220 results about "Computer vision" patented technology

Systems and techniques for an optical scanning microscope and/or other appropriate imaging system includes components for scanning and collecting focused images of a tissue sample and/or other object disposed on a slide. The focusing system described herein provides for determining best focus for each snapshot as a snapshot is captured, which may be referred to as “on-the-fly focusing.” The devices and techniques provided herein lead to significant reductions in the time required for forming a digital image of an area in a pathology slide and provide for the creation of high quality digital images of a specimen at high throughput.

The present invention relates to a method to make effective use of display space. In an embodiment of the invention, given a heterogeneous set of images along with metadata or nearby text, similar images are recursively clustered into a k-tree using the k-means algorithm. In an embodiment of the invention, the invention is particularly useful for showing image search results on small mobile devices.

Systems, methods, and apparatus for neuro-robotic tracking point selection are disclosed. A described example method to control a robot arm includes presenting one or more potential trackable features of a target object, emphasizing at least one of the potential trackable features, determining a selection of one of the emphasized features as a tracking point by monitoring a first mental response to emphasizing the feature, and effectuating an end goal via a robot by tracking the selected feature and effectuating a position based on the selected feature.

An information processing apparatus includes an image pickup unit, an extracting unit, an estimating unit, a categorizing unit, and a recording control unit. The image pickup unit captures an image of a subject. The extracting unit extracts a human figure from the captured image of the subject captured by the image pickup unit. The estimating unit estimates a posture of the human figure extracted by the extracting unit. The categorizing unit categorizes the posture of the human figure estimated by the estimating unit into a previously prepared pose. The recording control unit controls recording of the captured image on the basis of the pose that the posture of the human figure is categorized into by the categorizing unit.

The invention concerns a method and a system for purposes of registering the position of a vehicle (1) in a defined region (3), wherein a digital map of the defined region (3) is created, having a defined coordinates system, wherein the digital map includes stationary reference features (T1) with a unique identifying feature, before digital images are recorded of at least a sub-region of the defined region (3), preferably of the whole defined region (3), for purposes of registering and detecting further reference features (T1, T2, T3), wherein stationary and/or temporary reference features (T2, T3) without unique identifying features are also registered and detected, and are added to the digital map and/or an associated buffer store, so that the absolute position of the vehicle (1) in the defined region (3) can subsequently be determined, in that a digital image of a portion of the defined region (3) is recorded by the vehicle (1), and in the digital image reference features (T1, T2, T3) are detected and optionally identified, wherein the determination of absolute position is undertaken on the basis of the stationary and/or temporary reference features (T1, T2, T3) that have been detected and optionally identified.

The invention provides a vehicle and a method for detecting geometric parameters of tracks. The vehicle and the method are used for detecting data of the grooved tracks. The vehicle and the method have the advantages that laser displacement sensors, acceleration sensors, gyroscope sensors and the like are arranged on the vehicle for detecting the geometric parameters of the tracks, errors in sampled data of the laser displacement sensors due to inclination of a vehicle body can be corrected by a processor, accordingly, corrected data can be obtained, and actual geometric parameter data of the tracks can be generated by the processor by the aid of the corrected data and detection data acquired by the gyroscope sensors and the acceleration sensors; the data of the grooved tracks can be detected by the aid of the vehicle and method for detecting the geometric parameters of the tracks, and the generated geometric parameter data are high in accuracy by means of error correction.

The invention discloses a maneuvering extended target tracking method based on unscented Kalman filter, and belongs to the field of radar maneuvering target tracking. The method comprises the steps that according to characteristics of high-resolution range profile measurement information and a maneuvering characteristic of an extended target, and by utilizing various maneuvering modes which support functions to precisely describe the extended target, and finally based on a combination of the unscented Kalman filter and a multiple model algorithm, joint tracking of motion states and extension forms of the extended target is achieved. According to the maneuvering extended target tracking method based on the unscented Kalman filter, high-resolution radar range profile measurement information can be fast and precisely utilized, and precise joint estimation is conducted on the motion states and the extension forms of the extended target. Engineering is easy to achieve, and the method has a strong engineering application value and a popularization prospect.

The present invention, called Color Spectral Imaging (CSI), generally pertains to a method of displaying colorized two-dimensional medical images of human anatomy. Specifically, the present invention pertains to a method of assigning predetermined range of colors to computed tomography images for enhanced visualization.

The invention provides a method and a device for an integrating two-dimensional code with an image. The method of the invention comprises steps of adjusting the attributes of part of points in the two-dimensional code to enable the attributes of part of the points to be close to the attributes of the corresponding areas in the first image according to attribute information of a first image and attribute information of the points in the two-dimensional code of the first image, wherein the two-dimensional identification result of color lumps to which part of the points the attributes of which are not adjusted belong to is different from the two-dimensional recognition result of the area in the first image corresponding to the part of the points, and integrating the two-dimensional code with the first image to obtain a second image, wherein the attributes of points of the two-dimensional code are adjusted. The invention enables the two-dimensional code to be more matched with the environment color.

The invention discloses a tumor MRI weak supervised learning analysis modeling method, which comprises the following steps: S1, constructing a tumor MRI segmentation network based on a full convolutional neural network to realize tumor MRI preliminary segmentation; S2, taking the tumor MRI segmentation network as a generator, taking the classification model as a discriminator, and proposing a generative adversarial training algorithm of the tumor MRI segmentation network; and S3, taking unlabeled image data in the medical image as additional input condition information of the generator model and the discriminator model, guiding a data generation process, and enhancing the stability of the segmentation-generative adversarial network. The invention also discloses a model established by usingthe tumor MRI weak supervised learning analysis modeling method. According to the method, the tumor target region and the endangered organ can be more accurately and automatically segmented under thecondition of fewer training samples, and the method is applied to target region and endangered organ sketching of tumor radiotherapy.

A method and apparatus for recognizing a protrusion on a face is proposed. The apparatus forms two images, wherein one is formed in a condition in which a target is lighted and another is formed in a condition in which the target is non-lighted. Face regions are detected from the images respectively and then are compared each other. Then, analyzing change in intensity for indicating change in contrast of the compared regions is performed. Based on the result of the analyzing, it is determined whether there is a protrusion in a face presented in the images.

Methods and systems for reconstructing an object from observations of interaction of the object with a physical system.

The invention discloses a wifi-based location fingerprint positioning method. The method particularly comprises the following steps: 1, during a preparation process, wireless APs are deployed and reference points are selected and marked; 2, a fingerprint database is built, and data are acquired and a filtering technology is adopted to complete building of the fingerprint database; and 3, online matching is carried out, and a dynamic joint WKNN algorithm is adopted for indoor positioning. According to the wifi-based location fingerprint positioning method, a new data acquisition mode and the filtering technology are adopted for completing building of the fingerprint database, the dynamic joint WKNN algorithm is combined for indoor positioning, the fingerprint database information accuracy and the online matching precision are improved, and stable positioning is realized.

An imaging apparatus includes: an imaging unit that respectively generates, with imaging devices different from one another, a first captured image with a specific direction of a subject set in a longitudinal direction, a second captured image with an orthogonal direction orthogonal to the specific direction set in a longitudinal direction and including a subject adjacent to one side of the orthogonal direction of the subject included in the first captured image, and a third captured image with the orthogonal direction set in a longitudinal direction and including a subject adjacent to the other side of the orthogonal direction of the subject included in the first captured image; a detecting unit that detects a state of the imaging apparatus; and a control unit that determines, based on the detected state, a range of a target image as a target of display or recording among the first to third captured images.

A method of detecting a target in a scene comprises the steps of generating a comparison of the value of data elements in first and second data sets, the data elements corresponding to returns from the same part of the scene and setting a detection threshold value for the comparison so as to detect targets entering said that part of scene The method provides improved target detection in the presence of clutter.

Disclosed herein is chirography system including a chirography stylus fitted with an ultrasonic transducer tip and a font frame reader employing sensors at reference points of a font coordinate system. The system may be provided with a symbol recognition module adapted to identify symbol path traces of the stylus as the stylus traces the path guided by a cue card for a handwritten symbol. The system may also include an output for affirming successful recognition of a spatial chirography symbol by audibly expressing the identified symbol when the recognition succeeds and/or audibly prompting for another attempt when the recognition procedure fails. The system may employ one of physical and electronic cue cards including symbols adapted to be traced during a learning session.

The invention provides a speed measurement method for measuring the speed by the adoption of two cameras. The method comprises the steps that the first camera and the second camera are adopted for capturing images of a moving object to be measured; according to a point to be measured on the object to be measured, the azimuth angle of inclined light, incoming to the first camera, of the point to be measured on the object to be measured and the azimuth angle of inclined light, incoming to the second camera, of the point to be measured on the object are obtained according to the positions of the images, generated in the first camera and the second camera, of the object to be measured, and position coordinates, on different measurement points of a movement track of the point to be measured, of the point to be measured on the object to be measured are obtained; according to the position coordinates, on different measurement points of a movement track of the point to be measured, of the point to be measured on the object to be measured, the sum of the distance between adjacent measurement points of the point to be measured of the object to be measured is obtained, and the movement speed of the object to be measured is obtained according to measurement time. The invention further correspondingly provides a speed measurement device and a terminal. According to the speed measurement method and device and the terminal, the movement speed of the object, to be measured, in curvilinear movement can be measured by the adoption of the cameras.

One or more embodiments of the invention provide a system and method for processing an infrared image to receive infrared image data of a non-uniform scene, apply column noise filter correction to the infrared image data, and/or apply row noise filter correction to the infrared image data, and provide corrected infrared image data based on the column and/or row noise filter correction as infrared output image data.

A system, method, and computer-readable medium are disclosed for dynamically controlling a multi-modal camera system to take advantage of the benefits of sensing gestures with a 2D camera, while overcoming the challenges associated with 2D cameras for performing gesture detection. In certain embodiments, the multi-modal camera system includes an RGB camera and a depth camera, thus providing both a 2D and a 3D capture mode.