant Feature Transform (SIFT) algorithm...
A novel approach for counting people passing through a region where is surveilled by a parallel-fixed binocular camera is proposed in this paper. Firstly, two virtual counting lines are set to obtain four line space-time gray images. Then an integrated algorithm based on binocular stereovision and regional gray projection is proposed to extract and split overlapped moving objects in complex counting...
Background extraction is a fast and efficient moving object segmentation algorithm. This paper presents a new background extraction algorithm based on improved mode algorithm by using frame differential method to obtain the regions of static background. Then, this series of frames containing no moving foreground objects are counted by mode algorithm, thus improving the accuracy of the background extraction...
For many images with complicated foreground and background, it is difficult to locate interest object area by automatic segmentation algorithm. Interactive segmentation algorithms can provide effective control on these occasions. Interactive live-wire segmentation algorithm, which can provide accurate, reproducible boundary extraction, is widely applied. However, the algorithm, which employs Dijkstra...
In the paper an optimization of an iris image segmentation algorithm is presented. The algorithm consists of the following stages: reflections localization, reflections filling in, iris boundaries localization and eyelids boundaries localization. After insight into time complexity of the algorithm, the authors propose certain algorithm modifications to decrease its running time. The aim of the optimization...
We present an algorithm for real-time tracking of multiple pedestrians in a dynamic scene. The algorithm is targeted for embedded systems and reduces computational and storage costs by using an inexpensive kinematic tracking model with only fixed-point arithmetic representations. Our algorithm leverages from the observation that pedestrians in a dynamic scene tend to move with uniform speed over a...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.