An information processing apparatus includes a processor configured to: acquire a captured image of an object; specify a first area of the object in the captured image, the first area being an area occupied by a work target that is a target to be worked on; process the captured image to make a second area other than the first area invisible to generate a processed image; in response to a change in the first area with a deformation of the work target, apply a deformation area instead of the first area to make a second area obtained by the application invisible to generate a processed image, the deformation area being an area defined by a pre-registered shape of the work target after deformation; and transmit the processed image.

A global and local binary pattern image crack segmentation method based on robot vision comprises the following steps: enhancing a contrast of an acquired original image to obtain an enhanced map; using an improved local binary pattern detection algorithm to process the enhanced map and construct a saliency map; using the enhanced map and the saliency map to segment cracks and obtaining a global and local binary pattern automatic crack segmentation method; and evaluating performance of the obtained global and local binary pattern automatic crack segmentation method. The present application uses logarithmic transformation to enhance the contrast of a crack image, so that information of dark parts of the cracks is richer. Texture features of a rotation invariant local binary pattern are improved. Global information of four directions is integrated, and the law of universal gravitation and gray and roundness features are introduced to correct crack segmentation results, thereby improving segmentation accuracy. Crack regions can be segmented in the background of uneven illumination and complex textures. The method has good robustness and meets requirements of online detection.

A client device receives a first map tile, a second map tile, and map terrain data from a mapping system, the first and second map tiles together including map feature having a geometric base with a height value, the geometric base represented by a set of vertices split across the first and second map tiles. The client device identifies edges of the geometric base that intersect a tile border between the first and second map tiles. The client device determines a set of sample points based on the identified edges and determines a particular sample elevation value corresponding to a sample point in the set. The client device renders the map feature based on the particular sample elevation value and displays the rendering of the map feature.

A high efficiency method of processing images to provide perceptual high-contrast output. Pixel intensities are calculated by a weighted combination of a fixed number of static bounding rectangle sizes. This is more performant than incrementally growing the bounding rectangle size and performing expensive analysis on resultant histograms. To mitigate image artifacts and noise, blurring and down-sampling are applied to the image prior to processing.

Each input image from a plurality of input images is divided into a plurality of image tiles. A feature point map including a plurality of feature point tiles respectively corresponding to the plurality of image tiles is generated by extracting feature points included in each image tile of the plurality of image tiles. A descriptor map including a plurality of descriptor tiles respectively corresponding to the plurality of feature point tiles is generated by generating descriptors of feature points included in the feature point map. Mapping information containing matching relationships between feature points included in different input images of the plurality of input images is generated based on a plurality of descriptor maps respectively corresponding to the plurality of input images. Image merging performance may be enhanced by dividing the input image into the plurality of image tiles to increase distribution uniformity of the feature points.

Methods and systems for performing diagnostic functions for a deep learning model are provided. One system includes one or more components executed by one or more computer subsystems. The one or more components include a deep learning model configured for determining information from an image generated for a specimen by an imaging tool. The one or more components also include a diagnostic component configured for determining one or more causal portions of the image that resulted in the information being determined and for performing one or more functions based on the determined one or more causal portions of the image.

One exemplary implementation facilitates object detection using multiple scans of an object in different lighting conditions. For example, a first scan of the object can be created by capturing images of the object by moving an image sensor on a first path in a first lighting condition, e.g., bright lighting. A second scan of the object can then be created by capturing additional images of the object by moving the image sensor on a second path in a second lighting condition, e.g., dim lighting. Implementations determine a transform that associates the scan data from these multiple scans to one another and use the transforms to generate a 3D model of the object in a single coordinate system. Augmented content can be positioned relative to that object in the single coordinate system and thus will be displayed in the appropriate location regardless of the lighting condition in which the physical object is later detected.

The present disclosure relates to a method performed in a fingerprint analysis system for facilitating differentiating between a live finger and a spoof finger. The method comprises acquiring a plurality of time-sequences of images, each of the time-sequences showing a respective finger as it engages a detection surface of a fingerprint sensor. Each of the time-sequences comprises at least a first image and a last image showing a fingerprint topography of the finger, wherein the respective fingers of some of the time-sequences are known to be live fingers and the respective fingers of some other of the time-sequences are known to be spoof fingers. The method also comprises training a machine learning algorithm on the plurality of time-sequences to produce a model of the machine learning algorithm for differentiating between a live finger and a spoof finger.

The present disclosure relates to a method performed in a fingerprint analysis system for facilitating differentiating between a live finger and a spoof finger. The method comprises acquiring a plurality of time-sequences of images, each of the time-sequences showing a respective finger as it engages a detection surface of a fingerprint sensor. Each of the time-sequences comprises at least a first image and a last image showing a fingerprint topography of the finger, wherein the respective fingers of some of the time-sequences are known to be live fingers and the respective fingers of some other of the time-sequences are known to be spoof fingers. The method also comprises training a machine learning algorithm on the plurality of time-sequences to produce a model of the machine learning algorithm for differentiating between a live finger and a spoof finger.

A method and control system for generating and updating digital maps using a plurality of passages along a road portion by at least one road vehicle is provided. The method comprises obtaining positioning data and sensor data of each passage from the at least one road vehicle. Further, the method comprises forming a sub-map representation of the surrounding environment at each obtained longitudinal position based on the obtained sensor data, and estimating a longitudinal error for each obtained longitudinal position within each segment. Furthermore, the method comprises determining a new plurality of longitudinal positions of each road vehicle for each passage by applying the estimated longitudinal error on each corresponding obtained longitudinal position, and applying the determined new plurality of longitudinal positions on associated sensor data in order to generate a first layer of a map representation of the surrounding environment along the road portion.