Lin H.-H.,National Chiao Tung University |
Lin H.-H.,QNAP Inc |
Chuang J.-H.,National Chiao Tung University |
Liu T.-L.,Academia Sinica, Taiwan
IEEE Transactions on Image Processing | Year: 2011
To model a scene for background subtraction, Gaussian mixture modeling (GMM) is a popular choice for its capability of adaptation to background variations. However, GMM often suffers from a tradeoff between robustness to background changes and sensitivity to foreground abnormalities and is inefficient in managing the tradeoff for various surveillance scenarios. By reviewing the formulations of GMM, we identify that such a tradeoff can be easily controlled by adaptive adjustments of the GMM's learning rates for image pixels at different locations and of distinct properties. A new rate control scheme based on high-level feedback is then developed to provide better regularization of background adaptation for GMM and to help resolving the tradeoff. Additionally, to handle lighting variations that change too fast to be caught by GMM, a heuristic rooting in frame difference is proposed to assist the proposed rate control scheme for reducing false foreground alarms. Experiments show the proposed learning rate control scheme, together with the heuristic for adaptation of over-quick lighting change, gives better performance than conventional GMM approaches. © 2011 IEEE.
QNAP Inc | Date: 2010-12-07
To construct a video surveillance system, the Gaussian mixture modeling (GMM) is a popular choice among various background modeling approaches, for its capability of adaptation to background variations. However, the GMM often suffers from a tradeoff between robustness to background changes and sensitivity to foreground abnormalities, and is inefficient in managing the tradeoff for diverse surveillance scenarios. In the present invention, we identify that such a tradeoff can be easily controlled by a new computational scheme of two-type learning rate control for the GMM. Based on the proposed rate control scheme, a new video surveillance system that applies feedbacks of pixel properties computed in object-level analysis to the learning rate controls of the GMM in pixel-level background modeling is developed. Such a system gives better regularization of background adaptation and is efficient in resolving the tradeoff for many surveillance applications.
QNAP Inc | Date: 2014-03-19
An electronic device and a login method thereof are provided. The method includes the following steps. A first user information is received. A login authentication message corresponding to the first user information is obtained according to the first user information. A current sequence combination corresponding to a plurality of function buttons being pressed is received, and the function buttons are used for controlling the electronic device to execute a plurality of functions correspondingly. The current sequence combination is compared with a preset sequence combination of function buttons in the login authentication message. Whether a login process of the first user information is completed is determined. Accordingly, difficulties in entering a password may be solved by the function buttons on a remote controller, and an identity authentication may be simplified and quickly completed, so as to provide a better user experience for the user.
QNAP Inc | Date: 2015-04-16
A video playback method and a video playback apparatus are provided. The object path extraction module of the video playback apparatus extracts at least one object path from an original video. The video synthesizing module of the video playback apparatus selectively adjusts said object path, so as to synthesize the object path into the synthesis video. The video synthesizing module determines the time length of the synthesis video based on the playback time length set by user, wherein the time length of the synthesis video less than the time length of the original video.
QNAP Inc | Date: 2010-08-27
A locked warning apparatus used for a handle of a hard disk drive bracket is described. The locked warning apparatus includes a locking base, a locking device, an upper cover assembly, and a pressing unit. The locking base has a clasping portion and an elastic protrusion. The locking device has a blocking portion. The clasping portion of the locking base is fastened to the locking device in a form of line-surface interface contact. The blocking portion reciprocates a back and forth motion on the elastic protrusion of the locking base to allow the locking device to retain either a lock status or an unlock status correspondingly. When the locking device retains the lock status, the locking device buckles the upper cover assembly. When the locking device retains the unlock status, the upper cover assembly can be ejected from the locking base by pushing the pressing unit.