Abstract: A method for detecting gesture key points can include: acquiring a target image to be detected; determining a gesture category according to the target image, the gesture category being a category of a gesture contained in the target image; determining a target key point detection model corresponding to the gesture category from a plurality of key point detection models; and performing a key point detection on the target image by the target key point detection model.

Abstract: A crop residue monitoring system may include a harvester, a camera to capture an image of crop residue generated by the harvester, an analytical unit to derive a value for a crop residue parameter of the crop residue based upon an optical analysis of the image and a control unit to adjust a subsequent field operation based upon the value of the crop residue parameter.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include accessing an image from an image sensor; detecting an object area on the image; classifying the object area on the image; applying a filter to an object area of the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.

Abstract: Implementations relate to detecting/replacing transient obstructions from high-elevation digital images, and/or to fusing data from high-elevation digital images having different spatial, temporal, and/or spectral resolutions. In various implementations, first and second temporal sequences of high-elevation digital images capturing a geographic area may be obtained. These temporal sequences may have different spatial, temporal, and/or spectral resolutions (or frequencies). A mapping may be generated of the pixels of the high-elevation digital images of the second temporal sequence to respective sub-pixels of the first temporal sequence. A point in time at which a synthetic high-elevation digital image of the geographic area may be selected. The synthetic high-elevation digital image may be generated for the point in time based on the mapping and other data described herein.

Abstract: The invention discloses a point cloud geometric compression method based on a depth auto-encoder, which comprises the following steps of: (1) point cloud preprocessing: collecting a type of point cloud to be compressed as a training set, and normalizing the training set into a unit circle; (2) point cloud down-sampling: down-sampling the point clouds in the training set so that each point cloud have the same point number m and each point in the point cloud has (x, y, z) three-dimensional coordinates; and adopting a farthest point down-sampling method by randomly selecting a point for the first time and then selecting the point farthest away from the selected point set every time to add into the selected point set until the selected point number meets the requirement; (3) training a compression model: inputting the point cloud sampled in step (2) into a point cloud geometric compression framework based on a depth auto-encoder for training; and (4) geometric compression of the point cloud: applying the trained

Abstract: Systems and methods provide a demand forecasting and network optimization for telecommunications services in a network. The systems and methods use classical and quantum computing devices. The computing devices evaluate data types using statistical symmetry recognition and operate between classical and quantum environments. Computing devices receive deposited data, batch data, and streamed data that relates to telecommunications services and segregate the data into spatial and temporal factors. The computing devices receive an analytic request for a forecast of the telecommunications services and conduct a multi-class plural-factored elastic cluster (MPEC) analysis for the telecommunications services using the segregated data. The MPEC analysis includes generating vectors comprised of slopes from plural coefficients to determine demand elasticity from plural features.

Abstract: A method of adaptive point cloud attribute coding includes obtaining an attribute of a current point included in point cloud data, and obtaining candidate predicted values of the obtained attribute, the candidate predicted values including any one or any combination of a weighted average value of a plurality of distances from the current point respectively to other points included in the point cloud data, a first predicted value of a first distance from the current point to a first nearest point among the other points and a second predicted value of a second distance from the current point to a second nearest point after the first nearest point among the other points. The method further includes selecting, for the obtained attribute, one among the obtained candidate predicted values, using rate-distortion optimization, and setting, for a decoder, a flag indicating whether the obtained candidate predicted values includes the weighted average value.

Abstract: Described herein are systems, apparatus, methods and computer program products configured for image detection/recognition of products. The disclosed systems and techniques utilize video data to provide the necessary number of images and view angles needed to train a machine learning product detection/recognition system to recognize a specific product within later provided images. In various embodiments, a user may provide video data and the video data may be transformed in a manner that may aid in training of the machine learning system.

Abstract: Systems and methods for an automated measurement utility are disclosed. Image analysis is used to determine a quantity of items in a stack of items. The quantity of items can be determined further based on item information and location awareness information. The quantity of items can be used to determine resource requirements, predictive workloads, and to improve item processing operations.

Abstract: Embodiments of the present disclosure disclose a target detecting method and apparatus, a training method, an electronic device, and a medium. The target detecting method includes: separately extracting, by means of a neural network, characteristics of a template frame and a detection frame, where the template frame is a detection box image of a target object, and the template frame is smaller than the detection frame in image size; obtaining a classification weight and a regression weight of a local region detector based on the characteristic of the template frame; inputting the characteristic of the detection frame into the local region detector to obtain classification results and regression results of multiple alternative boxes output by the local region detector; and obtaining a detection box for the target object in the detection frame according to the classification results and regression results of the multiple alternative boxes output by the local region detector.

Abstract: A vision based light detection and ranging (LIDAR) system detects motion of a targeted object using a dynamic vision sensor to locate and track the targeted object. The dynamic vision sensor identifies activity events associated with the motion of the targeted object based on changes in brightness detected at pixels of the dynamic vision sensor. Based on the identified events, the vision based LIDAR system predicts a location of the targeted object and directs a tracking beam onto one or more spots on the targeted object and determines distances to the one or more spots to track the motion of the targeted object in three dimensions.

Abstract: Various embodiments relate generally to computer vision and automation to autonomously identify and deliver for application a treatment to an object among other objects, data science and data analysis, including machine learning, deep learning, and other disciplines of computer-based artificial intelligence to facilitate identification and treatment of objects, and robotics and mobility technologies to navigate a delivery system, more specifically, to an agricultural delivery system configured to identify and apply, for example, an agricultural treatment to an identified agricultural object. In some examples, a method may include receiving data representing an image, detecting a portion of the image associated with a unit of spatial translation relative to a reference, identifying a subset of pixels to be formed on the surface, and causing emission of a subset of pixel projectiles directed to impact a portion of a surface to form a replica of a portion of the image.

Abstract: An apparatus for detecting morphed or averaged images, wherein the morphed or averaged images are synthetically generated images including information from two or more different source images corresponding to two or more subjects. The apparatus may include a feature extraction module for receiving an input image and outputting a set of descriptor feature(s) characteristic of the image and a classifier module configured to allocate the input image either to a first class indicating that the image has been morphed or averaged or a second class indicating that it has not been morphed or averaged, based on the descriptor feature(s). The feature extraction module may include a plurality of neural networks providing complementary descriptor feature(s) to the classifier module. The apparatus further may include a fusion module for combining descriptor feature data from each neural network and transmitting the fused feature data to the classifier module.

Abstract: A method includes obtaining, by the treatment system configured to implement a machine learning (ML) algorithm, one or more images of a region of an agricultural environment near the treatment system, wherein the one or more images are captured from the region of a real-world where agricultural target objects are expected to be present, determining one or more parameters for use with the ML algorithm, wherein at least one of the one or more parameters is based on one or more ML models related to identification of an agricultural object, determining a real-world target in the one or more images using the ML algorithm, wherein the ML algorithm is at least partly implemented using the one or more processors of the treatment system, and applying a treatment to the target by selectively activating the treatment mechanism based on a result of the determining the target.

Abstract: Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.

Abstract: Implementations disclosed herein provide systems and methods that use classification-based machine learning to generate perceptually-plausible content for a missing part (e.g., some or all) of an image. The machine learning model may be trained to generate content for the missing part that appears plausible by learning to generate content that cannot be distinguished from real image content, for example, using adversarial loss-based training. To generate the content, a probabilistic classifier may be used to select color attribute values (e.g., RGB values) for each pixel of the missing part of the image. To do so, a pixel color attribute is segmented into a number of bins (e.g., value ranges) that are used as classes. The classifier determines probabilities for each of the bins of a color attribute for each pixel and generates the content by selecting the bin having the highest probability for each color attribute for each pixel.

Abstract: Systems and techniques are provided for anomalous path detection within cameras' fields of view. Video of the field of view of a camera in an environment may be received from the camera. A person may be detected in the video. Motion of the person in the video may be tracked to generate a motion path. Contextual data for the motion path may be received. The motion path and contextual data may be stored in a camera training data set. A camera model for the camera and the field of view may be generated by inputting the camera training data set to a machine learning system. The camera model for the camera and the field of view may be stored.

Abstract: A vegetation index calculation apparatus (10) is provided with a learning model generation unit (11) that generates a learning model, by using an image of a crop targeted for calculation of a vegetation index and an image of plants other than the crop to learn a feature amount of the image of the crop, an image acquisition unit (12) that acquires an aerial image of a target region where the crop is being grown, a specification unit (13) that applies the aerial image acquired by the image acquisition unit (12) to the learning model generated by the learning model generation unit (11), and specifies the image of the crop in the aerial image acquired by the image acquisition unit (12), and a vegetation index calculation unit (14) that calculates the vegetation index of the crop, using the image of the crop specified by the specification unit (13).

Abstract: Systems and methods for utilizing dynamic codes in a dynamic system comprising neural networks are disclosed. In an exemplary embodiment, training data is transmitted to an encoder block, the encoder block having an encoder neural network. Training data is encoded utilizing the encoder neural network of the encoder block, and then decoded by a decoder block, the decoder block having a decoder neural network. An end-end error is determined by comparing the training data that was transmitted to the encoder block against the decoded training data that was received from the decoder block. Encoder/decoder parameters to minimize the end-end error are optimized and transmitted. Upon receipt of the encoder/decoder parameter updates, the encoder block and the decoder block are initialized.

Abstract: Methods for image segmentation, computer devices, and storage mediums. The method includes acquiring a to-be-segmented image, inputting the to-be-segmented image into an input variable of a full convolution neural network and outputting a convolution characteristic pattern; inputting the convolution characteristic pattern into an input variable of a context-switchable neural network and outputting context expression information; and generating an intermediate characteristic pattern for image segmentation according to the convolution characteristic pattern and the context expression information.