Abstract: The present disclosure provides a target detection and model training method and apparatus, a device and a storage medium, and relates to the field of artificial intelligence, and in particular, to computer vision and deep learning technologies, which may be applied to smart city and intelligent transportation scenarios. The target detection method includes: performing feature extraction processing on an image to obtain image features of a plurality of stages of the image; performing position coding processing on the image to obtain a position code of the image; obtaining detection results of the plurality of stages of a target in the image based on the image features of the plurality of stages and the position code; and obtaining a target detection result based on the detection results of the plurality of stages.

Abstract: A machine learning apparatus for extracting a region from an input image, comprises: an inference unit configured to output the region by inference processing for the input image; and an augmentation unit configured to, in learning when learning of the inference unit is performed based on training data, perform data augmentation by increasing the number of input images constituting the training data, wherein the augmentation unit performs the data augmentation such that a region where image information held by the input image is defective is not included.

Abstract: The present invention belongs to the technical field of computer vision, and provides a video semantic segmentation method based on active learning, comprising an image semantic segmentation module, a data selection module based on the active learning and a label propagation module. The image semantic segmentation module is responsible for segmenting image results and extracting high-level features required by the data selection module; the data selection module selects a data subset with rich information at an image level, and selects pixel blocks to be labeled at a pixel level; and the label propagation module realizes migration from image to video tasks and completes the segmentation result of a video quickly to obtain weakly-supervised data. The present invention can rapidly generate weakly-supervised data sets, reduce the cost of manufacture of the data and optimize the performance of a semantic segmentation network.

Abstract: The present disclosure provides systems and methods for predicting a disease state of a subject using ultrasound imaging.

Abstract: An electronic device is provided. The electronic device includes a camera, a display, and a processor configured to obtain a first image including one or more external objects by using the camera, display to output a three-dimensional (3D) object generated based on attributes related to a face among the one or more external objects using the display, receive a selection of at least one graphic attribute from a plurality of graphic attributes which can be applied to the 3D object, generate a 3D avatar for the face based on the at least one graphic attribute, and generate a second image including at least one object reflecting a predetermined facial expression or motion using the 3D avatar.

Abstract: Techniques and apparatus for generating dense natural language descriptions for video content are described. In one embodiment, for example, an apparatus may include at least one memory and logic, at least a portion of the logic comprised in hardware coupled to the at least one memory, the logic to receive a source video comprising a plurality of frames, determine a plurality of regions for each of the plurality of frames, generate at least one region-sequence connecting the determined plurality of regions, apply a language model to the at least one region-sequence to generate description information comprising a description of at least a portion of content of the source video. Other embodiments are described and claimed.

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

Abstract: A system comprises an encoder configured to compress and encode data for a three-dimensional mesh using a video encoding technique. To compress the three-dimensional mesh, the encoder determines sub-meshes and for each sub-mesh: texture patches and geometry patches. Also the encoder determines patch connectivity information and patch texture coordinates for the texture patches and geometry patches. The texture patches and geometry patches are packed into video image frames and encoded using a video codec. Additionally, the encoder determines boundary stitching information for the sub-meshes. A decoder receives a bit stream as generated by the encoder and reconstructs the three-dimensional mesh.

Abstract: A line of coherent radiation is projected on a bed on which one or more particles is located, the one or more particles flowing produced as a result of a downhole operation in the borehole. An image of the bed is captured wherein one or more particles on the bed deflect the line of coherent radiation. One or more image edges is detected based on the captured image. A subset of the one or more image edges is identified as corresponding to edges of the one or more particles, based in part on changes in intensity of the captured image. Information about the one or more particles, including information about of size, shape and volume, can be determined from the one or more image edges corresponding to the edges of the one or more particles.

Abstract: An apparatus includes an interface and a processor. The interface may be configured to receive pixel data from a capture device. The processor may be configured to (i) process the pixel data arranged as one or more video frames, (ii) extract features from the one or more video frames, (iii) generate fused maps for at least one of disparity and optical flow in response to the features extracted, (iv) generate regenerated image frames by performing warping on a first subset of the video frames based on (a) the fused maps and (b) first parameters, (v) perform a classification of a sample image frame based on second parameters, and (vi) update the first parameters and the second parameters in response to whether the classification is correct. The classification generally comprises indicating whether the sample image frame is one of a second subset of the video frames or one of the regenerated image frames.

Abstract: In order to provide a learning data generating apparatus that is able to efficiently restrain erroneous detections, the learning data generating apparatus includes a data acquisition unit configured to acquire learning data including teacher data, and a generation unit configured to generate generated learning data based on the learning data and a generating condition, wherein the generation unit converts teacher data of a positive instance into teacher data of a negative instance according to a preset rule when generating the generated learning data.

Abstract: Systems and methods for registering arbitrary visual features for use as fiducial elements are disclosed. An example method includes aligning a geometric reference object and a visual feature and capturing an image of the reference object and feature. The method also includes identifying, in the image of the object and the visual feature, a set of at least four non-colinear feature points in the visual feature. The method also includes deriving, from the image, a coordinate system using the geometric object. The method also comprises providing a set of measures to each of the points in the set of at least four non-colinear feature points using the coordinate system. The measures can then be saved in a memory to represent the registered visual feature and serve as the basis for using the registered visual feature as a fiducial element.

Abstract: A method includes receiving a video comprising images representing an object, and determining, using a machine learning model, based on a first image of the images, and for each respective vertex of vertices of a bounding volume for the object, first two-dimensional (2D) coordinates of the respective vertex. The method also includes tracking, from the first image to a second image of the images, a position of each respective vertex along a plane underlying the bounding volume, and determining, for each respective vertex, second 2D coordinates of the respective vertex based on the position of the respective vertex along the plane. The method further includes determining, for each respective vertex, (i) first three-dimensional (3D) coordinates of the respective vertex based on the first 2D coordinates and (ii) second 3D coordinates of the respective vertex based on the second 2D coordinates.

Abstract: Embodiments of the disclosure provide systems and methods for generating a diagnosis report based on a medical image of a patient. The system includes a communication interface configured to receive the medical image acquired by an image acquisition device. The system further includes at least one processor. The at least one processor is configured to detect a medical condition based on the medical image and automatically generate text information describing the medical condition. The at least one processor is further configured to construct the diagnosis report, where the diagnosis report includes at least one image view showing the medical condition and a report view including the text information describing the medical condition. The system also includes a display configured to display the diagnosis report.

Abstract: A method and system for tone-mapping an image includes determining a tone-curve based on a model of image contrast distortion between the input image and a tone-mapped image and tone-mapping the input image according to the determined tone-curve. Determining the tone curve includes analytically calculating values of the tone-curve that reduce the image contrast distortion within the model of image contrast distortion. A tone-mapping operator includes a noise model generator and a tone-mapping module operable to receive one or more contextual parameters. The tone-mapping module includes an edge-stopping filtering submodule for extracting a base layer and detail layer of the input image, a tone-curve generating submodule and a combining submodule for combining the base layer and detail layer. At least one of the edge-stopping filtering submodule, the tone-curve generating submodule and combining submodule is adjustable based on the contextual parameters.

Abstract: Systems and methods to detect one or more segments of one or more objects within one or more images based, at least in part, on a neural network trained in an unsupervised manner to infer the one or more segments. Systems and methods to help train one or more neural networks to detect one or more segments of one or more objects within one or more images in an unsupervised manner.

Abstract: A system comprising: a document holder; an image sensor directed toward the document holder; a polarized filter between the image sensor and the document holder; a filter motor configured to rotate the polarized filter; one or more processors; and at least one memory having stored thereon computer program code that, when executed by the one or more processors, instructs the one or more processors to: control the filter motor to rotate the polarized filter; control the image sensors to capture a plurality of images of a document within the document holder, the plurality of images corresponding to a respective relative orientations of the polarized filter to the document; identify a feature of the document; and output, in response comparing respective visual characteristics of the feature of the document to corresponding expected visual characteristics of the first feature for the document, an indication of a verification of the document.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. In one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.

Abstract: Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

Abstract: A method of filtering a target pixel in an image forms, for a kernel of pixels comprising the target pixel and its neighbouring pixels, a data model to model pixel values within the kernel; calculates a weight for each pixel of the kernel comprising: (i) a geometric term dependent on a difference in position between that pixel and the target pixel; and (ii) a data term dependent on a difference between a pixel value of that pixel and its predicted pixel value according to the data model; and uses the calculated weights to form a filtered pixel value for the target pixel, e.g. by updating the data model with a weighted regression analysis technique using the calculated weights for the pixels of the kernel; and evaluating the updated data model at the target pixel position so as to form the filtered pixel value for the target pixel.