Abstract: A fusion based passenger tracking system includes one or more 2D/3D sensors for capturing 2D/3D data; one or more security sensors for capturing security data; and a processing module in communication with the one or more 2D/3D sensors to receive the 2D/3D data, and the one or more security sensors to receive the security data, the processing module uses the 2D/3D data and the security data to calculate passenger data to generate a passenger tracking list that tracks each individual passenger in the passenger data.

Abstract: Methods, devices, and systems for building space control are described herein. One device includes a memory, and a processor configured to execute executable instructions stored in the memory to receive a recording of a gesture interaction with a virtual control element associated with a setting of a space in a building, analyze the recorded gesture for gesture characteristics, and modify the setting of the space based on the virtual control element and the gesture characteristics.

Abstract: Techniques are provided for detection, classification and tracking of surface contacts based on multispectral image data from sensors on maritime assets. An example system may include an anomaly detection circuit configured to detect an object based on anomalies in the variance of pixels of water surface image data. The system may also include an object motion tracking circuit configured to analyze motion of the object relative to water surface waves. The analysis may compensate for motion of the asset and sensors. The system may further include an object classification circuit configured to classify the object as an object of interest, based on the analyzed motion of the object, and as a threat, further based on size estimation, edge detection, surface texture analysis, and volume analysis. The range from the asset to the object may be estimated based on the relation of the object to a detected or estimated horizon line.

Abstract: An industrial vehicle positioning system and method are presented. The system includes a first imaging subsystem for acquiring a first indicia image and a second imaging subsystem for acquiring a second indicia image. An image analysis subsystem is configured for analyzing the first indicia image to acquire a first location designation, and for analyzing the second indicia image to acquire a second location designation. A processor is configured for determining the location of the industrial vehicle based upon the first location designation and the second location designation.

Abstract: Methods and related apparatus (SP) to correct phase shift image data for phase wrapping artifacts. The data is detected at a detector (D) of an imaging system (IM) including interferometric equipment (G0, G1, G2). In a phase unwrapping method that involves optimizing an objective function with regularization, a two-sage approach is proposed. The measured data is processed in one stage with regularization and in the other stage without regularization. This allows improving the accuracy of the corrected (phase unwrapped) phase shift data because an undesirable bias caused by the regularization can be avoided.

Abstract: A method and apparatus for lane detection using overhead images and positional data. A server receives positional data from a vehicle and computes a continuous trajectory. The server receives an overhead image of a road section. The server crops and processes the overhead image to remove unwanted portions. The server identifies edge features using the continuous trajectory and steerable filters. The server identifies lanes in the overhead image using a maximization algorithm, the edge filters, and the continuous trajectory.

Abstract: Detection and identification a field's boundaries is performed in a workflow based on processing images of the field captured at different times, relative to a defined seed point. Images are clipped to align with the seed point and a bounding box around the seed point, and a mask is built by extracting edges of the field from the images. The workflow floods an area around the seed point that has pixels of a similar color, using the mask as an initial boundary. The flooded area is compared to threshold parameter values, which are tuned to refine the identified boundary. Flooded areas in multiple images are combined, and a boundary is built based on the combined flooded set. Manual, interactive tuning of floodfill areas allows for a separate boundary detection and identification workflow or for refinement of the automatic boundary detection workflow.

Abstract: Detection and identification a field's boundaries is performed in a workflow based on processing images of the field captured at different times, relative to a defined seed point. Images are clipped to align with the seed point and a bounding box around the seed point, and a mask is built by extracting edges of the field from the images. The workflow floods an area around the seed point that has pixels of a similar color, using the mask as an initial boundary. The flooded area is compared to threshold parameter values, which are tuned to refine the identified boundary. Flooded areas in multiple images are combined, and a boundary is built based on the combined flooded set. Manual, interactive tuning of floodfill areas allows for a separate boundary detection and identification workflow or for refinement of the automatic boundary detection workflow.

Abstract: A method of image-based quantification for allergen skin reaction includes imaging an area of skin that has been subject to a skin-prick test to produce one or more images of the area. The method includes identifying regions of wheal and/or flare in the one or more images of the area and quantifying weal and/or flare indicators based on the regions identified. The method also includes outputting results of the quantified wheal and/or flare indicators indicative of quantified allergen skin reaction.

Abstract: A method and device for banknote identification based on thickness signal identification, allowing for simple and highly efficient identification and separation of abnormal banknotes by means of combining two thickness identification methods, namely an upward-facing area identification method and a downward-facing area identification method, for banknote identification.

Abstract: There is presented a method 100 and apparatus 200 to measure the surface of the patient (thorax and abdominal regions), e.g., during therapy delivery and (if necessary) while imaging. Together with biomechanical considerations the position of internal structures of the patient, such as an organ, and optionally a tumor in an organ, is inferred from the measured patient surface. In case the patient breaths and thus the organ and/or tumor moves, the position may be determined, which may be advantageous during, e.g., radiation therapy, since it enables that whenever the tumor is at the right position according to the radiation therapy plan, the radiation is switched on. In a specific embodiment, a finite element model is employed.

Abstract: A method of generating a personalized parameter value for generating a medical image includes acquiring a first medical image of an object, which is imaged according to a predetermined parameter value set in a medical imaging apparatus, and a second medical image changed from the first medical image, determining a first standard parameter value corresponding to the first medical image and a second standard parameter value corresponding to the second medical image, and generating a personalized parameter value corresponding to the object on the basis of the first standard parameter value and the second standard parameter value.

Abstract: Embodiments are disclosed herein that relate to the automatic tracking of objects. For example, one disclosed embodiment provides a method of operating a mobile computing device having an image sensor. The method includes acquiring image data, identifying an inanimate moveable object in the image data, determining whether the inanimate moveable object is a tracked object, if the inanimate moveable object is a tracked object, then storing information regarding a state of the inanimate moveable object, detecting a trigger to provide a notification of the state of the inanimate moveable object, and providing an output of the notification of the state of the inanimate moveable object.

Abstract: Information is encoded in an image signal by exploiting spectral differences between colors that appear the same when rendered. These spectral differences are detected using image sensing that discerns the spectral differences. Spectral difference detection methods include using sensor-synchronized spectrally-structured-light imaging, 3D sensors, imaging spectrophotometers, and higher resolution Bayer pattern capture relative to resolution of patches used to convey a spectral difference signal.

Abstract: A method for automatically detecting a region of interest in a digital medical image, comprising over-segmenting the image into a plurality of superpixels through use of an over-segmentation algorithm; for each pair of neighboring superpixels in the plurality of superpixels, computing, through a machine learning algorithm, the probability of each pair being in one of three predetermined classes; for each superpixel in the plurality of superpixels, computing a probability of the superpixel being in the region of interest; generating an edge map from computing each pixel's value based on the computed superpixel probabilities; applying an extended Hough transform to the generated edge map to generate a Hough parameter counting space; determining the optimal quadrilateral in the Hough parameter counting space by excluding false positive edges; and designating the region of interest as being within the boundary of the determined optimal quadrilateral.

Abstract: A self-contained UAV sensor payload and on-board or off-board hardware and software for precision agriculture. The invention combines multiple cameras and navigation sensors to create a system for automatically collecting, geo-referencing, and stitching red, green, blue, and near infrared imagery and derived vegetation indices. The invention is able to produce all of these quantities in a single flight. The tight integration with integrated navigation sensors eliminates the need for integration with external sensors or avionics hardware and enables innovative solutions to image processing and analysis which greatly improve accuracy, processing speed, and reliability over alternative approaches.

Abstract: According to an embodiment, a biological component estimating apparatus includes a first acquiring unit and a first estimating unit. The first acquiring unit acquires a scattering coefficient distribution image having each pixel specified with a scattering coefficient of a measurement target region of a biological body for light including a wavelength range in a near infrared range. The first estimating unit estimates an amount of change in a biological component based on the scattering coefficient distribution image.

Abstract: Detection and identification a field's boundaries is performed in a workflow based on processing images of the field captured at different times, relative to a defined seed point. Images are clipped to align with the seed point and a bounding box around the seed point, and a mask is built by extracting edges of the field from the images. The workflow floods an area around the seed point that has pixels of a similar color, using the mask as an initial boundary. The flooded area is compared to threshold parameter values, which are tuned to refine the identified boundary. Flooded areas in multiple images are combined, and a boundary is built based on the combined flooded set. Manual, interactive tuning of floodfill areas allows for a separate boundary detection and identification workflow or for refinement of the automatic boundary detection workflow.

Abstract: A method for use with a stream of images defining a video. The method includes the steps of periodically conducting a face finding operation on an image in the stream. In respect to the last image in the stream preceding the image in which one or more faces was found, a tracker based upon wavelet decomposition is used to find a face for each face found in the last image for which no counterpart was found in the image.

Abstract: The present invention relates to an ultrasound imaging system (10) for inspecting an object (97) in a volume (40). The ultrasound imaging system comprises an image processor (36) configured to conduct a segmentation (80) of the object (97) simultaneously out of three-dimensional ultrasound mage data (62) and contrast-enhanced three-dimensional ultrasound image data (60). In particular, this may be done by minimizing an energy tem taking into account both the normal three-dimensional ultrasound image data and the contrast-enhanced three-dimensional image data. By this, the normal three-dimensional ultrasound image data and the contrast-enhanced three-dimensional image data may even be registered during segmentation. Hence, this invention allows a more precise quantification of one organ in two different modalities as well as the registration of two images for simultaneous visualization.