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.
Motion analysis is still a challenging task in many computer vision applications. This paper proposes a new low-level motion feature based on geometric regularity information, particularly suited for traffic surveillance. Firstly, a novel concept of temporal geometry consistency constraint (TGCC) is introduced, which exploits the fact that the geometric structure of a rigid object remains consistent...
The recursive optimal per-pixel estimate (ROPE) is an effective end-to-end distortion estimation scheme. Most existing ROPE-based applications assume that: (i) the encoder knows exactly the actual packet loss rate and (ii) the decoder error concealment scheme; (iii) no deblocking in-loop filtering is employed. However, in practice, these assumptions may not all be valid. In this paper, we investigate...
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspectives lie on a 6D nonlinear manifold in Rn. In general, this nonlinear manifold is complicated and numerous samples are required to learn it globally. In this paper, we present a novel method and some preliminary results...
This paper addresses the low complexity end-to-end distortion (ED) estimation problem for error resilient video coding. Unlike the existing "look-back-only" ED estimation paradigm, we propose a new hybrid paradigm involving both "look-back" and "look-ahead" estimation. For low complexity, our "look-back" estimation accurately accounts for the error propagation...
This paper proposes a new concealment-aware motion estimation and mode selection scheme for error resilient video coding, where a new distortion metric is adopted to better accounts for the impact of "worst-case" distortion on the overall perceptual video quality than the existing statistically defined end-to-end distortion metric does. Effective "motion copy" error concealment...
A common approach to model-based tracking is to use a model of the object to predict what will be observed, and then to compare that with real observations. For methods that make use of the object's photometric properties (appearance) in their measurements, illumination inconsistencies between the modeled and actual scene can cause tracking problems. In this paper we address one case: model-based...
This paper proposes a new motion vector (MV) smoothing algorithm to track the real motion in image sequences for MPEG video encoders. First, a pre-checking algorithm is employed to eliminate wrong motion vectors and preserve all possible motion vectors. For each block considered, the motion similarity between the neighboring blocks and the number of candidate motion vectors are jointly exploited 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.