Abstract: A method for determining a plant growth curve includes obtaining color images and depth images of a plant to be detected at different time points, performing alignment processing on each color image and each depth image to obtain an alignment image, detecting the color image through a pre-trained target detection model to obtain a target bounding box, calculating an area ratio of the target bounding box in the color image, determining a depth value of all pixel points in the target boundary frame according to the aligned image, performing denoising processing on each depth value to obtain a target depth value, generating a first growth curve of the plant to be detected according to the target depth values and corresponding time points, and generating a second growth curve of the plant to be detected according to the area ratios and the corresponding time points.

Abstract: This application provides a pathological section image processing method performed by a computer device. The method includes: obtaining stained images of a pathological section after cell membrane staining; determining cell nucleus positions of cancer cells in a stained image under an ith field of view in the n fields of view; generating a cell membrane description result of the stained image under the ith field of view, the cell membrane description result being used for indicating completeness and staining intensity of the cell membrane staining; determining quantities of cells of types in the stained image under the ith field of view according to the cell nucleus positions and the cell membrane description result; and determining an analysis result of the pathological section according to quantities of the cells of types in the stained images under the n fields of view.

Abstract: Systems and methods are described for compressing color information in point cloud data. In some embodiments, point cloud data includes point position information and point color information for each of a plurality of points. The point position information is provided to a neural network, and the neural network generates predicted color information (e.g. predicted luma and chroma values) for respective points in the point cloud. A prediction residual is generated to represent the difference between the predicted color information and the input point color position. The point position information (which may be in compressed form) and the prediction residual are encoded in a bitstream. In some embodiments, color hint data is encoded to improve color prediction.

Abstract: Apparatus and methods for determining information about one or more objects in a 3-dimensional (3D) space are disclosed. One aspect of the method includes defining a virtual ground plane within a monitored 3D space. The virtual ground plane is divided into a plurality of bins. Each bin has corresponding counter value. An object is detected in a respective image captured by each of a plurality of sensors. A respective line segment is selected corresponding to a respective light between each of the plurality of image sensors and the detected object. One or more bins of the virtual ground plane are selected onto which a respective projected line segment of each respective line segment overlap. Each counter value for each of the one or more selected bins is increased. A location of the object is determined based on a bin of the one or more bins having a highest counter value.

Abstract: A method for improving face recognition from unseen domains by learning semantically meaningful representations is presented. The method includes obtaining face images with associated identities from a plurality of datasets, randomly selecting two datasets of the plurality of datasets to train a model, sampling batch face images and their corresponding labels, sampling triplet samples including one anchor face image, a sample face image from a same identity, and a sample face image from a different identity than that of the one anchor face image, performing a forward pass by using the samples of the selected two datasets, finding representations of the face images by using a backbone convolutional neural network (CNN), generating covariances from the representations of the face images and the backbone CNN, the covariances made in different spaces by using positive pairs and negative pairs, and employing the covariances to compute a cross-domain similarity loss function.

Abstract: A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. A number of contexts associated with the received data is reduced based on reducing a size of an array corresponding to syntax elements for predictive tree-based coding of the point cloud. The data corresponding to the point cloud is decoded based on the reduced number of contexts.

Abstract: System and method for producing an adversarial article that may be used to disrupt an automated visual tracking process. An input module receives input related to a specific automated visual tracking process. Based on that input, a pattern-design module generates an adversarial pattern. The adversarial pattern may then be applied to an article, which may be any kind of physical or virtual object. The tracker's normal processing modes are disrupted when the tracker attempts to process an image containing the adversarial article(s). The tracker may be mounted on an autonomous vehicle, a mobile robot, or other mobile or stationary camera surveillance system.

Abstract: Disclosed are systems, apparatuses, and methods to determine, communicate, and/or respond to state information of at least one of a suspended load control apparatus, carrier, or load suspended by a cable from the carrier, wherein response to the state information may be to control at least one of the suspended load control apparatus, carrier, or load suspended by a cable from the carrier.

Abstract: An image coordinate system transformation method includes obtaining video images acquired by adjacent cameras, the adjacent cameras including a first camera and a second camera that have an overlapping photography region on a ground plane, recognizing N groups of key points of a target object on the ground plane from the video images acquired by the adjacent cameras, each group of key points including first key point extracted from a video image of the first camera and a second key point extracted from a video image of the second camera, the first key point and the second key point being the same feature point of the same target object appearing in the adjacent cameras at the same moment, and N being an integer greater than or equal to 3, and calculating a transformation relationship between image coordinate systems of the adjacent cameras according to the N groups of key points.

Abstract: Digital fingerprints include data indicative of interior features or structures of an object. The physical object may be rigid or malleable. The digital fingerprints may also include data indicative of features on an exterior surface of the object. Digital fingerprints may uniquely identify an object with respect to other objects, even with respect to other objects of a same type or class of objects. The technology may be relatively invariant to changes in scale, rotation, affine, homography, perspective, and illumination as between a reference digital fingerprint and a later acquired or generated digital fingerprint. Digital fingerprints may be used to authenticate an object as being a second instance or appearance of a previously digitally fingerprinted object.

Abstract: Some embodiments of a method may include obtaining an image a real-world environment, determining an estimated illuminant spectral power distribution of an illuminant of the real-world environment, and detecting a region of the image representing human skin. The method may further include determining a representative skin color value of the region and based on the estimated illuminant spectral power distribution and the representative skin color value most closely matching the representative color value, selecting a candidate skin reflectance spectrum. The method may further include updating the estimated illuminant spectral power distribution base on the representative skin color value and the selected candidate skin reflectance spectrum.

Abstract: An image processing method includes: (a) receiving a to-be-processed image; (b) obtaining a target brightness of the to-be-processed image; (c) creating a histogram curve of the to-be-processed image; (d) clipping the histogram curve according to a clipping value; (e) obtaining a mapping function of the clipped histogram curve; (f) obtaining a mapped image mapped according to the mapping function; (g) obtaining an average brightness of the mapped image; (h) obtaining a difference between the target brightness and the average brightness; and (i) if the difference is greater than a threshold, adjusting the clipping value and repeating steps (d) to (i) until the difference is less than the threshold. Thus, if the to-be-processed image does not reach the target brightness, the image processing device automatically repeats steps (c) to (i) until the to-be-processed image reaches the target brightness.

Abstract: An image processing apparatus including a decoder configured to identify an area in an image frame at which object recognition is to be performed by using type information of a macroblock included in the image frame, and perform object recognition on the area of the image frame and skip the object recognition on areas of the image frame other than the area.

Abstract: An electronic device and a method for training or applying a neural network model are provided. The method includes the following steps. An input data is received. Convolution is performed on the input data to generate a high-frequency feature map and a low-frequency feature map. One of upsampling and downsampling is performed to match a first size of the high-frequency feature map and a second size of the low-frequency feature map. The high-frequency feature map and the low-frequency feature map are concatenated to generate a concatenated data. The concatenated data is inputted to an output layer of the neural network model.

Abstract: A computer apparatus and method for identifying and visualizing tumors in a histological image and measuring a tumor margin are provided. A CNN is used to classify pixels in the image according to whether they are determined to relate to non-tumorous tissue, or one or more classes for tumorous tissue. Segmentation is carried out based on the CNN results to generate a mask that marks areas occupied by individual tumors. Summary statistics for each tumor are computed and supplied to a filter which edits the segmentation mask by filtering out tumors deemed to be insignificant. Optionally, the tumors that pass the filter may be ranked according to the summary statistics, for example in order of clinical relevance or by a sensible order of review for a pathologist. A visualization application can then display the histological image having regard to the segmentation mask, summary statistics and/or ranking. Tumor masses extracted by resection are painted with an ink to highlight its surface region.

Abstract: The present invention relates to a deep-learning based system and method of automatically determining a degree of damage to each area of a vehicle, which is capable of quickly calculating a consistent and reliable quote for vehicle repair by analyzing an image of a vehicle in an accident by using a deep learning-based Mark R-CNN framework and then extracting a component image corresponding to a damaged part, and automatically determining the degree of damage in the extracted component image based on a pre-trained model.

Abstract: A welding system includes a welding apparatus and an appearance inspection apparatus. The appearance inspection apparatus includes: a shape measurement unit that measures the shape of a weld; an image processor that generates image data based on data of the shape; a determination unit that determines whether the shape of the weld is good or bad based on the image data and a determination model; and a feedback unit that extracts shape defect information if the result of the determination by the determination unit is negative. An output controller of the welding apparatus corrects a welding condition for a workpiece based on the shape defect information extracted by the feedback unit.

Abstract: An example method of encoding a point cloud includes obtaining a value of a secondary residual for geometry coding a current predictive tree node of the point cloud; and encoding the value of the secondary residual, wherein encoding the value comprises: encoding, using a first set of context-adaptive binary arithmetic coding (CABAC) contexts, prefix bins of a syntax element having a value that specifies an absolute value of the value of the secondary residual minus 2; and encoding, using a second set of CABAC contexts that is different than the first set of contexts, suffix bins of the syntax element.

Abstract: Disclosed are a wavelet-based progressive fast recompression method and system for large-deformed mesh data. Given mesh data is compressed. The compressed mesh data is recompressed by propagating part of a deformed mesh to all meshes based on information extracted from the compressed data when the mesh data is deformed.

Abstract: The present disclosure describes devices and methods for generating RGB images from Bayer filter images using adaptive sub-pixel spatiotemporal interpolation. An electronic device includes a processor configured to estimate green values at red and blue pixel locations of an input Bayer frame based on green values at green pixel locations of the input Bayer frame and a kernel for green pixels, generate a green channel of a joint demosaiced-warped output RGB pixel from the input Bayer frame based on the green values at the green pixel locations, the kernel for green pixels, and an alignment vector map, and generate red and blue channels of the joint demosaiced-warped output RGB pixel from the input Bayer frame based on the estimated green values at the red and blue pixel locations, kernels for red and blue pixels, and the alignment vector map.