Abstract: According to some embodiments, a method includes accessing a live track list stored in memory. Each track of the live track list includes a coordinate of an object of interest captured by a physical sensor located within a physical environment and a unique ID. The method further includes comparing a new track to the live track list in order to determine if the new track matches any existing tracks. The method further includes merging the new track with the particular existing track when the new track matches a particular track in the live track list. The method further includes adding the new track to the live track list when the new track does not match any existing tracks. The method further includes displaying a virtual 3D environment that corresponds to the physical environment. The method further includes projecting virtual objects into the virtual 3D environment using the live track list.

Abstract: Apparatus and methods for applying motion blur to overcapture content. In one embodiment, the motion blur is applied by selecting a number of frames of the captured image content for application of motion blur; selecting a plurality of pixel locations within the number of frames of the captured image content for the application of motion blur; applying motion blur to the captured image content in accordance with the selected number of frames and the selected plurality of pixel locations; and outputting the captured image content with the applied motion blur. In some implementations, motion blur is applied via implementation of a virtualized neutral density filter. Computerized devices and computer-readable apparatus for the application of motion blur are also disclosed.

Abstract: Systems, methods, and computer program products for access-related safety determinations are provided. An example method includes receiving first image data of a field of view of a first imaging device that includes an access location and determining an access condition of the access location based upon the first image data. In response to an attempt to access the access location by a first user, the method includes receiving second image data of a field of view of a second imaging device that includes the first user upon which to perform a safety determination. The method further includes generating a safety parameter for the first user that is indicative of a presence and a positioning of a safety device of the first user, comparing the safety parameter with a validation threshold, and generating an alert signal in an instance in which the safety parameter fails to satisfy the validation threshold.

Abstract: A system may be configured to reliably identify, track, and collect data on a person of interest. In some aspects, the system may detect a facial representation within an image, generate a bounding box corresponding to the facial representation, determine an enhanced facial representation based at least in part on the bounding box and an image enhancement pipeline, and extract a plurality of facial features from the enhanced facial representation. Further, the system may determine quality information based on the plurality of facial features, determine that the quality information is greater than a threshold, and store the plurality of facial features in a data structure. In some aspects, the facial features may be used to identify red shoppers and green shoppers in a controlled environment.

Abstract: The embodiment of the present invention discloses an anti-drowning safety alarm method and device for swimming pools. Acquiring images taken by multiple cameras; inputting the images into a target detection model to detect human bodies and heads, so as to obtain human body target detection boxes and human head target detection boxes; calculating the relationship between the human heads and the human bodies according to these boxes; performing multi-camera fusion on the human body target detection boxes and the human head target detection boxes to obtain the human body boxes and head boxes; determining the relative position relationship between the human bodies or the human heads and the water surface; calculating the correlation between the bounding box sequence at the current moment and that at the previous moment to obtain the human tracking trajectory; updating the state database; generating alarm information according to the state database.

Abstract: An encoder system may include an analyzer that analyzes a current image area in an input video to select a transform. A selectable residue transformer, controlled by the analyzer, may perform the selectable transform on a residue image generated from the current image area and a predicted current image area, to generate a transformed residue image. An encoder may encode the transformed residue image to generate output data. The analyzer controls the encoder to encode information to identify the selectable transform and to indicate that the selectable transform for the current image area is different from a transform of a previous image area of the input video. A decoder system may include components appropriate for decoding the output data from the encoder system.

Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.

Abstract: Systems, apparatus, articles of manufacture and methods for face augmentation in video are disclosed. An example apparatus includes executable code to detect a face of a subject in the video, detect a gender of the subject based on the face, detect a skin tone of the subject based on the face, apply a first process to smooth skin on the face in the video, apply a second process to change the skin tone of the face, apply a third process to slim the face, apply a fourth process to adjust a size of eyes on the face, and apply a fifth process to remove an eye bag from the face. One or more of the first process, the second process, the third process, the fourth process, or the fifth process adjustable based on one or more of the gender or an age. The example apparatus also includes one or more processors to generate modified video with beauty effects, the beauty effects based on one or more of the first process, the second process, the third process, the fourth process, or the fifth process.

Abstract: Methods and apparatus are provided for optical coherence metrology or tomography across an extended area of an eye with improved registration. At least two optical coherence tomograms are acquired, with each tomogram containing data from regions of an anterior surface of the eye that are at least partially overlapping, and data from one or more deeper structures such as the retina or the anterior or posterior lens surfaces. The tomograms are then processed to register the data from the overlapping portions of the anterior surface regions, thereby registering the data from the deeper structures. In certain embodiments the reference arm of the apparatus comprises a compound reflector having at least two axially separated reflective surfaces for applying differential delays to different portions of the reference beam. The depth of field of the apparatus is thereby extended to enable measurement of eye length.

Abstract: A system includes a memory and a processing device operatively coupled to the memory. The processing device generates one or more parametric functions associated with tooth color based on color data for teeth from a first image, wherein each of the one or more parametric functions comprises a first variable for a first image axis and a second variable for a second image axis. The processing device receives image data comprising new contours of the mouth, wherein one or more of the teeth have a different position in the image data than in the first image. The processing device generates a new image based on the image data and the one or more parametric functions, wherein a shape of the teeth is based on the image data and a color of the teeth is based on applying the one or more parametric functions to the image data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for state and event monitoring. In some implementations, images captured by a camera are obtained, the images depicting an area of a property. Two or more images of the images are provided to a machine learning model. An output of the machine learning model is obtained, the output corresponding to the two or more images. One or more potential states of the area of the property are determined using the output of the machine learning model, each state of the one or more potential states corresponding to an image in the two or more images. An action is performed based on the one or more potential states.

Abstract: Ping-based imaging systems may be used for tracking motion of hard or soft objects within an imaged medium. Motion detection and motion tracking may be performed by defining fingerprint points and tracking the position of each fingerprint point based on the echoes of multiple transmitted pings.

Abstract: A system and method for determining car to lane distance is provided. In one aspect, the system includes a camera configured to generate an image, a processor, and a computer-readable memory. The processor is configured to receive the image from the camera, generate a wheel segmentation map representative of one or more wheels detected in the image, and generate a lane segmentation map representative of one or more lanes detected in the image. For at least one of the wheels in the wheel segmentation map, the processor is also configured to determine a distance between the wheel and at least one nearby lane in the lane segmentation map. The processor is further configured to determine a distance between a vehicle in the image and the lane based on the distance between the wheel and the lane.

Abstract: A system and method for visually automated interface integration that includes collecting image data; detecting a device interface source in the image data; processing the image data associated with the device interface source into an extracted interface representation; and exposing at least one access interface to the extracted interface representation.

Abstract: Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.

Abstract: Provided are a product purchase support system (100), a product purchase support device (10), and a POS terminal device (20) that improve the efficiency of checkout processing for product sales and enhance the convenience of customers when purchasing a product. The product purchase support system (100) according to the present invention includes the product purchase support device (10) including a depth camera (12) and a first display device (13), and a POS terminal device (20) that performs checkout processing for a product. When the product purchase support device (10) detects a product selection motion of selecting a product by a customer, it identifies a product selected by the customer and generates product information related to this product, and displays the product information on the first display device (13). Further, the product purchase support device (10) outputs the product information to the POS terminal device (20).

Abstract: A surveillance information generation apparatus (2000) includes a first surveillance image acquisition unit (2020), a second surveillance image acquisition unit (2040), and a generation unit (2060). The first surveillance image acquisition unit (2020) acquires a first surveillance image (12) generated by a fixed camera (10). The second surveillance image acquisition unit (2040) acquires a second surveillance image (22) generated by a moving camera (20). The generation unit (2060) generates surveillance information (30) relating to object surveillance, using the first surveillance image (12) and first surveillance information (14).

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for a secure edge platform that uses image classification machine learning models. An edge platform can include at least one camera and can identify image classification models that generate classification output data from image data generated by the cameras. The edge platform can receive image data generated by the camera, and provide the image data to the models. In response to providing the image data classification models, the edge platform can receive classification output data. In response to receiving the classification output data from the image classification models, the edge platform can generate augmentation data that is associated with the image data, then transmit detection data to a central server platform. The detection data can include (i) the classification output data and (ii) the augmentation data associated with the image data. Data can be made recordable, reportable, searchable, and alarmable.

Abstract: Described herein are techniques that may be used to provide for automatic obfuscation of one or more objects in a media data. Such techniques may comprise receiving, from a data source, a media data comprising a depiction of a number of objects, identifying, within the received media data, a set of objects associated with the media data, and storing an indication of one or more locations of the objects in the set of objects within the media data with respect to time. Upon receiving a request for the media data, such techniques may further comprise updating the media data by applying an obfuscation effect to the one or more locations with respect to time, and providing the updated media data in response to the request.

Abstract: Implementations generally perform pose reconstruction by tracking for video analysis. In some implementations, a method includes obtaining a plurality of videos of at least one subject performing at least one action in an environment. The method further includes tracking the at least one subject across at least two cameras. The method further includes reconstructing a 3-dimensional (3D) model of the at least one subject based on the plurality of videos and the tracking of the at least one subject.