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.
To effectively utilize storage space of edge streaming media servers, cache policies are being studied. Unlike traditional work that focused on hit ratio and overall system bandwidth cost, this paper recognize different significance of users and propose the concept of caching utility as a new metric to evaluate caching strategies. A user based caching algorithm, USCS, involving differentiated service...
The snowflake noise can bring many problems to the video detection, so we propose an efficient method based on video surveillance, which is to solve the detection of snowflake noise. This method is based on the basic features of snowflake noise. We extract video frame from the video, pick up the complacent pixel point, and get rid of the edge and some interference factor. Then the intermediate results...
The images of outdoor scenes obtained in haze, fog and other weather days are usually have poor contrast and color fidelity. In this paper, in order to effectively improve the degraded image in haze quality, reduce the effect of the haze to outdoor traffic video monitoring systems, we analyzed the image degradation reason and fuzzy mechanism of image in haze. From the viewpoints of image restoration...
Vehicle flow volume on the motorway in the urban area is successfully used to realize traffic decision-making and guidance. In this research, we introduced some critical components into a vehicle flow detection system. In order to enhance the accuracy and instantaneity of the vehicle counting in quick-change traffic conditions, an adaptive modeling and updating method of background was proposed. In...
With the advancement of motion capture technology, 3D skeleton data is easier to be obtained. 3D skeleton data has the advantage over traditional video data for the reason that it is less affected by illumination, complex background, self-occlusion and noise. 3D skeleton data brings new opportunities and challenges to the action recognition research. In this paper, we propose a new method for action...
According to the features of traffic supervisory video, Compressive Tracking (CT) algorithm is adopted to detect and track the moving car. When the camera angle, moving vehicle scale and background changed, the CT algorithm still has a strong robustness. However, the algorithm is invalid when car is sheltered so that the tracked car cannot be located. In order to overcome this problem, a new method...
Multi-camera tracking is quite different from single camera tracking in mathematical principles and application scenarios, and it faces new technology and system architecture challenges. The existing theories and algorithms used in object matching, cameras calibration and topology estimation, and information fusion have been reviewed and show that the integrated application of multi techniques and...
Modern video surveillance systems need to acquire clear video images of the interest targets in wide range scene, which usually have some difficulties only by changing the cameras focal length when the targets distance and constantly move. In order to obtain details of the features of long distance moving targets in wide range of monitoring scene, we use a panoramic camera and Intelligent Speed Dome...
When there are serious occlusion and illumination change, Probabilistic Occupancy Map (POM) algorithm can track six more people simultaneously with multiple video streams. The output result of foreground detection will be the available input data in POM algorithm, so the performance of a foreground detection algorithm is very important for the entire POM algorithm. Presently, Gaussian mixture model...
A post-processing technique is introduced to improve the Eulerian video magnification method, which is a state-of-the-art motion magnification method to manipulate small movements in videos based on spatio-temporal filtering. The proposed method use the Eulerian video magnification as a video spatio-temporal motion analyzer to get the pixel-level motion mapping. Then the input video pixels are warped...
In this paper, a reliable pixel-based foreground-background segmentation technique for detecting object(s) of interest (OOI) from video sequence captured by a fixed camera is proposed. OOIs, used for further tracking or positioning applications, should be detected accurately from those moving (or still) objects even under variable illumination and the corresponding background model need to update...
Recently, attention has been paid to tracking methods using sparse representation. Assuming that the representation residuals follow Gaussian distribution, the multi-object tracking methods based on sparse representation are proposed. However, these methods are sensitive to outliers such as occlusion due to the assumption of Gaussian distribution. In our paper, a novel sparse representation based...
A novel tracking method is developed based on logistic regression classifier and sparse representation in this paper. Firstly, the logistic regression classifier with online update is utilized to determine the searched image patches belonging to the potential targets or the false targets. Through the classification, a huge number of false targets can be removed from the searched patches. Then, the...
Traditional Top-N strategy for movie recommendation takes only users' ratings into account when mining users' needs or interests. But watching movie is a special behavior, in which users' interests should not just be represented by their ratings. We think that the decision to watch a movie also reflects the target users' needs, even though he or she may give it a low rating. In this paper, we introduce...
This paper presents a Belief Propagation (BP) stereo matching algorithm based on ground control points (GCP) and spatiotemporal consistency. In the context the BP algorithm based on spatiotemporal consistency has large amount of calculation with low matching accuracy, the proposed algorithm adds GCP into the spatiotemporal consistency BP algorithm model to propagate the disparities of GCP. This algorithm...
This paper presents a novel system for vision-based driving posture recognition. The driving posture dataset was prepared by a side-mounted camera looking at a driver's left profile. After pre-processing for illumination variations, eight action classes of constitutive components of the driving activities were segmented, including normal driving, operating a cell phone, eating and smoking. A global...
While classical face recognition (FR) technologies are mainly based on static images, video-based FR is concerned with the matching of two image sets containing facial images captured from each video. Video based FR is supposed to be advantageous as it takes more abundant information in to account to improve accuracy and robustness. Though many methods have been proposed, there still exists a variety...
The algorithm based on SIFT feature matching and Kalman filter has been used for digital video stabilization, it is efficient in many applications. However, video obtained by the method is still not stable. An improved scheme in motion filtering is proposed in this paper. The scheme is that global motion vector estimated by Kalman filter is filtered by an ideal low-pass filter with the Hanning window,...
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.