An efficient K-nearest neighbor search algorithm for three-dimensional (3D) lidar point cloud in unmanned driving and a use of the foregoing K-nearest neighbor search algorithm in a point cloud map matching process in the unmanned driving are provided. A novel data structure for fast K-nearest neighbor search is used, such that each voxel or sub-voxel includes a proper quantity of points to reduce redundant search. The novel K-nearest neighbor search algorithm is based on a double segmentation voxel structure (DSVS) and a field programmable gate array (FPGA). By means of the novel K-nearest neighbor search algorithm, nearest neighbors are searched for only in a neighboring expected area near a search point, thereby reducing search of redundant points. In addition, an optimized data transmission and access policy is used, which makes the algorithm more fit the characteristic of the FPGA.

Techniques are described for using computing devices to perform automated operations involved in analysis of images acquired in a defined area, as part of generating mapping information of the defined area for subsequent use (e.g., for controlling navigation of devices, for display on client devices in corresponding GUIs, etc.). The defined area may include an interior of a multi-room building, and the generated information including a floor map of the building, such as from an analysis of multiple 360° spherical panorama images acquired at various viewing locations within the building (e.g., using an image acquisition device with a spherical camera having one or more fisheye lenses to capture a panorama image that extends 360 degrees around a vertical axis)—the generating may be further performed without detailed information about distances from the images' viewing locations to objects in the surrounding building.

A BlockNet security organization storage mapping method for spatial data includes: first constructing a BlockNet gene propagation mechanism according to the characteristics of the BlockNet storage space data, and then designing multi-source gene propagation in a multi-space data center scenario mechanism. In the multi-source gene propagation mechanism, the propagation round control and the in/out-degree control mechanism are designed for the possible radiation crossover problems and radiation impact problems. A BlockNet information update plan is designed for data modification and update requirements in spatial data storage scenarios. In addition to realizing the unique primary key block coding of spatial data and accelerating the indexing speed, it also retains elevation information through multi-dimensional coding, expands the amount of information, improves the utilization efficiency of spatial data, and the security of data mapping and storage process is greatly improved.

Body and hand correlation method, apparatus, device, storage medium and computer program are provided. Method includes: in an image of which an image content includes a body to be correlated and a hand to be correlated, a first correlation probability between a body detection box of the body and a hand detection box of the hand is determined; a second correlation probability between the body and a wrist key point in a key point is determined based on the key point in the body detection box, the key point including the wrist key point and elbow key point belonging to the same arm; a third correlation probability between the hand detection box and the wrist key point is determined based on the wrist key point and elbow key point; and a correlation degree between the body and the hand is determined based on the first, second, and third correlation probabilities.

Systems (100) and methods (1000) for operating a shoulder Speaker Microphone (“SM”) device coupled to a radio. The methods comprising: using a speaker and a microphone of the shoulder SM device to facilitate auditory communications to and from a user of the radio; activating a thermal imaging device integrated with the shoulder SM device when the shoulder SM device resides at a location of an incident event; capturing thermal images by the thermal imaging device of the shoulder SM device; and performing operations by the shoulder SM device to cause the thermal images to be streamed over a network.

A CMOS image sensor for a code reader in an optical code recognition system incorporates a digital processing circuit that applies a calculation process to the capture image data as said data acquired by the sequential readout circuit of the sensor, in order to calculate a macro-image from the capture image data, which corresponds to location information of code(s) in the capture image, and transmit this macro-image in the image frame following the capture image data, in the footer of the frame.

A method to facilitate extraction of display objects for industrial diagrams are disclosed herein. The method comprises: receiving user input indicating a first display object within an industrial diagram; extracting the first display object to generate a first graphic extraction template; identifying one or more regions within the first graphic extraction template; masking the text information; linking each of the one or more regions with at least a portion of an object name of the first display object; extracting all the display objects, from the industrial diagram, that are of the type of the first display object using the first graphic extraction template to generate a first set of extracted graphic objects; and for each of the first set of extracted graphic objects, matching text information within each of the one or more regions with at least a portion of an object name.

An apparatus for detecting backlight of image, comprising: a processor configured to convert a pixel value for each of a plurality of image frames based on a first threshold, and block the pixel value into a plurality of block regions to generate a converted frame, generate brightness cumulative data based on the converted frame, determine a block region in which a block value is maximum in the brightness cumulative data as a backlight candidate block region, classify the block regions into first and second regions based on a position of the backlight candidate block region and calculate a backlight score using the sum of block values for the block region of the first region and the sum of block values for the block region of the second region, and determine the image as a backlight image when the backlight score based on a second threshold.

Methods, systems, articles of manufacture, and apparatus to recalibrate confidences for image classification are disclosed. An example apparatus to classify an image includes an image crop detector to detect a first image crop from the image, the first image crop corresponding to a first object, a grouping controller to select a second image crop corresponding to a second object at a location of the first object, a prediction generator to, in response to executing a trained model, determine a label corresponding to the first object and a confidence level associated with the label, and a confidence recalibrator to recalibrate the confidence level based on a probability of the first object having a first attribute based on the second object having a second attribute, the confidence level recalibrated to increase an accuracy of the image classification.

The present disclosure relates to method and system for extracting information based on user interactions performed on screen of a computing system. Method includes receiving processed input data comprising video capturing screen and user interactions events occurring from user interactions, and co-ordinate information. Thereafter, computing system determines Regions of Interest (RoI) on screen based on captured user interactions, events and co-ordinate information, and identifies type of user interaction performed with at least one screen element in the RoI, as either keyboard or mouse type interaction. Subsequently, computing system performs one of: determining type of screen element as a text box or a table based on pattern recognition when type of user interaction is identified as keyboard type interaction or determining type of screen element to be selectable User Interface elements and extracting content and label of selectable UI elements, when interaction is identified as mouse type interaction.