Abstract: Systems and techniques for optimizing deployment of a camera scanning system in an environment for item identification are described. An example technique involves obtaining a first set of parameters of the camera scanning system and obtaining a second set of parameters of the environment. A third set of parameters of a predicted scan volume of the camera scanning system are determined based on the first set of parameters and the second set of parameters. At least one of the first or second sets of parameters is modified upon determining that the predicted scan volume satisfies a first predetermined condition. An indication of at least one of the first, second, or third sets of parameters is transmitted upon determining that the predicted scan volume satisfies a second predetermined condition.

Abstract: An object position region detection unit of an object detection device detects a position region of an object included in an input image on the basis of a first class definition in which a plurality of classes is defined in advance. A class identification unit identifies a class out of a plurality of classes to which the object belongs on the basis of the first class definition. An object detection result output unit outputs class information of the object as a detection result of the object on the basis of a second class definition in which a plurality of classes is defined in advance, the second class definition associated with the first class definition. The number of classes defined in the second class definition is smaller than the number of classes defined in the first class definition.

Abstract: Systems and methods for detecting, geolocating, assessing, and/or inventorying infrastructure assets. In some embodiments, a plurality of images captured by a moving camera may be used to generate a point cloud. A plurality of points corresponding to a pavement surface may be identified from the point cloud. The plurality of points may be used to generate at least one synthetic image of the pavement surface, the at least one synthetic image having at least one selected camera pose. The at least one synthetic image may be used to assess at least one condition of the pavement surface.

Abstract: Systems and methods for anatomical structure segmentation in medical images using multiple anatomical structures, instructions and segmentation models.

Abstract: A computer-implemented method includes: accessing a first database holding information encoding a set of labels that specify a condition of at least one of: a surface pipe, or an underground enclosure that runs at a plurality of depth locations; accessing a second database holding a plurality of inspection logs that record measurement data of the surface pipe or underground enclosure; based on, at least in part, the labeling information and the plurality of inspection logs, training a deep learning model configured to classify, into the set of labels, the condition of the surface pipe or underground enclosure when presented with the inspection logs; applying the deep learning model to one or more newly received inspection logs containing measurement data of a new surface pipe or a new underground enclosure; and subsequently classifying, into the set of labels, the condition of the new surface pipe or the new underground enclosure.

Abstract: A device may receive a target document. The device may segment the target document into multiple segments. The device may determine, for each segment of the multiple segments, a set of color parameters for a corresponding set of pixels included in that segment. The device may determine, for each segment of the multiple segments, an average color parameter for that segment based on the set of color parameters for the corresponding set of pixels included in that segment. The device may generate a target color profile for the target document based on determining the average color parameter for each segment. The device may compare the target color profile and a model color profile associated with classifying the target document. The device may classify the target document based on comparing the target color profile and the model color profile.

Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps.

Abstract: Batch processing footage to perform one or more post-production tasks in the field of moving images. Footage is processed and tagged with metadata. The metadata is used to identify the same digital elements across different portions of the footage, enabling post-production tasks to be performed across the different portions simultaneously.

Abstract: The image coding method includes: determining a context in a current block in the image, from among a plurality of contexts; and performing arithmetic coding on the control parameter for the current block to generate a bitstream corresponding to the current block, wherein in the determining: the context is determined under a condition that control parameters of neighboring blocks of the current block are used, when the signal type is a first type, the neighboring blocks being a left block and an upper block of the current block; and the context is determined under a condition that the control parameter of the upper block is not used, when the signal type is a second type, and the second type is (i) “merge_flag”, (ii) “ref_idx_l0” or “ref_idx_l1”, (iii) “inter_pred_flag”, (iv) “mvd_l0” or “mvd_l1”, (v) “no_residual_data_flag”, (vi) “intra_chroma_pred_mode”, (vii) “cbf_luma”, and (viii) “cbf_cb” or “cbf_cr”.

Abstract: Provided in embodiments of the present invention are a method and a system for generating a magnetic resonance image and a computer-readable storage medium. The method comprises: acquiring a plurality of quantitative maps; synthesizing a first weighted image on the basis of the plurality of quantitative maps; and converting the first weighted image into a corresponding second weighted image on the basis of a trained deep learning network.

Abstract: An image filtering arrangement comprising a controller configured to receive an image data file; propose zero or more regions of interest for the image data file; and to select adaptive filtering for at least one of the proposed zero or more regions of interest and apply the selected adaptive filtering to the at least one of the proposed zero or more regions of interest.

Abstract: According to an embodiment, an encoding device includes an index setting unit and an encoding unit. The index setting unit generates a common index in which reference indices of one or more reference images included in a first index and a second index are sorted in a combination so as not to include a same reference image in accordance with a predetermined scanning order. The first index representing a combination of the one or more reference images referred to by a first reference image. The second index representing a combination of the one or more reference images referred to by a second reference image. The encoding unit encodes the common index.

Abstract: A three-dimensional data encoding method includes: performing motion compensation on a plurality of encoded point clouds; merging the plurality of encoded point clouds that have been motion compensated to generate a reference point cloud; generating an N-ary tree structure of a current point cloud, where N is an integer greater than or equal to 2; and encoding the N-ary tree structure of the current point cloud using the reference point cloud.

Abstract: A computing system that can receive an object search request from a user indicating a request to search for a specific object in an area traversed by one or more autonomous vehicle. The object search request can include a set of physical characteristics of the specific object. The computing system can then transmit a signal to an autonomous vehicle indicating a request for the autonomous vehicle to search for the specific object. The signal can cause the autonomous vehicle to transmit an image, selected based on a physical characteristic of the object, to the computing system. The computing system can then generate a score indicative of a difference between one or more physical characteristic of the object in the image and the specific object. The computing system can then selectively transmit the image to a mobile device operated by the user based on the score.

Abstract: Disclosed are a method and an apparatus for image encoding/decoding. The method for image decoding includes comparing whether a size of a current transform block and a size of a smallest transform block (smallest transform unit (STU)) are the same as each other, and decoding information indicating whether transformation is performed on the current transform block and determining whether to perform inverse transformation on the current transform block based on the decoded information indicating whether the transformation is performed when the size of the current transform block and the size of a smallest transform block are the same as each other.

Abstract: The present invention provides an image encoding method and an image decoding method. The image decoding method, according to the present invention, comprises the steps of: decoding information associated with a clipping range of a current block; and performing sample adaptive offset (SAO) filtering on the basis of the information associated with the clipping range, wherein the information associated with the clipping range may include information on the maximum and minimum values of a pixel value included in the current block.

Abstract: Disclosed herein is a methodology for refining novel-class features in a few-shot learning scenario by fine-tuning the feature extractor by reducing both class-agnostic biases and class-specific biases. A distribution calibration module is used to reduce the class-agnostic bias by normalizing the overall feature distribution for novel classes and further reshaping the feature manifold for fast adaptation during fine-tuning. Selected sampling is used to reduce class-specific bias by augmenting more data for better estimation.

Abstract: A method and system for calibrating a digital imaging apparatus by placing an object of known dimensions in a camera field of view, creating a digital image of the object, measuring the object dimensions in the digital image, creating a mathematical relationship between the object dimensions and the measured object dimensions in the digital image, creating n additional digital images each image having a distinct camera zoom level; measuring the position of a plurality of locations on the object for the n additional images, calculating a value for said locations in the n additional digital images, linking corresponding locations in the n additional images to create a calibration metric for a plurality of zoom values and calibrating any lens by comparing the zoom position of the lens in a camera with the calibration value. The present invention reduces calibration time and generates images which can be quickly verified by the operator.

Abstract: According to an embodiment, an image coding method is for coding an image including a luminance component and color difference components. The method includes acquiring a reference image; and generating a predicted image by interpolating the luminance component and the color difference components in the reference image according to a motion vector. If a size of a block, which is designated as a unit of the interpolation, is equal to or smaller than a predetermined first threshold value, the generating includes inhibiting a bi-directional prediction, and performing only a uni-directional prediction to generate the predicted image according to the motion vector.

Abstract: An image processing device assists searching for image data in an image viewing service, and includes: a recognizer that recognizes a part representing a target object from the image data; an extractor that extracts a color used in pixels in the part recognized; a determiner that determines a color that is not extracted from the part but is likely to be used in searching by a service user, based on a search tendency in searching by the service user; and an adder that creates a first tag indicating the color extracted by the extractor and a second tag indicating the color determined by the determiner and adds the first tag and the second tag as search tags to the image data.