Abstract: In a video processing method, a target video is received. Scene description information of a shooting scene in the target video is obtained. The scene description information indicates features of the shooting scene in the target video. A video processing package that corresponds to the shooting scene in the target video is obtained based on the scene description information. The video processing package is configured to add at least one content to the target video. The at least one content is added to the target video based on the video processing package.

Abstract: A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity.

Abstract: Methods, systems, and apparatus, including computer-readable media, are described for performing neural network computations using a system configured to implement a neural network on a hardware circuit. The system includes a host that receives a batch of inputs to a neural network layer. Each of the inputs is stored in a memory location identified by an address. The system identifies one or more duplicate addresses in a listing of addresses for one or more inputs. For each duplicate address: the system generates a unique identifier that identifies the duplicate address in the listing of addresses. The system (i) obtains first inputs from memory locations identified by addresses corresponding to the unique identifiers and (ii) generates an output of the layer from the obtained first inputs.

Abstract: Disclosed is a computing device for generating region information of at least one object included in an image, the computing device including: a memory including computer-executable components; and a processor for executing the computer-executable components stored in the memory, in which the computer-executable components include: a key point heat map generation component for generating, for the image, a key point heat map including key point information of the at least one object; a non-rotating bounding box generation component for generating a non-rotating bounding box based on the generated key point heat map; a rotating bounding box generation component for generating a rotating bounding box by using the non-rotating bounding box; and a final bounding box generation component for representing a region occupied by the at least one object in the image by using at least one of the non-rotating bounding box or the rotating bounding box.

Abstract: A method for detecting the maximum potential presence of a material in an object. The method includes obtaining raw x-ray image data comprising a plurality of pixels for the object from an X-ray scanning device, wherein each pixel of the plurality of pixels has associated therewith an attenuation value and an effective atomic number (Zeff) for the pixel. The method further includes converting, for each pixel having a Zeff value greater than a threshold effective atomic number (Zeff-threshold), the Zeff at the pixel to the Zeff-threshold while applying a correction factor to the attenuation value for the pixel to bring the attenuation value into correspondence with the conversion of the Zeff value for the pixel and determining a maximum potential amount of the material present at each pixel based on the corrected attenuation value at the pixel. This renders material more apparent in visual display.

Abstract: A computer-implemented method for training a generative adversarial network. A generator of the generative adversarial network is configured to generate at least one image based on at least one input value. Training the generative adversarial network includes maximizing a loss function that characterizes a difference between a first image determined by the generator for at least one first input value and a third image determined by the generator for at least one second input value.

Abstract: An own-position estimating device for estimating an own-position of a moving body by matching a feature extracted from an acquired image with a database in which position information and the feature are associated with each other in advance, includes an estimating unit estimating the own-position of the moving body by matching the feature extracted by the extracting unit with the database, and a determination threshold value adjusting unit adjusting a determination threshold value for extracting the feature, in which the determination threshold value adjusting unit acquires the database in a state in which the determination threshold value is adjusted, and adjusts the determination threshold value on the basis of the determination threshold value linked to each of the position information items in the database, and the extracting unit extracts the feature from the image by using the determination threshold value adjusted by the determination threshold value adjusting unit.

Abstract: An article processing apparatus (1) according to an embodiment discharges an article to a downstream apparatus (2) disposed downstream. The article processing apparatus includes: a display (110); a capturing unit (100) that captures a picture including at least part of the downstream apparatus; and a controller (30) that displays, in a case where a processing operation of the article remains stopped in the article processing apparatus, on the display, the picture captured by the capturing unit.

Abstract: A white balance processing method and an electronic device are provided. The method includes: obtaining a first image in response to a first operation, where the first image is an image of a first color space captured by a multispectral color filter array sensor; performing decomposition processing and demosaicing processing on the first image to obtain a second image and a third image; obtaining a color correction matrix according to the second image and the third image, where the color correction matrix represents a pixel change amount of transforming the second image into the third image; inputting the color correction matrix into a white balance model to obtain a white balance parameter; and performing image processing on the first image according to the white balance parameter to obtain a fourth image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for monocular underwater camera biomass estimation. In some implementations, an exemplary method includes obtaining an image of a fish captured by a monocular underwater camera; providing the image of the fish to a depth perception model; obtaining output of the depth perception model indicating a depth-enhanced image of the fish data in the image; determining a biomass value estimate of the fish based on the output; and determining an action based on one or more biomass values estimates including the biomass value estimate of the fish.

Abstract: Novel tools and techniques are provided for implementing automatic document pattern recognition and analysis. In various embodiments, a computing system might receive one or more first documents containing first remittance information. The computing system might analyze the one or more first documents to extract first remittance information from the first document by obtaining one or more historical documents and correlating the one or more first documents to the one or more historical documents. Next, based on the correlation of the one or more first documents to the one or more historical documents, the computing system might determine at least one historical document that correlates to the one or more first documents. Additionally, the computing system might extract the first remittance information from the one or more first documents based on the at least one historical document.

Abstract: A data compression processing system includes: a selection unit configured to select a compression processing setting to be applied to processing target data from among a plurality of compression processing settings; and a compression processing unit configured to compress the processing target data according to the compression processing setting selected by the selection unit. The selection unit is configured to: receive a condition required for compression processing of the processing target data; apply a plurality of compression processing settings applicable to the processing target data to evaluation data to perform compression processing; select, from the plurality of compression processing settings, a setting that satisfies the condition when applied to the processing target data based on a result of the compression processing for the evaluation data; and manage the selected compression processing setting in association with the condition.

Abstract: A vision sensor includes a pixel array comprising pixels arranged in a matrix, an event detection circuit, an event rate controller, and an interface circuit. Each pixel is configured to generate an electrical signal in response to detecting a change in incident light intensity. The event detection circuit detects whether a change in incident light intensity has occurred at any pixels, based on processing electrical signals received from one or more pixels, and generates one or more event signals corresponding to one or more pixels at which a change in intensity of incident light is determined to have occurred. The event rate controller selects a selection of one or more event signals corresponding to a region of interest on the pixel array as one or more output event signals. The interface circuit communicates with an external processor to transmit the one or more output event signals to the external processor.

Abstract: The present application provides a region management and control method, device, apparatus and storage medium. The region management and control method includes: obtaining a current image in a video image and a target region graphic included in the current image; determining whether a person graphic in the current image and the target region graphic meet a predetermined condition; and sending alarm information in response to the person graphic in the current image and the target region graphic meeting the predetermined condition. The predetermined condition includes at least one of: a space condition, a person identity condition, a time condition, a person protection condition, a person number condition or a person body temperature condition.

Abstract: An example device for correcting an image includes a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory, wherein the processor, by executing the one or more instructions, is further configured to obtain an image including a plurality of objects, identify the plurality of objects in the image based on a result of using one or more neural networks, determine a plurality of correction filters respectively corresponding to the plurality of identified objects, and correct the plurality of objects in the image, respectively, by using the plurality of determined correction filters.

Abstract: The following relates to a computer-implemented method and system for transforming a trained artificial intelligence model into a trustworthy artificial intelligence model, by providing the trained artificial intelligence model via a user interface of a webservice platform, providing a validation data set, which is based on training data of the trained artificial intelligence model, generating generic samples by a computing component of the webservice platform based on the validation data set, and transforming the trained artificial intelligence model by optimizing a calibration based on the generic samples. The transformation of the AI model is performed by a computing component of the web service platform. The input, i.e. the trained artificial intelligence model as well as a validation data set, is provided to the computing component via a user interface of the web service platform. Such a user interface is implemented by any applicable frontend.

Abstract: A relative position calculator calculates relative position and attitude of a vehicle based on images captured by an image capturing apparatus on the vehicle. An absolute position calculator extracts a marker from an image captured by the image capturing apparatus, and calculates absolute position and attitude of the vehicle, based on position and attitude of the one extracted marker. A corrector calculates the corrected position and attitude, not using the absolute position and attitude calculated based on the position and attitude of the marker when a difference or ratio of an apparent height and width of the marker in the image is equal to or smaller than a threshold, but using the absolute position and attitude calculated based on the position and attitude of the marker when the difference or ratio is larger than the threshold.

Abstract: The present invention relates to the field of medical monitoring, and in particular non-contact monitoring of one or more physiological parameters in a region of a patient during surgery. Systems, methods, and computer readable media are described for generating a pulsation field and/or a pulsation strength field of a region of interest (ROI) in a patient across a field of view of an image capture device, such as a video camera. The pulsation field and/or the pulsation strength field can be generated from changes in light intensities and/or colors of pixels in a video sequence captured by the image capture device. The pulsation field and/or the pulsation strength field can be combined with indocyanine green (ICG) information regarding ICG dye injected into the patient to identify sites where blood flow has decreased and/or ceased and that are at risk of hypoxia.

Abstract: Apparatus and methods for the stitch zone calculation of a generated projection of a spherical image. In one embodiment, a non-transitory computer-readable apparatus comprising a storage apparatus, the storage apparatus comprising instructions configured to, when executed by a processor apparatus, cause a computerized apparatus to identify a stitch line associated with an equatorial area of a plurality of spherical images; re-orient the plurality of spherical images in accordance with the stitch line; and project the re-oriented plurality of spherical images to a selected image projection type.

Abstract: Provided are a segmentation system and method of an ascending aorta and a coronary artery from coronary CT angiography (CCTA) using a hybrid approach, which relates to a technology of extracting only the shape of the coronary artery and ascending aorta from the input coronary CT medical image.