Abstract: An image recognition apparatus includes a processor including a plurality of arithmetic units; and a memory storing a plurality of data elements, each corresponding to one of candidate regions detected in an image and indicating a location and an evaluation value of the corresponding candidate region. The processor sorts the data elements by calculating in parallel, in reference to evaluation values, indexes each indicating a position of a corresponding one of the data elements in a sorted ordering and transferring in parallel, after the calculation of the indexes, the data elements based on the indexes. The processor selects part of the candidate regions based on the sorted ordering of the data elements.

Abstract: An electronic device and method are disclosed. The electronic device includes a camera, a display, and a processor. The processor implements the method, including capturing an image using a camera of the electronic device for animation of an avatar, the image including at least a part of a face of a user, analyzing, by a processor, a portion of the image including the at least the part of the face to determine whether an entirety of the face is captured within the image, and selecting a primary image or an alternative image for display of the avatar based on the determination, including: displaying the avatar on a display of the electronic device using the alternative image when less than the entirety of the face is captured within the image.

Abstract: Embodiments described herein provide a system for facilitating image sampling for training a target detector. During operation, the system obtains a first image depicting a first target. Here, the continuous part of the first target in the first image is labeled and enclosed in a target bounding box. The system then generates a set of positive image samples from an area of the first image enclosed by the target bounding box. A respective positive image sample includes at least a part of the first target. The system can train the target detector with the set of positive image samples to detect a second target from a second image. The target detector can be an artificial intelligence (AI) model capable of detecting an object.

Abstract: Disclosed herein are methods and systems for detection and discrimination of optical signals from a densely packed substrate. These have broad applications for biomolecule detection near or below the diffraction limit of optical systems, including in improving the efficiency and accuracy of polynucleotide sequencing applications.

Abstract: Disclosed herein are methods and systems for detection and discrimination of optical signals from a densely packed substrate. These have broad applications for biomolecule detection near or below the diffraction limit of optical systems, including in improving the efficiency and accuracy of polynucleotide sequencing applications.

Abstract: An information processing apparatus includes an acquiring unit, a confirming unit, and a controller. The acquiring unit acquires a text recognition result with respect to a first image showing a document and a certainty factor indicating a certainty of the text recognition result. The confirming unit confirms the text recognition result if the certainty factor is above or equal to a threshold value. The controller controls an output of a warning for the text recognition result with respect to the first image in a case where the text recognition result and a text recognition result with respect to a second image showing a relevant document related to the document do not match even when the certainty factor is above or equal to the threshold value.

Abstract: Planar regions in three-dimensional scenes offer important geometric cues in a variety of three-dimensional perception tasks such as scene understanding, scene reconstruction, and robot navigation. Image analysis to detect planar regions can be performed by a deep learning architecture that includes a number of neural networks configured to estimate parameters for the planar regions. The neural networks process an image to detect an arbitrary number of plane objects in the image. Each plane object is associated with a number of estimated parameters including bounding box parameters, plane normal parameters, and a segmentation mask. Global parameters for the image, including a depth map, can also be estimated by one of the neural networks. Then, a segmentation refinement network jointly optimizes (i.e., refines) the segmentation masks for each instance of the plane objects and combines the refined segmentation masks to generate an aggregate segmentation mask for the image.

Abstract: A method for characterizing damage to bits or bottom hole assemblies can include identifying, via a supervised learning model, a location, an extent, a type, a consistency, or any combination thereof of damage to a bit or a bottom hole assembly from an image of the bit or the bottom hole assembly. A graphical output is generated based on the damage to the at least one component of the bit or the bottom hole assembly.

Abstract: A video processing system and method apply a bilateral filter to images of a video stream in real time. The bilateral filter is executed and applied using a graphics processing unit (GPU) controlled by a processor. The bilateral filter may be encoded in a shader operated by the GPU. The GPU or processor may be configured to compress one or more video images of the video stream. Blurring or smoothing of the video images by the shader-implemented bilateral filter may reduce image noise thereby increasing a compression performance. The bilateral filter may be applied exclusively to a background of the video images which are substantially free of sharp edges. The video stream may be received from cameras covering an area of an airport, which may be an airport apron.

Abstract: A generative adversarial network including a generator portion and a discriminator portion is constructed. The network is configured such that the network operates to enhance intensity images, wherein an intensity image is obtained by illuminating an object with an energy pulse and measuring the return strength of the energy pulse, and wherein a pixel of the intensity image corresponds to the return strength. As a part of the configuring, a loss function of the generative adversarial network is minimized, the loss function comprising a mean square error loss measurement of a noisy intensity image relative to a mean square error loss measurement of a corresponding clean intensity image. An enhanced intensity image is generated by applying the minimized loss function of the network to an original intensity image, the applying improving an image quality measurement of the enhanced intensity image relative to the original intensity image.

Abstract: A traffic monitoring system includes a first car moving on a first path; a camera having a field of vision including at least a portion of the first path; and a computing system. The computing system receives a plurality of images from the camera. The computing system has a processor. When instructed, the processor performs circling a perimeter of the first car on each of the images with a first rectangle; composing a first set of points, each point of the first set of points representing a center of the first rectangle; finding a first centroid using the first set of points, wherein the first centroid represents the first path; and calculating a speed of the first car using the first centroid.

Abstract: A system and a method to analyze a phenotypical response of cells to a treatment are disclosed in which a model development module receives images of a plurality of reference cell carriers and treatment information associated with the plurality of reference cell carriers, identifies parameters of cells in the image that distinguish those reference cell carriers to which the treatment has been applied from other reference cell carriers, and trains a model using the identified parameters. A high-content imaging system includes an image capture device, and the image acquisition module receives from the image capture device a plurality of images of cell carriers to be evaluated. The model application module applies the trained model to the plurality of images of the cell carriers to be evaluated to predict a concentration of the treatment applied to each of the cell carriers evaluated.

Abstract: A measurement method and apparatus are provided. The measurement method is applicable to an image acquisition device, and includes: acquiring image data to generate an image data file (S101); capturing an object to be measured in an image corresponding to the image data file (S102); obtaining a first distance between a horizontal line going through a lowest point of the object to be measured in the image and a horizontal line going through a center point of the image (S103); and calculating a second distance between the object to be measured and the image acquisition device based on the first distance, an installation height of the image acquisition device and a pitch angle of the image acquisition device (S104). Compared with the relevant art, the image acquisition device can measure the distance to an object to be measured while achieving relatively low production cost and easy installation. As a result, actual demands can be better satisfied.

Abstract: A system and method for semantic segmentation using hybrid dilated convolution (HDC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and producing multiple convolution layers; grouping the multiple convolution layers into a plurality of groups; applying different dilation rates for different convolution layers in a single group of the plurality of groups; and applying a same dilation rate setting across all groups of the plurality of groups.

Abstract: Systems and methods for segmenting an image using a convolutional neural network are described herein. A convolutional neural network (CNN) comprises an encoder-decoder architecture, and may comprise one or more Long Short Term Memory (LSTM) layers between the encoder and decoder layers. The LSTM layers provide temporal information in addition to the spatial information of the encoder-decoder layers. A subset of a sequence of images is input into the encoder layer of the CNN and a corresponding sequence of segmented images is output from the decoder layer. In some embodiments, the one or more LSTM layers may be combined in such a way that the CNN is predictive, providing predicted output of segmented images. Though the CNN provides multiple outputs, the CNN may be trained from single images or by generation of noisy ground truth datasets. Segmenting may be performed for object segmentation or free space segmentation.

Abstract: A system is provided for object localization in image data. The system includes an object localization framework comprising a plurality of object localization processes. The system is configured to receive an image comprising unannotated image data having at least one object in the image, access a first object localization process of the plurality of object localization processes, determine first bounding box information for the image using the first object localization process, wherein the first bounding box information comprises at least one first bounding box annotating at least a first portion of the at least one object in the image, and receive first feedback regarding the first bounding box information determined by the first object localization process. The system is further configured to persist the image with the first bounding box information or access a second object localization process based on the first feedback.

Abstract: An object detection apparatus includes a boundary box decision circuit and a processing circuit. The boundary box decision circuit receives lens configuration information of a lens, and refers to the lens configuration information to determine a bounding box distribution of bounding boxes that are assigned to different detection distances with respect to the lens for detection of a target object. The processing circuit receives a captured image that is derived from an output of an image capture device using the lens, and performs object detection upon the captured image according to the bounding box distribution of the bounding boxes.

Abstract: An object attribution analyzing method applied to an object attribution analyzing device and includes dividing a plurality of continuous frames into a current frame and several previous frames, utilizing face detection to track and compute a first attribution predicted value of an object within the current frame, utilizing the face detection to acquire a feature parameter of the object within the current frame for setting a first weighting, acquiring a second attribution predicted value of the object within the several previous frames, setting a second weighting in accordance with the first weighting, and generating a first induction attribution predicted value of the object within the plurality of continuous frames via the first attribution predicted value weighted by the first weighting and the second attribution predicted value weighted by the second weighting.

Abstract: A method for estimating time to collision (TTC) of a detected object in a computer vision system is provided that includes determining a three dimensional (3D) position of a camera in the computer vision system, determining a 3D position of the detected object based on a 2D position of the detected object in an image captured by the camera and an estimated ground plane corresponding to the image, computing a relative 3D position of the camera, a velocity of the relative 3D position, and an acceleration of the relative 3D position based on the 3D position of the camera and the 3D position of the detected object, wherein the relative 3D position of the camera is relative to the 3D position of the detected object, and computing the TTC of the detected object based on the relative 3D position, the velocity, and the acceleration.

Abstract: The embodiments of the present disclosure provide a method for processing 3D data, an apparatus for processing 3D data, a device and a storage medium. The method includes: acquiring three-dimensional point cloud data to be processed; mapping the three-dimensional point cloud data into a two-dimensional image space to obtain a first depth map; performing an expansion processing on the first depth map after changing an occlusion relation between target objects contained in the first depth map; and changing the occlusion relation between the target objects contained in the first depth map subject to the expansion processing to obtain a second depth map matched to the three-dimensional point cloud data.