Abstract: The disclosure herein relates to devices for compression, decompression or reconstruction of image data for still or moving pictures, such as image data detected with a digital camera. In some embodiments, data channels are compressed using a scalable compression algorithm. The compression algorithm may allow customization of compression parameters, such as a quantization factor, code block size, number of transform levels, reversible or irreversible compression, a desired compression ratio with a variable bit rate output, a desired fixed bit rate output with a variable compression rate, progression order, output format, or visual weighting. A lower quality image or an image with lower resolution may be reconstructed using only some of the compressed data. Use of offsets to various layers and color channels allow reconstruction of the image without requiring decompression of all of the full image data.

Abstract: An image processing apparatus which extracts a lesion having a ground glass opacity from an image includes a change unit which changes a pixel value corresponding to a candidate region for the ground glass opacity to a predetermined pixel value range, a first feature amount extraction unit which obtains a first feature amount from the image, the pixel value of which is changed, and an extraction unit which extracts the lesion from the image based on the first feature amount.

Abstract: Disclosed are an apparatus and a method for detecting an object for a vehicle, the apparatus including: a camera unit configured to output a surrounding image of a vehicle; an object candidate extracting unit configured to extract an object candidate from the output surrounding image of the vehicle; a height reference filtering unit configured to output a filtered image by excluding an object having a height equal to or smaller than a threshold value from the extracted object candidate; and an object recognizing unit configured to detect a specific object from the output filtered image.

Abstract: Systems and methods for creating a ground confidence map of a geographic area, comprising the steps of creating a ground confidence map of a geographic area, the ground confidence map having a plurality of pixels with each pixel corresponding to a particular geographic location; assigning the pixels in the ground confidence map with pixel values indicative of composite ground confidence scores by calculating composite ground confidence scores for the pixel values of common geographic regions within the overlapping portions of the source images within a kernel corresponding to the particular geographic location of the pixels; and storing pixel values indicative of a statistical probability that the geographical location represented by the particular pixels represent the ground.

Abstract: A wafer metrology system includes an interferometer sub-system and a controller. The interferometer sub-system is configured to generate an interferogram with an intensity map that corresponds to a modulated representation of a wafer surface. Further, the interferometer sub-system includes a detector configured to capture the interferogram. The controller includes one or more processors configured to generate a wrapped phase map of the interferogram, define patterns associated with features on the wafer, and correct phase discontinuities by applying a phase unwrapping procedure to the wrapped phase map to generate an unwrapped phase map and correcting phase discontinuities in the unwrapped phase map based on the patterns, or by combining phase unwrapping and correction in a unified step. Further, the patterns comprise two or more structures such that a portion of the unwrapped phase map associated with structures of the same type is continuous across borders separating structures of the same type.

Abstract: A method and apparatus for resolving a set of objects in an image of an area. A partition that captures a set of objects is identified using the image. The partition is comprised of a group of contiguous object pixels. A number of local max pixels are identified from the group of contiguous object pixels in the partition. A quantitative resolution of the set of objects captured in the partition is performed based on the number of local max pixels identified.

Abstract: A method and apparatus for cross-domain medical image synthesis is disclosed. A source domain medical image is received. A synthesized target domain medical image is generated using a trained contextual deep network (CtDN) to predict intensities of voxels of the target domain medical image based on intensities and contextual information of voxels in the source domain medical image. The contextual deep network is a multi-layer network in which hidden nodes of at least one layer of the contextual deep network are modeled as products of intensity responses and contextual response.

Abstract: Computerized methods are performable by a driver assistance system while the host vehicle is moving. The driver assistance system includes a camera connectible to a processor. First and second image frames are captured from the field of view of the camera. Corresponding image points of the road are tracked from the first image frame to the second image frame. Image motion between the corresponding image points of the road is processed to detect a hazard in the road. The corresponding image points are determined to be of a moving shadow cast on the road to avoid a false positive detection of a hazard in the road or the corresponding image points are determined not to be of a moving shadow cast on the road to verify detection of a hazard in the road.

Abstract: The technology disclosed relates to automatically (e.g., programmatically) initializing predictive information for tracking a complex control object (e.g., hand, hand and tool combination, robot end effector) based upon information about characteristics of the object determined from sets of collected observed information. Automated initialization techniques obviate the need for special and often bizarre start-up rituals (place your hands on the screen at the places indicated during a full moon, and so forth) required by conventional techniques. In implementations, systems can refine initial predictive information to reflect an observed condition based on comparison of the observed with an analysis of sets of collected observed information.

Abstract: Watermark data is converted to watermark coefficients, which may be embedded in an image by converting the image to a frequency domain, embedding the watermark in image coefficients corresponding to medium-frequency components, and converting the modified coefficients to the spatial domain. The watermark data is extracted from the modified image by converting the modified image to a frequency domain, extracting the watermark coefficients from the image coefficients, and determining the watermark data from the watermark coefficients. The watermark data may be truncated image data bits such as truncated least significant data bits. After extraction from the watermark, the truncated image data bits may be combined with data bits representing the original image to increase the bit depth of the image. Watermark data may include audio data portions corresponding to a video frame, reference frames temporally proximate to a video frame, high-frequency content, sensor calibration information, or other image data.

Abstract: In a system that displays the existing position of an object caught by a camera on a map, the load on a user are reduced, and user-friendliness is increased. The position of an object in a camera image is converted into a position on a map with the use of conversion equations. The existing position of the object based on a result of the conversion is displayed on the map based on results of the conversion. The existence allowed region of the object on the map is set through a designation by the user. The parameters of the conversion equations are determined based on results of the conversion at respective times within a predetermined period of time and the set existence allowed region of the object so that trajectories of the object on the map fall within the existence allowed region.

Abstract: An approach is provided for providing one or more road conditions based on aerial imagery. The road condition platform processes and/or facilitates a processing of one or more road segments on an aligned image including an aerial image frame of an area and a reference map of the area to determine one or more non-road elements. The road condition platform also determines one or more characteristics of the one or more non-road elements disposed within the one or more road segments. The road condition platform further determines one or more road conditions based on the one or more characteristics.

Abstract: The disclosure relates to a method of automatically producing a three-dimensional (3D) segmentation of a heart chamber, the method comprising: obtaining data sets from cardiac magnetic resonance imaging (MRI) or ultrasound, generating a 3D segmentation of the heart chamber from the data sets using an active contour method, modifying the 3D segmentation by adding a plurality of intra-chamber structures; and identifying an enclosing myocardium using the 3D segmentation generated by the method.

Abstract: Methods, systems, computer programs, circuits and workstations are configured to generate at least one two-dimensional weighted CBF territory map of color-coded source artery locations using an automated vascular segmentation process to identify source locations using mutual connectivity in both image and label space.

Abstract: A medical image processing apparatus includes a data acquirer that scans an object with a fiducial marker attached thereto to acquire volume data, and a data processor that estimates a plane of interest, based on a position of the fiducial marker and a position of a landmark in the volume data.

Abstract: A system for transmitting notifications based on image data analysis may comprise: an image registration module to receive, from an unmanned aerial vehicle, current image data of a geographic location; a change detection module to: compare the current image data with previous image data of the geographic location to identify a change in the geographic location; and analyze the change to determine a category of the change in the geographic location; and an action module to: determine at least one party to notify about the change based on the category; and transmit a notification to the at least one party via an unmanned aerial vehicle.

Abstract: The present disclosure is directed to an autonomous vehicle having a vehicle control system. The vehicle control system includes a vehicle detection system. The vehicle detection system includes receiving an image of a field of view of the vehicle and identifying a region-pair in the image with a sliding-window filter. The region-pair is made up of a first region and a second region. Each region is determined based on a color of pixels within the sliding-window filter. The vehicle detection system also determines a potential second vehicle in the image based on the region-pair. In response to determining the potential second vehicle in the image, the vehicle detection system performs a multi-stage classification of the image to determine whether the second vehicle is present in the image. Additionally, the vehicle detection system provides instructions to control the first vehicle based at least on the determined second vehicle.

Abstract: A similarity detection system receiving a plurality of input entities, the system including a cohesive subgraph identification device configured to calculate, based on attributes of the plurality of input entities, a first parameter and a second parameter based on the first parameter, and further configured to identify a plurality of subgraphs from the second parameter and a subgraph correlation tracking and clustering device configured to determine a relationship between different subgraphs based on a similarity factor between the second parameter and the plurality of subgraphs.

Abstract: A map creation apparatus includes an image receiver configured to receive images in time series while moving; a first calculator configured to extract an image area indicating an object from the images and calculate a coordinate of the object in a world coordinate system; a second calculator configured to track the object in the extracted image area with the images and calculate an optical flow of the object; an eliminator configured to calculate a difference in coordinate between vanishing points generated by the movement of the image receiver and the object based on the optical flow, and eliminate the image area of the object from the images when determining the object as a moving object based on the calculated difference; and a storage controller configured to store map information including the coordinate of the object, not eliminated by the moving object eliminator, in the world coordinate system.

Abstract: A method for identifying print control elements for quality data acquisition includes encoding position information in a human-readable identification code, encoding specific print job information and the human-readable identification code in a machine-readable data code, positioning the codes alongside their associated print control element on a printing substrate, photographing the printed print control element and adjacent machine-readable data code using information from adjacent identification code, and processing data with a mobile communication device having a camera function and communications interface. Image data produced are exporting to a support computer via the communications interface.