Abstract: An object detection method for detecting objects under moving cloud shadow comprises two main sub-procedures linked to each other. The first main sub-procedure is for detecting the moving cloud region and its moving border regions. Once the moving border region is detected, a moving border mask is used to filter out the foreground objects located under the moving border regions. The filtered foreground objects include both real objects and the false alarms generated by abrupt intensity change caused by fast-moving cast cloud shadows. The decision for the elimination of possible false alarms is performed in the second main sub-procedure.

Abstract: A method for learning deep convolutional features specifically designed for correlation filter based visual tracking includes the steps of, selecting a first image from a first image patch; selecting a second image from a second image patch; forward propagating selected first image by a convolutional neural network model formula, the formula has random weights with zero mean for the parameters; forward propagating selected second image by the convolutional neural network model formula; computing correlation filter using forward propagated second image and centered correlation response; circularly correlating forward propagated first image and computed correlation filter to generate predicted response map; calculating the loss by comparing the predicted response map with desired correlation corresponding selected first image and second image and updating the parameters of the convolutional neural network model formula according to calculated loss.

Abstract: A method for learning deep convolutional features specifically designed for correlation filter based visual tracking includes the steps of, selecting a first image from a first image patch; selecting a second image from a second image patch; forward propagating selected first image by a convolutional neural network model formula, the formula has random weights with zero mean for the parameters; forward propagating selected second image by the convolutional neural network model formula; computing correlation filter using forward propagated second image and centered correlation response; circularly correlating forward propagated first image and computed correlation filter to generate predicted response map; calculating the loss by comparing the predicted response map with desired correlation corresponding selected first image and second image and updating the parameters of the convolutional neural network model formula according to calculated loss.

Abstract: The invention generally provides a method and apparatus for up-converting the frame rate of a digital video signal, the method comprising: receiving a digital video signal containing a first frame and a second frame; finding in one of the received frames, matches for objects in the other of the received frames; utilizing 3 dimensional position data in respect of the objects within the frames to determine 3 dimensional movement matrices for the matched objects; using the 3 dimensional movement matrices, determining the position of the objects in a temporally intermediate frame and thereby generating an interpolated frame, temporally between the first and second frame.

Abstract: A method and an apparatus are disclosed for increasing the frame rate of an input video signal by interpolating video frames between original video frames of the input video signal and inserting interpolated video frames between original video frames of the input video signal to produce an output video signal having a higher frame rate than the input signal.

Abstract: The invention relates to using the properties of the mobile client terminal, preferably data processing capability and the screen size, and the capacity of the communication channel between the video streaming server and the client terminal, to determine the bit rate, frame rate and the spatial resolution that the multimedia data, preferably video, needs to be encoded with in order to provided the end user with the maximum possible subjective user satisfaction. The invention also pertains to sending the multimedia data coded with the determined parameters to the client terminal using a video transcoder and a streaming server.

Abstract: The invention generally provides a method and apparatus for up-converting the frame rate of a digital video signal, the method comprising: receiving a digital video signal containing a first frame and a second frame; finding in one of the received frames, matches for objects in the other of the received frames; utilising 3 dimensional position data in respect of the objects within the frames to determine 3 dimensional movement matrices for the matched objects; using the 3 dimensional movement matrices, determining the position of the objects in a temporally intermediate frame and thereby generating an interpolated frame, temporally between the first and second frame.

Abstract: A method and an apparatus are disclosed for increasing the frame rate of an input video signal by interpolating video frames between original video frames of the input video signal and inserting interpolated video frames between original video frames of the input video signal to produce an output video signal having a higher frame rate than the input signal.

Abstract: The invention relates to using the properties of the mobile client terminal, preferably data processing capability and the screen size, and the capacity of the communication channel between the video streaming server and the client terminal, to determine the bit rate, frame rate and the spatial resolution that the multimedia data, preferably video, needs to be encoded with in order to provided the end user with the maximum possible subjective user satisfaction. The invention also pertains to sending the multimedia data coded with the determined parameters to the client terminal using a video transcoder and a streaming server.

Abstract: A rule-based method which detects and tracks the moving objects in video frames in an automated way is invented. The method can be used in object based image sequence compression applications. Motion of pixels between two consecutive frames are estimated using a block based motion estimation method, and the resultant dense motion vector field is segmented. Using the same method, a second segmentation is achieved based on partitioning of the image according to color values of the pixels. The image, which is formed by the translation of the final segmentation results of the previous frame using the estimated motion vectors, is used as the third segmentation. By the help of a sequence of rules, which uses the three different segmentation masks as its inputs, detection and tracking of moving objects in the scene is achieved within accurate boundaries; the problems caused by occlusion or uncovered background are insignificant.