Abstract: A method for human-object interaction detection includes receiving an image. A set of features are extracted from multiple positions of the image. One or more human-object pairs may be predicted based on the extracted set of features. A human-object interaction may be determined based on a set of candidate interactions and the predicted human-object pairs.

Abstract: A system and method of performing high precision anatomical measurements of non-visible aspects of features of living organisms that include a visible contoured shape on the anatomical region of the living organism is disclosed. The system and method include an imager configured to take a series of images of an anatomical region of a living organism, such as a human patient in a clinic, doctor's office, or hospital. The system and method create a three-dimensional digital anatomical model of the exterior or visible part of the anatomical region that includes a target feature, such as a breast, nose, foot, or tumor. The target feature within the three-dimensional digital model is then isolated and manipulated to find measurements of non-visible aspects of the feature, such as mass, distances between visible points which pass through invisible tissues, e.g., depth and base width, volume, area, and surface angle measurements of the feature.

Abstract: In a setting mode, a processor stores in a memory a reference image for pattern search, measurement location information indicating a plurality of measurement locations, and imaging setting information indicating at which magnification imaging is performed. In a measurement mode, the processor controls an imaging section, acquires a target image for pattern search, executes a pattern search on the target image using the reference image, specifies a plurality of imaging positions for imaging each of the plurality of measurement locations based on the measurement location information and a result of the pattern search, causes the imaging section to perform imaging at a magnification set for each measurement location, and measures a dimension of the measurement location.

Abstract: A target object detection model is provided. The target object detection model includes a YOLOv3-Tiny model. Through the target object detection model, low-level information in the YOLOv3-Tiny sub-model can be merged with high-level information therein, so as to fuse the low-level information and the high-level information. Since the low-level information can be further used, the comprehensiveness of target detection is effectively improved, and the detection effect of small targets is improved.

Abstract: A method for detecting wheels of a vehicle on a road comprises directing a vehicle classification sensor onto a section of the road and recording a 3D representation of the vehicle, directing a camera onto the section and recording a source 2D image, determining a bounding box circumscribing the 3D representation, a side and four corner points of said bounding box side, identifying corner points in a source 2D image plane, defining four corner points of a rectangle in a destination 2D image plane, calculating a projective transformation between the source corner image points and the destination corner image points, transforming source 2D image pixels to destination 2D image pixels of a first destination 2D image, and detecting the wheels using the destination 2D image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for eye gesture recognition. In one aspect, a method includes obtaining an electrical signal that represents a measurement, by a photodetector, of an optical signal reflected from an eye and determining a depth map of the eye based on phase differences between the electrical signal generated by the photodetector and a reference signal. Further, the method includes determining gaze information that represents a gaze of the eye based on the depth map and providing output data representing the gaze information.

Abstract: One example provides a computing system comprising a depth sensor comprising a plurality of pixels, and a storage machine holding instructions executable by a logic machine to, for each pixel, make K phase measurements to form a set of noisy phase measurements, determine a location at which a projection line that passes through the set of noisy phase measurements in a K-dimensional phase space passes through a lower dimensional plane, the projection line being parallel to a noise free phase evolution line, compare the location to a plurality of independent terms of a predetermined matrix of points in the lower dimensional plane, locate a corresponding set of noiseless phase orders by using a selected set of independent terms to reference a look-up table, determine a distance value for the pixel based upon the corresponding set of noiseless phase orders, and output the distance value for the pixel.

Abstract: This invention provides a system and method for using an area scan sensor of a vision system, in conjunction with an encoder or other knowledge of motion, to capture an accurate measurement of an object larger than a single field of view (FOV) of the sensor. It identifies features/edges of the object, which are tracked from image to image, thereby providing a lightweight way to process the overall extents of the object for dimensioning purposes. Logic automatically determines if the object is longer than the FOV, and thereby causes a sequence of image acquisition snapshots to occur while the moving/conveyed object remains within the FOV until the object is no longer present in the FOV. At that point, acquisition ceases and the individual images are combined as segments in an overall image. These images can be processed to derive overall dimensions of the object based on input application details.

Abstract: Discussed generally are techniques for managing operation of programs in a sequential order. A method can include receiving a query for an image, the query indicating characteristics of the image, selecting a chain of algorithms configured to identify the image based on the characteristics, operating an algorithm of the selected chain of algorithms that operate in increased fidelity order on an input to produce a first result, operating a ground truth algorithm on the input to generate a second result, comparing the first and second results to determine a probability of correctness (Pc) and confidence interval (CI) for the algorithm, and altering the chain of algorithms based on the determined Pc and CI.

Abstract: The present disclosure discloses an unsupervised domain adaptation method, a device, a system and a storage medium of semantic segmentation based on uniform clustering; first, a prototype-based source domain uniform clustering loss and an empirical prototype-based target domain uniform clustering loss are established, to reduce intra-class differences of pixels responding to the same category; meanwhile, the pixels with similar structures but different classes are driven away from each other, wherein they tend to be evenly distributed, increasing the inter-class distance and overcoming the problem that the category boundaries are unclear during the domain adaptation process; next, the prototype-based source domain uniform clustering loss and the empirical prototype-based target domain uniform clustering loss are integrated into an adversarial training framework, which reduces the domain difference between the source domain and the target domain, thus improving the accuracy of semantic segmentation.

Abstract: A method for generating a super resolution image may comprise up-scaling an input low resolution image; determining a directivity for each patch included in the up-scaled image; selecting an orientation-specified neural network or an orientation-non-specified neural network according to the directivity of the patch; applying the selected neural network to the patch; and obtaining a super resolution image by combining one or more patches output from the orientation-specified neural network and the orientation-non-specified neural network.

Abstract: In some implementations, a device may receive an image that depicts an environment associated with a vehicle. The device may partition the image into a plurality of subsections. The device may analyze the plurality of subsections to determine respective subsection information, wherein subsection information, for an individual subsection, indicates: a probability score that the subsection includes a line segment associated with an object class, a position of a representative point of the line segment, and a direction of the line segment. The device may identify, based on the respective subsection information of the plurality of subsections, a line associated with the object class that is associated with a set of subsections of the plurality of subsections. The device may perform one or more actions based on identifying the line associated with the object class.

Abstract: A system, apparatus, method and computer program product are provided for determining a mobile device integrity status. Images of a mobile device captured by the mobile device and using a reflective surface are processed with various trained models, such as neural networks, to verify authenticity, detect damage, and to detect occlusions. A mask may be generated to enable identification of concave occlusions or blocked corners of an object, such as a mobile device, in an image. Images of the front and/or rear of a mobile device may be processed to determine the mobile device integrity status such as verified, not verified, or inconclusive. A user may be prompted to remove covers, remove occlusions, and/or move the mobile device closer to the reflective surface. A real-time response relating to the mobile device integrity status may be provided. The trained models may be trained to improve the accuracy of the mobile device integrity status.

Abstract: The invention relates to reconstructing a synthetic dense super-resolution image from at least one low-information-content image, for example from a sequence of diffraction-limited images acquired by single molecule localization microscopy. After having obtained such a sequence of diffraction-limited images, a sparse localization image is reconstructed from the obtained sequence of diffraction-limited images according to single molecule localization microscopy image processing.

Abstract: An information processing apparatus includes a captured image acquisition unit that acquires an image captured by imaging a device including plural markers. A marker image coordinate specification unit specifies a representative coordinate of each marker image from the captured image, and a position and posture derivation unit derives position information and posture information of the device using the representative coordinates of the marker images. The marker image coordinate specification unit specifies a first boundary box surrounding a region within which pixels having a first luminance or more continuously appear, specifies a second boundary box surrounding a region within which pixels having a second luminance or more continuously appear in the first boundary box, the second luminance being higher than the first luminance, and derives a representative coordinate of each marker image based on pixels in the first or second boundary box in response to the number of specified second boundary boxes.

Abstract: A navigation method based on ground texture images, an electronic device and storage medium. The method includes: performing transform domain based image registration on an acquired image of a current frame and an image of a previous frame, and determining a first pose of the image of the current frame; determining whether the image of the current frame meets a preset condition, and if so, inserting the image of the current frame as the key-frame image into a map, and performing loop closure detection and determining a loop key-frame image; performing transform domain based image registration on the image of the current frame and the loop key-frame image, and determining a second pose of the image of the current frame; and determining an accumulated error according to the first pose and the second pose, and correcting the map according to the accumulated error.

Abstract: An approach for improving object detection performance by using bilateral organ information disclosed. The approach comprises introducing a penalty term to an object localization model. The penalty term encourages the model to identify same physical regions (actual same physical location in the patient's body) in multiple images, which create an image of the same organ. The approach includes a sub-component of the model that can output an entity embedding, in additional to the conventional classification and localization prediction. During optimization process, similar entity embedding for the same logical entity are encouraged, and similar entity embedding for different logical entities are discouraged.

Abstract: A three-dimensional data encoding method includes: dividing three-dimensional points included in three-dimensional data into three-dimensional point sub-clouds including a first three-dimensional point sub-cloud and a second three-dimensional point sub-cloud; appending first information indicating a space of the first three-dimensional point sub-cloud to a header of the first three-dimensional point sub-cloud, and appending second information indicating a space of the second three-dimensional point sub-cloud to a header of the second three-dimensional point sub-cloud; and encoding the first three-dimensional point sub-cloud and the second three-dimensional point sub-cloud so that the first three-dimensional point sub-cloud and the second three-dimensional point sub-cloud are decodable independently of each other.

Abstract: Disclosed is a cross-view image optimizing method and apparatus, and a computer equipment and a readable storage medium.

Abstract: A system and method for model-based camera tracking and image occlusion removal for a camera viewing a sports field (or other scene) includes receiving a synthesized data set comprising at least one empty field image of the field, the empty field image with at least one occlusion graphic, and camera parameters corresponding to the empty field image, training a neural network model to estimate the empty field image and the corresponding camera parameters by providing the model with an input training image comprising the empty field image with occlusion graphic, and providing the model with model output targets comprising the empty field image and the corresponding camera parameters as targets for the model, receiving by the neural network model, alive input image comprising a view of the field with live occlusions, and providing by the neural network model, using trained model parameters, estimated live camera parameters or an estimated empty field image associated with the live input image.