Abstract: The present application provides an image reconstruction method, a device, equipment, a system, and a computer-readable storage medium. Said method comprises: obtaining a target reconstruction model (S1); invoking a first convolutional layer in the obtained target reconstruction model to extract shallow layer features from the obtained image to be reconstructed (S2); invoking a residual network module in the target reconstruction model to obtain middle layer features from the shallow layer features (S3); invoking a densely connected network module in the target reconstruction model to obtain deep layer features from the middle layer features (S4); and invoking a second convolutional layer in the target reconstruction model to perform image reconstruction on the deep layer features so as to obtain a reconstructed image of the image to be reconstructed (S5). Said method improves the quality and resolution of a reconstructed image.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives an image of a document, the document comprising a set of text. The program further provides the set of text to a machine learning model configured to determine, based on the set of text, a plurality of probabilities for a plurality of defined types of documents. Based on the plurality of probabilities for the plurality of defined types of documents, the program also determines a type of the document from the plurality of defined types of documents.

Abstract: A method for learning disentangled representations of videos is presented. The method includes feeding each frame of video data into an encoder to produce a sequence of visual features, passing the sequence of visual features through a deep convolutional network to obtain a posterior of a dynamic latent variable and a posterior of a static latent variable, sampling static and dynamic representations from the posterior of the static latent variable and the posterior of the dynamic latent variable, respectively, concatenating the static and dynamic representations to be fed into a decoder to generate reconstructed sequences, and applying three regularizers to the dynamic and static latent variables to trigger representation disentanglement. To facilitate the disentangled sequential representation learning, orthogonal factorization in generative adversarial network (GAN) latent space is leveraged to pre-train a generator as a decoder in the method.

Abstract: In a case where a three-dimensional model of a construction stored in a storage is to be displayed on a display, an information display apparatus 10 accepts a view operation including an operation for enlarging the three-dimensional model from an operation interface and at least enlarges and displays the three-dimensional model. After a desired position on the three-dimensional model enlarged and displayed on the display is specified in accordance with a user operation, the information display apparatus identifies a three-dimensional position on the three-dimensional model corresponding to the position and identifies a management segment that is an inspection unit of the construction on the basis of the identified three-dimensional position. After the management segment is thus identified, the information display apparatus reads management information corresponding to the identified management segment from the storage and displays the management information on the display.

Abstract: The disclosure relates to an artificial intelligence (AI) system using a machine learning algorithm such as deep learning and the like, and an application thereof. In particular, there is provided a control method for an electronic apparatus for searching for an image, the method comprising displaying an image comprising at least one object, detecting a user input for selecting an object, recognizing an object displayed at a point at which the user input is detected and acquiring information regarding the recognized object by using a recognition model trained to acquire information regarding an object, displaying a list including the information regarding the object, and based on one piece of information being selected from the information regarding the object included in the list, providing a related image by searching for the related image based on the selected information.

Abstract: A manufacturing method of learning data is used for making a neural network perform learning. The manufacturing method of learning data includes a first acquiring step configured to acquire an original image, a second acquiring step configured to acquire a first image as a training image generated by adding blur to the original image, and a third acquiring step configured to acquire a second image as a ground truth image generated by adding blur to the original image. A blur amount added to the second image is smaller than that added to the first image.

Abstract: The present invention provides a travel control apparatus (20) including an in-vehicle image acquisition unit (21) that acquires an in-vehicle image generated by a camera for capturing an inside of a vehicle compartment of a reserved vehicle, an in-vehicle sensing unit (22) that senses that a reserving person is present within a vehicle compartment of the reserved vehicle, based on the in-vehicle image, and a permission output unit (23) that outputs, when it is sensed that the reserving person is present within a vehicle compartment of the reserved vehicle, travel permission of the reserved vehicle.

Abstract: The present disclosure relates to an image processing method for correcting colors in an input image representing a scene, the image processing method including: processing the input image with a machine learning model, wherein the machine learning model is previously trained to detect a predefined number N>1 of sources of light illuminating the scene and to generate N estimated illuminant images associated respectively to the N sources of light, wherein each estimated illuminant image includes an estimated color of the light emitted by the respective source of light and an estimated contribution image; generating a total illuminant image by using the N estimated illuminant images; and generating an output image by correcting the colors in the input image based on the total illuminant image.

Abstract: The present disclosure provides a decision-making method and apparatus for water and fertilizer stress of crops, and a mobile phone terminal, and belongs to the technical field of intelligent agriculture. The method includes: determining a current crop coefficient and canopy temperature of a crop to be identified on the basis of a first crop image and a second crop image; determining a water stress state and a nutrient stress state on the basis of the current crop coefficient and canopy temperature of the crop to be identified; and processing the water stress state and the nutrient stress state with a fuzzy control algorithm, and determining a water and fertilizer stress decision result of the crop to be identified.

Abstract: An image processing system generates an image mask from an image. The image is processed by an object detector to identify a region having an object, and the region is classified based on an object type of the object. A masking pipeline is selected from a number of masking pipelines based on the classification of the region. The region is processed using the masking pipeline to generate a region mask. An image mask for the image is generated using the region mask.

Abstract: The present invention provides a facial acupoint locating method, an acupuncture method, an acupuncture robot, and a storage medium. The facial acupoint locating method includes: collecting an RGB image and a depth image of a face by using a depth camera, and generating three-dimensional point cloud data of the face based on the RGB image and the depth image; inputting the three-dimensional point cloud data of the face into a trained face segmentation model to obtain a plurality of facial feature regions, where the plurality of the facial feature regions include eyebrow regions, eye regions, a nose region, and a mouth region; and acquiring an association relationship between the plurality of the facial feature regions and key acupoint points, and determining locations of the facial acupoints based on the association relationship and the plurality of the facial feature regions.

Abstract: A method for training a depth estimation model implemented in an electronic device includes obtaining a first image pair from a training data set; inputting the first left image into the depth estimation model, and obtaining a disparity map; adding the first left image and the disparity map, and obtaining a second right image; calculating a mean square error and cosine similarity of pixel values of all corresponding pixels in the first right image and the second right image; calculating mean values of the mean square error and the cosine similarity, and obtaining a first mean value of the mean square error and a second mean value of the cosine similarity; adding the first mean value and the second mean value, and obtaining a loss value of the depth estimation model; and iteratively training the depth estimation model according to the loss value.

Abstract: In an approach to non-destructive inspection of IC devices, one or more images of a Device Under Test (DUT) are received from one or more imaging devices. Observed features are detected in the one or more images and producing a first synthetic representation of a part design of the DUT that includes the observed features. The presence of one or more first unobserved features are inferred, where the one or more first unobserved features are inferred using a mapping and inference model (MIM). The one or more first unobserved features are added to the first synthetic representation of the part design of the DUT.

Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

Abstract: The present invention relates to the curation of map data. More particularly, the present invention relates to a method for preparing map data to present to a data curator for substantially optimal quality assurance. Further, the present invention relates to a tool for a data curator to verify map data. According to a first aspect, there is provided a method comprising: generating a plurality of interdependent map portions from a global map; determining, from the plurality of interdependent map portions, at least one interdependent map portion that requires validation; creating at least one group of interdependent map portions, the group of interdependent map portions comprising: the determined at least one interdependent map portion that requires validation; and at least one additional interdependent map portion; and outputting the at least one group of interdependent map portions for validation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating realistic extensions of images. In one aspect, a method comprises providing an input that comprises a provided image to a generative neural network having a plurality of generative neural network parameters. The generative neural network processes the input in accordance with trained values of the plurality of generative neural network parameters to generate an extended image. The extended image has (i) more rows, more columns, or both than the provided image, and (ii) is predicted to be a realistic extension of the provided image. The generative neural network is trained using an adversarial loss objective function.

Abstract: A computer-implemented method for predicting the likelihood an embryo will produce a bovine male offspring by processing video image data derived from video of a target embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data to predict the likelihood the target embryo will produce a bovine male offspring.

Abstract: A method, system and computer program product are provided for determining wire contact insertion based on image analysis. Methods include: acquiring at least one image of a connector having a plurality of wire contact insertion holes; identifying a wire contact within a wire contact insertion hole of the plurality of wire contact insertion holes; determining that the wire contact insertion hole is a correct wire contact insertion hole; determining that the wire contact has been fully inserted into the correct wire contact insertion hole; and providing feedback indicating that the wire contact is fully inserted into the correct wire contact insertion hole. The feedback includes in some cases a first indicator indicating that the wire contact is in the correct wire contact insertion hole and a second indicator indicating that the wire contact is fully inserted into the correct wire contact insertion hole.

Abstract: Embodiments herein disclose a system and method for officiating interference in sports, such as squash. The system utilizes bounding boxes to detect objects within images of a playing field, and tracks the change in the positioning of these objects. Using depth estimation, the system creates a three-dimensional representation of the playing field, and simulates a location of each object on the playing field. The system divides a front wall of the playing field into attacking sections and divides a floor of the playing field into segments. Based on the three-dimensional coordinates of the objects, a relevant attacking section and at least one relevant segment is obtained. The system calculates at least one metric metrics based on the objects' coordinates. The system utilizes an artificial intelligence model that renders a decision based on the calculated metrics, the relevant attacking section, the at least one relevant segment, and one or more rules.

Abstract: Examples of the present disclosure describe systems and methods for detecting and remediating compression artifacts in multimedia items. In example aspects, a machine learning model is trained on a dataset related to compression artifacts and non-compression artifacts. Input data may then be collected by a data collection module and provided to a pattern recognition module. The pattern recognition module may extract visual and audio features of the multimedia item and provide the extracted features to the trained machine learning model. The trained machine learning model may compare the extracted features to the model, and a confidence value may be generated. The confidence value may be compared to a confidence value threshold. If the confidence value is equal to or exceeds the confidence threshold, then the input data may be classified as containing at least one compression artifact. Remedial action may subsequently be applied (e.g., boosting the system with technical resources).