Abstract: Systems and methods in accordance with embodiments of this invention perform depth regularization and semiautomatic interactive matting using images. In an embodiment of the invention, the image processing pipeline application directs a processor to receive (i) an image (ii) an initial depth map corresponding to the depths of pixels within the image, regularize the initial depth map into a dense depth map using depth values of known pixels to compute depth values of unknown pixels, determine an object of interest to be extracted from the image, generate an initial trimap using the dense depth map and the object of interest to be extracted from the image, and apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.

Abstract: A communication vehicle system or platform that provides for the integration of multiple audio, visual, telecommunications, thermal, radiological, chemical and biological data detection and/or communication devices. The communication vehicle can be configured for providing mobile communications and surveillance in an environment in which the surrounding communications and/or power infrastructure has been damaged or is non-existent. For example, the vehicle can be deployed to the scene of a disaster or emergency. Accordingly, the mobility of the preferred communication vehicle can enhance and extend the reach of any emergency operations center. Other possible applications include law enforcement surveillance; tactical military command and control; weather and storm chasing; homeland security search and rescue; forward deployment monitoring, news agencies and border patrol.

Abstract: The present invention relates to a method for encoding and decoding an image signal and to corresponding apparatuses therefor. In particular, during the encoding and/or decoding of an image signal filtering with at least two filters is performed. The sequence of the filter application and possibly the filters are selected and the filtering is applied in the selected filtering order and with the selected filters. The determination of the sequence of applying the filters may be performed either separately in the same way at the encoder and at the decoder, or, it may be determined at the encoder and signaled to the decoder.

Abstract: Techniques and tools for reducing latency in video encoding and decoding by constraining latency due to reordering of video frames, and by indicating the constraint on frame reordering latency with one or more syntax elements that accompany encoded data for the video frames. For example, a real-time communication tool with a video encoder sets a syntax element that indicates a constraint on frame reordering latency, which is consistent with inter-frame dependencies between multiple frames of a video sequence, then outputs the syntax element. A corresponding real-time communication tool with a video decoder receives the syntax element that indicates the constraint on frame reordering latency, determines the constraint on frame reordering latency based on the syntax element, and uses the constraint on frame reordering latency to determine when a reconstructed frame is ready for output (in terms of output order).

Abstract: Provided is a vision system for detecting a defect, including a conveyer belt configured to move at least one bottle through the vision system; a light emitting diode (LED) backlight configured to silhouette any dark contamination on a surface or inside the at least one bottle; a robot with a bottle gripper tooling, the robot configured to pick up the at least one bottle and rotate the at least one bottle; at least one camera configured to take pictures of the at least one bottle while the at least one bottle is being rotated; and a flipper arm configured to stop or allow the at least one bottle to move to a position where the robot picks up the at least one bottle.

Abstract: An image processing device and method that enable suppression of an increase in the amount of coding of a scaling list. The image processing device sets a coefficient located at the beginning of a quantization matrix by adding a replacement difference coefficient that is a difference between a replacement coefficient used to replace a coefficient located at the beginning of the quantization matrix and the coefficient located at the beginning of the quantization matrix to the coefficient located at the beginning of the quantization matrix; up-converts the set quantization matrix; and dequantizes quantized data using an up-converted quantization matrix in which a coefficient located at the beginning of the up-converted quantization matrix has been replaced with the replacement coefficient. The device and method can be applied to an image processing device.

Abstract: In accordance with one or more techniques of this disclosure, a video coder may divide a current prediction unit (PU) into a plurality of sub-PUs. Each of the sub-PUs may have a size smaller than a size of the PU. Furthermore, the current PU may be in a depth view of the multi-view video data. For each respective sub-PU from the plurality of sub-PUs, the video coder may identify a reference block for the respective sub-PU. The reference block may be co-located with the respective sub-PU in a texture view corresponding to the depth view. The video coder may use motion parameters of the identified reference block for the respective sub-PU to determine motion parameters for the respective sub-PU.

Abstract: An electronic device for motion compensation is provided. The electronic device has a processing unit configured to perform a decoding program on a video bitstream to output decoding data, wherein the decoding data has a plurality of inter-prediction macroblocks, and the processing unit further generates a plurality of first pixel interpolation values according to the inter-prediction macroblocks which are smaller than a predetermined macroblock size. A motion compensation acceleration circuit is configured to generate a plurality of second pixel interpolation values according to the inter-prediction macroblocks which are larger than or equal to the predetermined macroblocks size, and generate a plurality of reconstructed macroblocks according to the first pixel interpolation values, the second pixel interpolation values, and a plurality of corresponding residue values.

Abstract: A method for detecting an object includes acquiring a first video of a source domain where a vision-based object detector is trained. Change detection is performed on the first video to collect one or more first localized, unlabeled sample images from the source domain. A second video is acquired of a target domain where the vision-based object detector is used. Change detection is performed on the second video to collect one or more second localized, unlabeled sample images from the target domain. A domain adaptation parameter is determined based on, one or more domain shift properties between the one or more first localized, unlabeled sample images from the source domain and the one or more second localized, unlabeled sample images from the target domain. The vision-based object detector is adapted to be used for object detection in the target domain based on the domain adaptation parameter.

Abstract: An image processing device and method that enable suppression of an increase in the amount of coding of a scaling list. The image processing device sets a coefficient located at the beginning of a quantization matrix by adding a replacement difference coefficient that is a difference between a replacement coefficient used to replace a coefficient located at the beginning of the quantization matrix and the coefficient located at the beginning of the quantization matrix to the coefficient located at the beginning of the quantization matrix; up-converts the set quantization matrix; and dequantizes quantized data using an up-converted quantization matrix in which a coefficient located at the beginning of the up-converted quantization matrix has been replaced with the replacement coefficient. The device and method can be applied to an image processing device.

Abstract: Systems and methods are described for modifying a cosmetic product based on a microbe profile including an ingredient-microbe interaction dataset including information associated with interactions between reference cosmetic ingredients and types of reference microbes; and a computing device including circuitry configured to receive information associated with the microbe profile of an individual, receive information associated with an ingredient list of the cosmetic product, compare the microbe profile of the individual and the ingredient list of the cosmetic product to the ingredient-microbe interaction dataset, identify an interaction between at least one cosmetic ingredient in the ingredient list of the cosmetic product and at least one of the one or more types of microbes in the microbe profile of the individual, recommend a modification to the ingredient list in response to an identified interaction, and report to a user the recommended modification.

Abstract: Systems and methods are described for modifying a cosmetic product based on a microbe profile including an ingredient-microbe interaction dataset including information associated with interactions between reference cosmetic ingredients and types of reference microbes; and a computing device including circuitry configured to receive information associated with the microbe profile of an individual, receive information associated with an ingredient list of the cosmetic product, compare the microbe profile of the individual and the ingredient list of the cosmetic product to the ingredient-microbe interaction dataset, identify an interaction between at least one cosmetic ingredient in the ingredient list of the cosmetic product and at least one of the one or more types of microbes in the microbe profile of the individual, recommend a modification to the ingredient list in response to an identified interaction, and report to a user the recommended modification.

Abstract: Disclosed herein are an apparatus and a method of video pre-processing for motion estimation, the apparatus comprising a similarity description module, a storage module, a verdict module, and a motion estimation module. The similarity description module receives a first image in a video, the first image consisting of first blocks, and calculates the similarity descriptors of every first block and a second block of a second image in the video. The second block corresponds to a reference block among the first blocks. The similarity descriptor of each block, which corresponds to a pixel matrix, indicates whether the pixel values of at least one pair of adjacent pixels in the pixel matrix are identical. The verdict module determines whether the similarity descriptors of the second and reference blocks are identical and reaches a verdict, whereby motion estimation is selectively performed on the second block.

Abstract: A method for determining the location of a portable device relative to a display is provided. An image stream is captured by the portable device when the portable device is positioned proximate to the display. The image stream is captured from a region of the display when the display is actively rendering a content stream, the content stream including embedded content for position determination. The embedded content is detected within the captured image stream, and the location of the portable device relative to the display is determined based on the detected embedded content.

Abstract: In one embodiment, an image-capturing device includes a camera, one or more motion-estimating devices to detect motion data for the device, and a processing system which is configured to automatically estimate a first direction of a sweep motion of the image-capturing device based on the motion data. The processing system is further configured to automatically estimate a second direction of the sweep motion of the image-capturing device based on images captured by the image-capturing device and to automatically select the first direction or the second direction of the sweep motion.

Abstract: Techniques and tools for reducing latency in video encoding and decoding by constraining latency due to reordering of video frames, and by indicating the constraint on frame reordering latency with one or more syntax elements that accompany encoded data for the video frames. For example, a real-time communication tool with a video encoder sets a syntax element that indicates a constraint on frame reordering latency, which is consistent with inter-frame dependencies between multiple frames of a video sequence, then outputs the syntax element. A corresponding real-time communication tool with a video decoder receives the syntax element that indicates the constraint on frame reordering latency, determines the constraint on frame reordering latency based on the syntax element, and uses the constraint on frame reordering latency to determine when a reconstructed frame is ready for output (in terms of output order).

Abstract: System and method for video processing. First video levels for pixels for a left image of a stereo image pair are received from a GPU. Gamma corrected video levels (g-levels) are generated via a gamma look-up table (LUT) based on the first video levels. Outputs of the gamma LUT are constrained by minimum and/or maximum values, thereby excluding values for which corresponding post-OD display luminance values differ from static display luminance values by more than a specified error. Overdriven video levels are generated via a left OD LUT based on the g-levels. The overdriven video levels correspond to display luminance values that differ from corresponding static display luminance values by less than the error threshold, and are provided to a display device for display of the left image. This process is repeated for second video levels for a right image of the stereo image pair, using a right OD LUT.

Abstract: Techniques and tools for reducing latency in video encoding and decoding by constraining latency due to reordering of video frames, and by indicating the constraint on frame reordering latency with one or more syntax elements that accompany encoded data for the video frames. For example, a real-time communication tool with a video encoder sets a syntax element that indicates a constraint on frame reordering latency, which is consistent with inter-frame dependencies between multiple frames of a video sequence, then outputs the syntax element. A corresponding real-time communication tool with a video decoder receives the syntax element that indicates the constraint on frame reordering latency, determines the constraint on frame reordering latency based on the syntax element, and uses the constraint on frame reordering latency to determine when a reconstructed frame is ready for output (in terms of output order).

Abstract: The present invention relates to a method for encoding and decoding an image signal and to corresponding apparatuses therefor. In particular, during the encoding and/or decoding of an image signal filtering with at least two filters is performed. The sequence of the filter application and possibly the filters are selected and the filtering is applied in the selected filtering order and with the selected filters. The determination of the sequence of applying the filters may be performed either separately in the same way at the encoder and at the decoder, or, it may be determined at the encoder and signaled to the decoder.

Abstract: In an example, a video coder may determine a first layer component of a first layer of video data, wherein the first layer of video data is associated with a layer identifier. The video coder may generate at least one filtered layer component by filtering the first layer component, and assign the layer identifier of the first layer and a filtered layer component index to the at least one filtered layer component, where the filtered layer component index is different than a layer component index of the first layer component. The video coder may also add the at least one filtered layer component to a reference picture set for performing inter-layer prediction of a layer other than the first layer of video data.