Abstract: A multimodal system is provided for managing safety in an industrial environment. The system comprises: a computer vision component for generating a computer vision output data; a real-time locating component for generating location data about an object within the industrial environment; a LIDAR component for generating 3D point cloud data of the industrial environment; and one or more processors coupled to the computer vision component, the real-time locating component and the LIDAR component and configured to: (i) generate label data using the location data and identity about one or more objects generated by the real-time locating component, and (ii) update one or more predictive models utilized by the component vision component or the multimodal system using the label data.

Abstract: An object area measurement method and an apparatus are provided, relating to the computer vision and deep learning technology. The method includes acquiring an original image with a spatial resolution, the original image including a target object; acquiring an object identification model including at least two sets of classification models; generating one or more original image blocks based on the original image; performing operations on each original image block: scaling each original image block at at least two scaling levels to obtain scaled image blocks with at least two sizes, the scaled image blocks respectively corresponding to the at least two sets of classification models, and inputting the scaled image blocks into the object identification model to obtain an identification result of the target object; and determining an area of the target object based on the respective identification results of the one or more original image blocks and the spatial resolution.

Abstract: An information processing apparatus includes a processor configured to infer an object represented in image data to be processed, the object being inferred by using a learning model for inferring the object represented in the image data, and perform image processing on the image data with a correction level of the image processing for correcting the image data being varied on a basis of a probability of correctness in inference of the object.

Abstract: Techniques for detecting anomalies in multispectral image data, and more specifically for detecting presentation attacks by using multispectral image data in biometric security applications, are provided. In some embodiments, a system may receive multispectral image data and generate an estimation of a first image of a plurality of images of the multispectral image data, wherein the estimation is based on other images of the multispectral image data, but not the first image itself. The estimation may then be compared to the first image to generate an indication as to whether the multispectral image data represents a presentation attack. In some embodiments, a system may receive multispectral training image data and may extract features from the data to generate and store a network architecture for predicting relationships of multispectral images of subjects.

Abstract: Systems and methods for object detection. The methods comprise, by a computing device: obtaining a plurality of intensity values denoting at least a difference in a first location of at least one object in a first image and a second location of the at least one object in a second image; converting the intensity values to 3D position values; inputting the 3D position values into a classifier algorithm to obtain classifications for data points of a 3D point cloud (each of the classifications comprising a foreground classification or a background classification); and using the classifications to detect at least one object which is located in a foreground or a background.

Abstract: Systems and techniques are generally described for determining similar content. First embedding data may be generated for first content based at least in part on a specified similarity task. A first query comprising the first embedding data may be generated and sent to a first database partition. A first search result representing second content may be determined using the first embedding data. A second query comprising the first embedding data may be generated and sent to a second database partition different from the first data base partition. A second search result representing third content may be determined using the first embedding data. In some examples, output data comprising at least one of the first search result and the second search result may be generated. The output data may represent content classified as similar to the first content.

Abstract: A method, an apparatus, and a device for classifying LiDAR point cloud data, and a storage medium. The method includes: acquiring sample point cloud data and LiDAR point cloud data to be classified; building a point cloud classifier according to the sample point cloud data; classifying the LiDAR point cloud data to be classified by the point cloud classifier. In the present disclosure, the point cloud classifier is trained from the sample point cloud data, and the automatic classification is performed by the point cloud classifier for the LiDAR point cloud data to be classified. The sample point cloud data used for training the point cloud classifier includes various tower data and electric power line data. Moreover, after the classification result is obtained from the automatic classification, the speckling merging optimization is further performed, and the optimization is performed according to the tower position file and the preset optimization rule.

Abstract: An adaptable climate control method for controlling a thermal climate within a confined space based on thermal and/or physiological features of one or more occupants of the confined space is provided. The method includes receiving thermal images of a plurality of target areas from the occupants, identifying a plurality of interesting points of the received thermal images, and isolating the interesting points to construct thermal maps of the target areas. Thermal features of the occupants are determined using the respective thermal maps and the thermal features are used to construct thermal feature vectors for the occupants. Physiological features from physiological sensors can also be added as elements of the thermal feature vectors to form integrated vectors. The thermal feature vectors and/or integrated vectors are classified using a classifiers and at least a portion of the thermal climate of the confined space is adjusted based on the classification of the vectors.

Abstract: Systems and methods for assessing plotting device accuracy in aid of a process for qualifying plotter systems. The system and process involve an ideal (virtual) test pattern consisting of digital data defining a nominal grid augmented by geometric features (e.g., closed two-dimensional geometric shapes which respectively surround intersections or vertices of the nominal grid). The plotting device under test is commanded to print a test plot having a pattern that matches the test pattern, but the test plot may deviate from the test pattern. To measure the amount of deviation, first an image of the test plot on the printed medium is captured using an accurate optical scanner. Then a mathematical measurement process, implemented in a computer vision application (e.g., a software package), is employed to detect deviations of the test plot from the test pattern. A statistical analysis is then performed to determine whether the deviations are within specifications.

Abstract: Systems and methods are provided for detecting a flashing light on one or more traffic signal devices. The method includes capturing a series of images of one or more traffic signal elements in a traffic signal device over a length of time. The method further includes, for each traffic signal element, analyzing the series of images to determine one or more time periods at which the traffic signal element is in an on state or an off state, and analyzing the time periods to determine one or more distinct on states and one or more distinct off states. The method further includes identifying one or more cycles correlating to a distinct on state immediately followed by a distinct off state, or a distinct off state immediately followed by a distinct on state, and, upon identifying a threshold number adjacent cycles, classifying the traffic signal element as a flashing light.

Abstract: A vehicle collects video data of an environment surrounding the vehicle including traffic entities, e.g., pedestrians, bicyclists, or other vehicles. The captured video data is sampled and presented to users to provide input on a traffic entity's state of mind. The user responses on the captured video data is used to generate a training dataset. A machine learning based model configured to predict a traffic entity's state of mind is trained with the training dataset. The system determines input video frames and associated dimension attributes for which the model performs poorly. The dimension attributes characterize stimuli and/or an environment shown in the input video frames. The system generates a second training dataset based on video frames that have the dimension attributes for which the model performed poorly. The model is retrained using the second training dataset and provided to an autonomous vehicle to assist with navigation in traffic.

Abstract: Optimizing seismic to depth conversion to enhance subsurface operations including measuring seismic data in a subsurface formation, dividing the subsurface formation into a training area and a study area, dividing the seismic data into training seismic data and study seismic data, wherein the training seismic data corresponds to the training area, and wherein the study seismic data corresponds to the study area, calculating target depth data corresponding to the training area, training a machine learning model using training inputs and training targets, wherein the training inputs comprise the training seismic data, and wherein the training targets comprise the target depth data, computing, by the machine learning model, output depth data corresponding to the study area based at least in part on the study seismic data; and modifying one or more subsurface operations corresponding to the study area based at least in part on the output depth data.

Abstract: Methods and systems disclosed herein relate generally to systems and methods for predicting content based on vector data structures generated from image pixels. A content-prediction application accesses a color palette having two or more color-palette categories and selects a first color of the color palette. The content-prediction application generates a first vector based on a set of pixel values that represent the first color of the color palette. The content-prediction application determines a distance metric between the first vector and a second vector, in which the second vector is identified by applying a convolutional neural network model on an image depicting an item that includes a second color. In response to determining that the distance metric is less than a predetermined threshold, the content-prediction application selects the content item corresponding to the second vector.

Abstract: A spectrum analysis apparatus is an apparatus for analyzing an analysis object on the basis of a spectrum of light generated in the analysis object containing any one or two or more of a plurality of reference objects, and includes an array conversion unit, a processing unit, a learning unit, and an analysis unit. The array conversion unit generates two-dimensional array data on the basis of a spectrum of light generated in the reference object or the analysis object. The processing unit includes a deep neural network. The analysis unit causes the array conversion unit to generate the two-dimensional array data on the basis of the spectrum of light generated in the analysis object, inputs the two-dimensional array data to the deep neural network, and analyzes the analysis object on the basis of data output from the deep neural network.

Abstract: An image recognition method, an apparatus, an electronic device, and a storage medium.

Abstract: A system comprises a picture and metadata captured by a content capture system; a recognizable characteristic datastore configured to store recognizable characteristics of different users; a module configured to identify a time and a location associated with the picture based on the metadata, and to identify one or more potential target systems within a predetermined range of the location at the time; a characteristic recognition module configured to retrieve the recognizable characteristics of one or more potential users associated with the potential target systems, and evaluate whether the picture includes one or more representations of at least one actual target user from the potential users based on the recognizable characteristics of the potential users; a distortion module configured to distort a feature of the representations of the least one actual target user in response to the determination; a communication module configured to communicate the distorted picture to a computer network.

Abstract: A method for detecting unmanned aerial vehicles (UAV) includes detecting an unknown flying object in a monitored zone of air space. An image of the detected unknown flying object is captured. The captured image is analyzed to classify the detected unknown flying object. A determination is made, based on the analyzed image, whether the detected unknown flying object comprises a UAV.

Abstract: An inference apparatus comprises a plurality of PEs (Processing Elements) and a control part. The control part operates a convolution operation in a convolutional neural network using each of a plurality of pieces of input data and a weight group including a plurality of weights corresponding to each of the plurality of pieces of input data by controlling the plurality of PEs. Further, each of the plurality of PEs executes a computation including multiplication of a single piece of the input data by a single weight and also executes multiplication included in the convolution operation using an element with a non-zero value included in each of the plurality of pieces of input data.

Abstract: Embodiments described herein provide an apparatus comprising a processor to project and accumulate three-dimensional (3D) point data from a blob onto a plane; construct a histogram of the 3D point data; identify a center of mass of the blob based on histogram data; surround peaks in coordinates for data in the blob with a shape defined by a diameter of the blob based on the center of mass; obtain height data for the 3D point data; and calculate dimensions for a bounding box to surround the blob based on the shape and the height data. Other embodiments may be described and claimed.

Abstract: Embodiments of a wearable device can include a head-mounted display (HMD) which can be configured to display virtual content. While the user is interacting with visual or audible virtual content, the user of the wearable may encounter a triggering event such as, for example, an emergency condition or an unsafe condition, detecting one or more triggering objects in an environment, or determining characteristics of the user's environment (e.g., home or office). Embodiments of the wearable device can automatically detect the triggering event and automatically control the HMD to deemphasize, block, or stop displaying the virtual content. The HMD may include a button that can be actuated by the user to manually deemphasize, block, or stop displaying the virtual content.