Abstract: A method for deduplication applicable to a file chunked into a plurality of deduplicated chunks is provided and includes: defining a calculation range in the file according to types of the chunks in the file, where the calculation range includes a plurality of consecutive chunks in the file; generating an evaluation value according to the types of the chunks in the calculation range to determine whether to mark the chunks in the calculation range; and re-chunking and deduplicating the marked chunks in the file. A computer-readable medium and a file system corresponding to the method for deduplication are also provided.

Abstract: A human face identification apparatus, a distributed human face identification system and a corresponding method are provided. The method includes obtaining a human face block from an image, identifying a data of a person corresponding to the human face block according to a client database by a client apparatus, controlling the client apparatus to transmit the human face block to a server apparatus and controlling the server apparatus to identify the human face block according to a server database when the data of the person corresponding to the human face block cannot be identified by the client apparatus, and copying the data of the person corresponding to the human face block from the server database to the client database when the data of the person is identified according to the server database by the server apparatus.

Abstract: Provided are an echo delay time estimation method and system thereof, wherein the echo delay time estimation method is executed by the echo delay time estimation system with the following steps: receiving a testing signal and a received signal and executing a time to frequency analysis to generate a testing signal spectrogram and a received signal spectrogram; respectively executing a characteristic signal dynamic detection calculation for the testing signal spectrogram and the received signal spectrogram to generate a testing signal characteristic dynamic vector and a received signal characteristic dynamic vector; executing a cross-correlated vector estimation for the testing signal characteristic dynamic vector and the received signal characteristic dynamic vector to generate a cross-correlated vector; and calculating an echo delay time according to the cross-correlated vector.

Abstract: A storage system of original frames of monitor data and a storage method thereof are provided. The storage system includes a monitor sensor, an event marking circuit, a data storage circuit and a frame processing circuit. The monitor sensor provides a plurality of original frames. The event marking circuit has an input terminal coupling to the monitor sensor and an output terminal, and is used for determining an event intensity of a corresponding one of the original frames and marks the event intensity on the corresponding original frame. The data storage circuit is coupled to the output terminal and is used for completely storing the original frames. The frame processing circuit is coupled to the data storage circuit and is used for checking whether the original frames within the data storage circuit are deleted according to the event intensities.

Abstract: An enhanced object detection method uses image discontinuousness for enhancing performance of identifying objects of a specific class in an image data. The method includes retrieving an image data; computing an image discontinuousness value between a first area and other areas surrounding of the first area, which is with different sizes and in different positions within the image data, and marking areas with an image discontinuousness value larger than a threshold; and identifying the objects of the specific class within the sliding window and outputting detection result.

Abstract: A background model learning system for lighting change adaptation for video surveillance is provided. The system includes a background model estimation unit that estimates a background model for a scene of interest; a foreground map construction unit that constructs a reference foreground map of the time instance; and a lighting change processing unit that revises the reference foreground map by reducing false foreground regions resulting from lighting changes. The revised foreground map is then sent back to both the background model estimation unit and the lighting change processing unit as feedbacks for model learning rate tuning in background model estimation and map integration in lighting change processing, respectively, for the next time instance.

Abstract: In the present invention, we identify that such a tradeoff between robustness to background changes and sensitivity to foreground abnormalities can be easily controlled by a new computational scheme of two-type learning rate control for the Gaussian mixture modeling (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.

Abstract: The present invention is to provide a method for reconstructing data in case of failure of two HDs of a RAID, wherein the RAID is a logical disk drive assembly including at least three HDs and a RAID controller and data is divided into block strips which are stored on data blocks of different HDs respectively, The method comprises the steps of reading super blocks of all of the HDs; comparing the number of the HDs and time being involved in a previous operation and stored in the super blocks with each other; reading common data involved in the previous degraded operation of the RAID; writing the read common data into the super blocks of all of the HDs; and recovering a configuration of the RAID to the degraded mode again.