A stereo imaging device is capable of detecting a target with a high precision, while photographing a wide range. The stereo imaging device has an imaging unit 5 including a lens and an imaging sensor. The lens has a low distortion region and a high distortion region, the low distortion region being a portion having a distortion smaller than a predetermined amount, the high distortion region being a portion having a distortion larger than the low distortion region. A cutout unit outputs an image from which a range including a detection target has been cut out from an area photographed through the low distortion region, such output being performed for image photographed by a pair of imaging units when a detection target is present within an area photographed through the low distortion region. A detection unit detects a detection target based on the cutout image.

Computing systems for efficient incident management in large scale computer systems are described herein. In one embodiment, an incident management system can be configured to, in response to receiving a user input requesting an unidentified incident management service, convert an alphanumerical string of the user input into a pixelated matrix having multiple pixels individually corresponding to a character or number in the alphanumerical string. The incident management system can then feed the converted pixelated matrix into a neural network to identify one or more incident management services corresponding to the received user input with a corresponding probability value. The incident management system can then perform an application programming interface (API) call to execute a computer application to provide one of the identified incident management services to the user.

A text extraction computing method that comprises calculating an estimated character pixel height of text from a digital image. The method may scale the digital image using the estimated character pixel height and a preferred character pixel height. The method may binarizes the digital image. The method may remove distortions using a neural network trained by a cycle GAN on a set of source text images and a set of clean text images. The set of source text images and clean text images are unpaired. The source text images may be distorted images of text. Calculating the estimated character pixel height may include summarizing the rows of pixels into a horizontal projection, and determining a line-repetition period from the projection, and quantifying the portion of the line-repetition period that corresponds to the text as the estimated character pixel height. The method may extract characters from the digital image using OCR.

A method includes receiving, by a device, a first image of a scene and a second image of at least a portion of the scene. The method includes identifying a first plurality of features from the first image and comparing the first plurality of features to a second plurality of features from the second image to identify a common feature. The method includes determining a particular subset of pixels that corresponds to the common feature, the particular subset of pixels corresponding to a first subset of pixels of the first image and a second subset of pixels of the second image. The method also includes generating a first image quality estimate of the first image based on a comparison of a first degree of variation within the first subset of pixels and a second degree of variation within the second subset of pixels.

A method and an apparatus for storing a resource and an electronic device are provided. The method includes: extracting a resource with a storage size exceeding a preset capacity threshold, and backing up the extracted resource to a cloud server; obtaining link address information of the resource backed up to the cloud server; performing a clip processing on the extracted resource, and encapsulating the link address information corresponding to the extracted resource into the clip-processed resource; and replacing the extracted resource stored in an electronic device with the encapsulated resource.

A method for image processing, an electronic device, and a storage medium are provided. The method includes the following. For each processing method in a preset set of processing methods, a first feature parameter and a second feature parameter are determined according to image data to-be-processed, where the preset set includes at least two processing methods selected from whitening methods and/or normalization methods, and the image data to-be-processed includes at least one image data. A first weighted average of the first feature parameters is determined according to a weight coefficient of each first feature parameter, and a second weighted average of the second feature parameters is determined according to a weight coefficient of each second feature parameter. The image data to-be-processed is whitened according to the first weighted average and the second weighted average.

An image processing apparatus includes an input interface to acquire an image, and first to fourth controllers. The first controller performs image processing on the image. The second controller performs correction on an optical distortion in the image. The third controller performs recognition on the image. The fourth controller superimposes a result of the recognition onto the image and outputs a resulting image. The first controller can perform first and second image processing. The second controller can perform first and second correction processing. The third controller receives an input of the image, and outputs information indicating a location of a recognized object. The fourth controller receives an input of the image, and superimposes a drawing indicating the location of the recognized object onto a corresponding location in the image.

A method for processing point cloud data includes: point cloud data in a target scene and weight vectors of a first discrete convolution kernel are obtained; interpolation processing is performed on the point cloud data based on the point cloud data and the weight vectors of the first discrete convolution kernel to obtain first weight data, the first weight data representing weights of allocation of the point cloud data to positions corresponding to the weight vectors of the first discrete convolution kernel; first discrete convolution processing is performed on the point cloud data based on the first weight data and the weight vectors of the first discrete convolution kernel to obtain a first discrete convolution result; and a spatial structure feature of at least part of point cloud data in the point cloud data is obtained based on the first discrete convolution result.

An image unit converter system is provided. The system may include a user computing device comprising a memory storing conversion factor data. The user computing device is programmed to receive from a camera coupled to the user computing device an image of a drawing or list with original dimension units applied to the drawing or list that is viewable by a camera coupled to the computing device. The user computing device may also be programmed to automatically process the signal received from the camera and retrieve conversion factor data. Further, the user computing system may also be programmed to, using the conversion factor data retrieved, automatically convert all dimensions in the drawing or list according to a user defined unit conversion factor and display on the user computing device the drawing or list with converted units replacing the original dimension units in real time.

Disclosed is a system for identifying at least one optimum pre-processing technique for text extraction. A data receiving module receives an input image and an expected text pertaining to the input image. Furthermore, a performance module performs a plurality of pre-processing techniques on the input image in order to extract textual information, present in the input image, by using at least one text extraction technique. Subsequently, a recording module records processing time spent on each pre-processing technique performed on the input image. Further, a comparison module compares the textual information with the expected text. Further to comparing the textual information with the expected text, the ranking module may rank each of the plurality of pre-processing techniques based on a result of comparison between the textual information and the expected text, thereby identifying at least one optimum pre-processing technique for text extraction.