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.
Different from traditional algorithms, the material modeling method utilizing luma Y in YUV color space has been developed in this paper. Our method, which interactively acquires material appearance from a single image, includes four main steps: removing highlight, recovering normal based on luma Y, estimating diffuse coefficient, setting glossiness and specular coefficient interactively. The experiment...
Vehicle identification is one of the frequently studied problems in video surveillance. Commonly, identifying an unknown vehicle object requires a large amount of training instances. Unfortunately, in the large parking scenario, the cost may be prohibitively expensive because of the finitely waiting time from the car owners. In this paper, we show that it is possible to identify a registered vehicle...
In this paper, we propose a multi-cue fusion approach to detect the road boundary using stereo vision, which fits road boundary with a few edge points. Firstly boundary areas are determined in accordance with the normal vector information. Based on the cues of normal vector, height and color in the boundary area, three Bayes models are established respectively. Then the Naive Bayes framework could...
Lane detection is crucial part of vision driver assistance system of intelligent vehicles. In this paper we present a multi-lane detection method using omni-directional camera. The contribution of this paper is twofold. Firstly, we present an anisotropy steerable filter with the aim of get more reliable lane markings feature extraction under adverse circumstance. Secondly, an optimization method to...
Images captured in foggy scenes suffer from degraded contrast and colors. It's imperative to overcome the weather effects and make outdoor vision systems more reliable. This paper describes a fast algorithm to enhance the visibility of foggy scenes with solely a single image. Firstly, the thickness of the fog is estimated with a Gaussian filter and an intensity image, which is composed of the foggy...
In this paper, a new framework is proposed for autonomous universal surveillance based on video and audio data. ??Universal?? indicates no specification of targets of interest. Instead, regions of importance (ROIs) in a scene should be detected. Specifically, in the video domain, a frame-based main subject detection is proposed based on adaptive selection of low-level features. In the audio domain,...
This paper proposes a fast and robust algorithm for traffic sign detection and recognition. The algorithm includes two stages: traffic sign detection and recognition. In the first stage, Adaboost algorithm based red pixels model of speed limit sign in the Lab color space is built. Then the model is used to extract area of latent speed limit signs. After that, the improved Hough Transform is used to...
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.