A point which requires visual attention is added to map data. A map data generation device acquires image data in which the outside is captured from a vehicle by an input device and a point data of the vehicle, associates both data, and generates a visual saliency map acquired by estimating fluctuation of visual saliency based on the image data by the visual saliency extraction unit. Then, whether or not a point or a section indicated by position information corresponding to the visual saliency map is a point or a section which requires visual attention is analyzed based on the visual saliency map by an analysis unit, and the point or the section which requires the visual attention is added to the map data based on an analysis result of the analysis unit by an addition device.

This disclosure describes techniques for of improving an image readability via one or more patterns that may be taken using different light wavelengths. A first pattern may include alphanumeric characters, barcodes, Quick Response (QR) codes, or a similar unique code that can be used to identify vehicle license plates, road signals, charts, placards, advertisements, or the like, using a light wavelength such as a visible light wavelength. A paired second pattern may include a copy of the first pattern or a different pattern but constructed with a different material that responds to a different light wavelength e.g., Ultra-Violet (UV) light wavelength. In one example, the paired second pattern may be identified and used as a reference for identifying the first pattern. This technique of using multi-patterns for identifying road signals, charts, placards, advertisements, and particularly the vehicle license plates during extreme weather conditions may improve law enforcement operations or other similar purposes.

Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to adapt a computing device to classify physical features in a deployment environment. In a particular implementation, computing resources may be selectively de-allocated from at least one of one or more elements of a computing architecture based, at least in part, on assessed impacts to the one or more elements of the computing architecture.

The present disclosure relates to an image processing method and device, an electronic apparatus and a storage medium. The method comprises: acquiring an iris image group comprising at least two iris images to be compared; detecting iris locations in the iris images and segmentation results of iris areas in the iris images; performing multi-scale feature extraction and multi-scale feature fusion on an image area corresponding to the iris locations, to obtain iris feature maps corresponding to the iris images; performing comparison using the segmentation results and the iris feature maps respectively corresponding to the at least two iris images, and determining whether the at least two iris images correspond to the same object based on a comparison result of the comparison. Embodiments of the present disclosure realize accurate comparison of iris images.

In one embodiment, a method for solution inference using neural networks in LiDAR localization includes constructing a cost volume in a solution space for a predicted pose of an autonomous driving vehicle (ADV), the cost volume including a number of sub volumes, each sub volume representing a matching cost between a keypoint from an online point cloud and a corresponding keypoint on a pre-built point cloud map. The method further includes regularizing the cost volume using convention neural networks (CNNs) to refine the matching costs; and inferring, from the regularized cost volume, an optimal offset of the predicted pose. The optimal offset can be used to determine a location of the ADV.

Techniques are disclosed for generating a vector image from a raster image, where the raster image is, for instance, a photographed or scanned version of a hand-drawn sketch. While drawing a sketch, an artist may perform multiple strokes to draw a line, and the resultant raster image may have adjacent or partially overlapping salient and non-salient lines, where the salient lines are representative of the artist's intent, and the non-salient (or auxiliary) lines are formed due to the redundant strokes or otherwise as artefacts of the creation process. The raster image may also include other auxiliary features, such as blemishes, non-white background (e.g., reflecting the canvas on which the hand-sketch was made), and/or uneven lighting. In an example, the vector image is generated to include the salient lines, but not the non-salient lines or other auxiliary features. Thus, the generated vector image is a cleaner version of the raster image.

In a method for reconstruction of a feature in an environmental scene of a road, a 3D point cloud of the scene and a sequence of 2D images of the scene are generated. A portion of candidates of 3D points of the 3D point cloud is identified by projecting the 3D points to each of the 2D images, determining a plurality of candidates of the 3D points of the 3D point cloud representing the feature by semantic segmentation in each of the images, projecting the candidates of the 3D points on a plane of the road in each of the 2D images, and selecting those candidates of the 3D points staying in a projection range on the road in each of the 2D images. The selected candidates of the 3D points are merged for determining estimated locations of the feature. The feature can be modeled by generating a fitting curve along the estimated locations.

Systems and methods for generating interpolated images are disclosed. In examples, image features are extracted from a first image and a second image; such image features may be warped using first and second plurality of parameters. A first candidate intermediate frame may be generated based on the warped first features and the warped second features. Multi-scale features associated with the image features extracted from the first image and the second image may be obtained and warped using the first and second plurality of parameters. A second candidate intermediate frame may be generated based on the warped first multi-scale features and the warped second multi-scale features. By blending the first candidate intermedia frame with the second candidate intermediate frame, an interpolated image may be generated.

A method for automatically creating an equipment inventory from a plurality of images of a site. The method includes receiving, by a processor, the plurality of images of the site, labeling, by the processor, equipment present in each image of the plurality of images of the site, creating, by the processor, an overlap curve for neighboring images of the plurality of images of the site, determining, by the processor, a useful image of each side of the site based on the overlap curve, the useful image including a subset of the plurality of images, creating, by the processor, an overlay of equipment in the useful image of each side of the site, counting, by the processor, equipment present in the overlay of each side of the site, and generating, by the processor, the equipment inventory by adding a number of equipment counted in the overlay of each side of the site.

Methods and systems for extracting personal data from a sensitive document are provided. The system includes a document prediction module, a cropping module, a denoising module, and an optical character recognition (OCR) module. The document prediction module predicts type of document of the sensitive document using a keypoint matching-based approach and the cropping module extracts document shape and extracts one or more fields comprising text or pictures from the sensitive document. The denoising module prepares the one or more fields for optical character recognition, and the OCR module performs optical character recognition on the denoised one or more fields to detect characters in the one or more fields.