Abstract: In one aspect, a system for receiving communications while a user operates a motor vehicle is provided. The system may include (1) a BLUETOOTH interface configured to establish a connection to a BLUETOOTH device associated with the motor vehicle, (2) a wireless communication interface configured to receive a wireless communication from a remote device, and (3) a processor coupled to the wireless communication interface and the BLUETOOTH interface, and configured to: (a) determine the user is operating the motor vehicle based upon the connection to the BLUETOOTH device, and (b) suppress a notification of the user of receipt of the wireless communication while the user is operating the motor vehicle.

Abstract: Apparatus with I/O modules such as a networked security camera with a plurality of wireless connections to continue to use at least one network connection is presented. The apparatus, comprising a plurality of RF units, a plurality of SIM card interfaces, at least one processing unit, at least one non-transitory computer readable storage medium and at least on input/output module, is able to continue sending and receiving data through one or more wireless networks using a plurality of RF units. Further, when more bandwidth and/or higher reliability is required, the apparatus aggregates data connections established with different wireless networks.

Abstract: In one aspect, the present disclosure implements a method that determines whether a submitted image satisfies a geographic constraint which includes defining a rule that establishes a geographic restriction on the submitted image, accessing a geo-code associated with the submitted image, determining whether the geo-code indicates that the submitted image was taken at a location that violates the geographic restriction defined in the rule, and if a determination is made that the submitted image was taken at a location that violates the geographic restriction defined in the rule, eliminating the submitted image from being considered a valid entry in the contest.

Abstract: A sensor may be configured to determine how many people that have entered or exited a space. The sensor may comprise a pyroelectric infrared (PIR) detection circuit capable of generating different output signal patterns in response to a person entering or exiting the space. The sensor may determine whether the person has entered or exited the space based on the output signal pattern. The sensor may include a thermopile array, a radar detection circuit, or a visible light sensing circuit. The thermopile array, radar detection circuit, or visible light sensing circuit may be capable of detecting a person's location and/or movements within an area monitored by the sensor and determining, based on the detected movements, whether the person has entered or left the space. An occupant count of the space may then be determined accordingly by the sensor or by a system controller.

Abstract: Offline task-based feature processing for aerial vehicles is provided. A system can extract features from a world model generated using sensor information captured by sensors mounted on an aerial vehicle. The system generates a label for each of the features and identifies identify processing levels based on the features. The system selects a processing level for each feature of a subset of features based on a task performed by the aerial vehicle and the label associated with the feature. The system generates one or more processed features by applying the processing level to a respective feature of the subset of the plurality of features. The system presents the one or more processed features on a display device of the aerial vehicle.

Abstract: A method for classifying input data includes receiving the input data that describe an object, wherein the input data corresponds to plural classes; associating the input data with voxels that describe the object; calculating a real-number sequence X(n), which is associated with a measured parameter P that describes the object; quantizing the real-number sequence X(n) to generate a finite set sequence Q(n), where n describes a number of levels; generating a voxel-based weight matrix for each class of the input data; and calculating a score S for each class of the plural classes, based on a corresponding voxel-based weight matrix. The score S is a number that indicates a likelihood that the input data associated with a given sample belongs to a class of the plural classes.

Abstract: In a control device (10), a determination unit (11) determines “a plurality of collision-occurrence-estimated devices” for which “transmission collision” is estimated to occur due to overlapping of transmission schedule timings among the plurality of communication devices. A transmission control unit (12) executes transmission control of transmitting, to each of some of the plurality of collision-occurrence-estimated devices, each of a plurality of “timing distribution control signals” for distributing transmission timings of the plurality of collision-occurrence-estimated devices determined by the determination unit (11).

Abstract: One embodiment is a navigation system for an aircraft including a positioning system to generate information related to a position of the aircraft, a group of cameras mounted to a body of the aircraft, each camera of the group of cameras to simultaneously capture images of a portion of an environment that surrounds the aircraft, and a processing component coupled to the positioning system and the group of cameras, the processing component to determine a current position of the aircraft based on the information related to the position of the aircraft and the images.

Abstract: A data subscription system provides emergency event data to receiving systems. The data subscription system includes an event emitter and a distribution module. The event emitter receives event data describing an event in a computer-aided dispatch (CAD) system; the event is related to an emergency call. The event emitter identifies a subscription subscribed to the event based on a tenant identifier identifying a CAD tenant associated with the event, and adds a data message with the event data to a queue for the identified subscription. The distribution module retrieves the data message from the queue, transforms the data message based on one or more filtering or formatting rules, and transmits the transformed data message to a receiving system associated with the subscription.

Abstract: In some embodiments, systems and methods are provided to recognize retail products, comprising: a model training system configured to: identify a customer; access an associated customer profile; access and apply a set of filtering rules to a product database based on customer data; generate a listing of products specific to the customer; access and apply a model training set of rules to train a machine learning model based on the listing of products and corresponding image data for each of the products in the listing of products; and communicate the trained model to the portable user device associated with first customer.

Abstract: Systems and methods for enhanced object detection for autonomous vehicles based on field of view. An example method includes obtaining an image from an image sensor of one or more image sensors positioned about a vehicle. A field of view for the image is determined, with the field of view being associated with a vanishing line. A crop portion corresponding to the field of view is generated from the image, with a remaining portion of the image being downsampled. Information associated with detected objects depicted in the image is outputted based on a convolutional neural network, with detecting objects being based on performing a forward pass through the convolutional neural network of the crop portion and the remaining portion.

Abstract: An imaging system includes a sensor configured to receive imaging data, where the imaging data comprises k-space data from a magnetic resonance imaging (MRI) scan of a patient. The imaging system also includes a processor operatively coupled to the sensor and configured to identify a degree of interaction between measured points of the k-space data located at a radius from a center of k-space. The processor is also configured to determine, based at least in part on the degree of interaction between the measured points, density weights for a density compensation filter. The processor is also configured to apply the density compensation filter to the k-space data to generate filtered k-space data. The processor is further configured to generate an MRI image of the patient based at least in part on the filtered k-space data.

Abstract: An example driver assistance system includes an object detection (OD) network, a semantic segmentation network, a processor, and a memory. In an example method, an image is received and stored in the memory. An object detection (OD) polygon is generated for each object detected in the image, and each OD polygon encompasses at least a portion of the corresponding object detected in the image. A region of interest (ROI) is associated with each OD polygon. Such method may further comprise generating a mask for each ROI, each mask configured as a bitmap approximating a size of the corresponding ROI; generating at least one boundary polygon for each mask based on the corresponding mask, each boundary polygon having multiple vertices and enclosing the corresponding mask; and reducing a number of vertices of the boundary polygons based on a comparison between points of the boundary polygons and respective points on the bitmaps.

Abstract: Systems and methods for generating and processing images captured while inspecting above-ground pipelines are disclosed. Embodiments may include a robotic crawler or other devices which carry imaging equipment and traverse a target pipe which are configured to capture image data simultaneously from a plurality of angles. Such systems may substantially reduce and in some cases overcome the need to take multiple traversals of a pipeline under inspection. Embodiments may also be directed toward control systems for such devices as well as image processing systems which process the multiple image sets to produce a composite imaging result.

Abstract: To enable a high quality HDR video communication, which can work by sending corresponding LDR images potentially via established LDR video communication technologies, which works well in practical situations, applicant has invented a HDR video decoder (600, 1100) arranged to calculate a HDR image (Im_RHDR) based on applying to a received 100 nit standard dynamic range image (Im_RLDR) a set of luminance transformation functions, the functions comprising at least a coarse luminance mapping (FC), which is applied by a dynamic range optimizer (603), and a mapping of the darkest value (0) of an intermediate luma (Y?HPS), being output of the dynamic range optimizer, to a received black offset value (Bk_off) by a range stretcher (604), the video decoder comprising a gain limiter (611, 1105) arranged to apply an alternate luminance transformation function to calculate a subset (502) of the darkest luminances of the HDR image, from corresponding darkest lumas (Y?_in) of the standard dynamic range image.

Abstract: Certain aspects of the present disclosure provide techniques for communicating, by a user equipment (UE), over multiple slices. A method that may be performed by the UE includes receiving, by a modem, from an operating system (OS), a request for route identifier, the request for route identifier comprising a traffic descriptor corresponding to a first application from which the request for route identifier originated. The method further includes transmitting a route identifier to the OS, the route identifier generated by the modem based on a routing policy that provides mapping between the traffic descriptor and a network route. The method further includes receiving, by the modem, a start network request comprising the route identifier. The method further includes establishing, in response to the start network request, a network connection via the network route.

Abstract: A system for an attention-based perception includes a camera device configured to provide an image of an operating environment of a vehicle. The system further includes a computerized device monitoring the image, analyzing sensor data to identify a feature in the image as corresponding to an object in the operating environment and assign a score for the feature based upon an identification, a location, or a behavior of the object. The computerized device is further operable to define candidate regions of interest upon the image, correlate the score for the feature to the candidate regions of interest to accrue a total region score, select some of the candidate regions for analysis based upon the total region scores, and analyze the portion of the candidate regions to generate a path of travel output. The system further includes a device controlling the vehicle based upon the output.

Abstract: Methods for improving compliance with regulations pertaining to vehicle driving records are disclosed. One or more digital images from a camera mounted in a vehicle are received. Based on a determination that the vehicle has hours of service that have not been assigned to a driver, a subset of the one or more digital images corresponding to the hours of service are identified based on the timestamps. The subset of the one or more digital images are processed to identify a correspondence between a face of a person included in the one or more digital images and a face of a known person. Based on the correspondence transgressing a threshold level of correspondence, a user interface is generated for presentation on a device. The user interface includes an interactive user interface element for accepting a recommendation to assign the known person as the driver for the unassigned hours of service.

Abstract: A document processing apparatus includes a processor configured to extract an image area, in which an image is disposed, from a plurality of documents to be processed, perform an image recognition process on the image area, compare information on the image of the image area for each document, the information being obtained by performing the image recognition process, and decide a difference for the documents based on a result of comparison of the information on the image and a decision rule for the documents.

Abstract: Segmentation first breaks the images into segments or regions, with the segments of the region having text or symbols. The segmented image is separately applied to two different CNN-based models. Each model produces text boxes where potential text might exist. Then, a selective NMS algorithm is applied to the output of each model to produce a final group of text regions. These text regions are analyzed and actions are taken.