Abstract: A method of operating a surveillance system having a display unit configured to display a surveillance image includes acquiring the surveillance image from at least one acquisition device. The method also includes setting surveillance event that includes setting a desired surveillance object indicating an attribute of the surveillance event. Further, the method includes displaying the selected surveillance object with the acquired surveillance image on the display unit to indicate the set surveillance event and analyzing the acquired surveillance image to determine whether the set surveillance event has occurred. In addition, the method includes performing an indicating operation in the surveillance system in response to the occurrence of the set surveillance event.

Abstract: A method and apparatus for detecting an object using a perspective plane are disclosed. The method includes determining a perspective plane for a background scene, and determining a moving object within the background scene based upon the determined perspective plane. By using a visual surveillance device and an apparatus for detecting objects, the method and apparatus for detecting an object using a perspective plane is capable of efficiently detecting objects and tracking the movements of the corresponding objects.

Abstract: A method of operating a surveillance system having a display unit configured to display a surveillance image includes acquiring the surveillance image from at least one acquisition device. The method also includes setting surveillance event that includes setting a desired surveillance object indicating an attribute of the surveillance event. Further, the method includes displaying the selected surveillance object with the acquired surveillance image on the display unit to indicate the set surveillance event and analyzing the acquired surveillance image to determine whether the set surveillance event has occurred. In addition, the method includes performing an indicating operation in the surveillance system in response to the occurrence of the set surveillance event.

Abstract: A method and apparatus for detecting an object using a perspective plane are disclosed. The method includes determining a perspective plane for a background scene, and determining a moving object within the background scene based upon the determined perspective plane. By using a visual surveillance device and an apparatus for detecting objects, the method and apparatus for detecting an object using a perspective plane is capable of efficiently detecting objects and tracking the movements of the corresponding objects.

Abstract: The present invention discloses a method for extracting an object region in a motion picture, which can extract the object region of a current frame using different methods based on a degree of motion of the object. Especially, when the object has many motions, an object region of a previous frame is modified by comparing a CDI (Change Detected Image) generated based on a difference between the previous frame and the current frame with the previous frame. As a result, the present invention can be applied to image communication requiring real-time processing, and also applied to techniques requiring precise background change by dividing the object region in pixel units.

Abstract: An object-based bit rate control method and a system therefore provides a user with satisfactory quality of image by using significance of the object. The object is separated from the image, and significance is imposed on each object. A quantization parameter is differently varied according to the significance of the object. Especially, a variable width of the quantization parameter is controlled in a boundary region of the object and the other regions.

Abstract: The present invention relates to a method for summarizing a news video stream using a synthetic key frame based upon news video text. The method according to the invention generates the synthetic key frame by allocating different importance measures according to an icon text region and a general text region.

Abstract: There is provided a moving picture coding method, which is capable of providing high picture quality and high compression ratio. The moving picture coding method includes the steps of: classifying an inputted image into predetermined image groups according to characteristic of a sense of sight; assigning different weights according to the respective image groups to change a quantization parameter; applying low pass filters (LPFs) having different frequency magnitudes; and performing a variable length coding (VLC) to the respective image groups.

Abstract: There is provided a video communication system, which is capable of preventing damage or loss of video data. The video communication system includes: a video encoder for performing a data hiding to an error information provided from the video decoder, transmitting a processed error information to the video decoder, and performing an error concealment with reference to the error information; and the video decoder for extracting an information on an error frame, providing the extracted frame information to the video encoder, extracting the hidden data provided from the video encoder, and performing an error concealment with reference to the extracted hidden data.

Abstract: There is provided a moving picture coding method, which is capable of effectively processing error concealment through data hiding. The moving picture coding method includes the steps of: extracting a picture header information of an inputted image at an encoder; transmitting the extracted picture header information through data hiding; and performing an error concealment using the transmitted picture header information at a decoder.

Abstract: There is provided a moving picture coding method, which hides data in multimedia images. The moving picture coding method includes the steps of: extracting a motion vector of an inputted image through a motion estimation and a motion compensation, and performing a DCT (discrete cosine transform) to a difference image of the inputted image to set an initial quantization parameter; performing a data hiding to the set quantization parameter, and changing the quantization parameter to recognize whether or not the data hiding is performed; performing a quantization using the changed quantization parameter; and performing a data hiding by changing a level value of each block by block unit, to which a DCT is performed.

Abstract: There is provided a moving picture coding method, which is capable of effectively processing error concealment through data hiding. The moving picture coding method includes the steps of: extracting an information on region of interest (ROI) of an inputted image at an encoder; transmitting the extracted information on the ROI through data hiding; and performing an error concealment using the information on the ROI at a decoder.

Abstract: An object-based bit rate control method and a system therefore provides a user with satisfactory quality of image by using significance of the object. The object is separated from the image, and significance is imposed on each object. A quantization parameter is differently varied according to the significance of the object. Especially, a variable width of the quantization parameter is controlled in a boundary region of the object and the other regions.

Abstract: An object-based bit rate control method prevents cut-off of video and maintains high quality of video even when a bit rate of a network is seriously lowered. The object is segmented from the image, and significance is imposed on macro blocks included in the segmented object. When the bit rate of the network is lowered, the macro block having high significance is normally encoded and transmitted, and the macro block having low significance is not encoded.

Abstract: The present invention discloses a method for extracting an object region, which can precisely modify a boundary of a roughly extracted object region (reference region). The boundary of the reference region can be modified by detecting edge pixels nearest to the boundary pixel of the reference region. Thereafter, an expanded region is designated from the modified reference region, and a surrounding region having the smallest color difference is selected by using color differences between the expanded region and the surrounding regions. At last, the modified boundary of the reference region is modified by using distribution of interest region included in the selected surrounding region. As a result, the object region can be more precisely extracted by preventing confusion of the boundary by modifying the reference region twice.

Abstract: The present invention is provided a face detecting method depending on image that includes a step of obtaining a color group mainly distributed in a given image; a step of designating a color group corresponding to a human color in the obtained color groups; and a step of segmenting a portion composed with pixels corresponding to color group of a human color.

Abstract: The present invention discloses a method for extracting an object region in a motion picture, which can extract the object region of a current frame using different methods based on a degree of motion of the object. Especially, when the object has many motions, an object region of a previous frame is modified by comparing a CDI (Change Detected Image) generated based on a difference between the previous frame and the current frame with the previous frame. As a result, the present invention can be applied to image communication requiring real-time processing, and also applied to techniques requiring precise background change by dividing the object region in pixel units.

Abstract: The present invention relates to a method for summarizing a news video stream using a synthetic key frame based upon news video text. The method according to the invention generates the synthetic key frame by allocating different importance measures according to an icon text region and a general text region.

Abstract: The present invention generally relates to a multimedia browsing system, and more particularly, to a method for generating a synthetic key frame, which allows a video stream to be efficiently summarized while being searched and filtered based upon the summarization. The present invention generates the synthetic key frame based upon video text by calculating an importance measure of text areas extracted from the video image and using only those text areas having the importance measures of at least a predetermined value.