摘要:
The invention relates generally to edge detection and presentation in thermal images. Infrared and visible light images comprising at least partially overlapping target scenes are analyzed. An edge detection process is performed on the visible light image to determine which pixels represent edges in the target scene. A display image is generated in which some pixels include infrared image data and in which pixels corresponding to edges in the visible light image include a predetermined color and do not include corresponding infrared image data to emphasize edges. Edge pixels in the display image can include exclusively the predetermined color, or in some examples, a blend of a predetermined color and visible light image data. Methods can include replacing one or the other of visible light edge pixels or corresponding infrared pixels with the predetermined color before combining the visible light and infrared image data to create a display image.
摘要:
A product recognition system comprises a product image data collector arranged to capture image data which is representative of an image of a product item. The product recognition system also comprises an acoustic energy source arranged to emit acoustic energy towards the product item. The product recognition further comprises a product acoustic data collector arranged to (i) capture acoustic energy deflected from the product item, (ii) process the captured acoustic data which has been deflected from the product item to provide product acoustic data which is representative of one or more characteristics of the product item, and (iii) compare the product acoustic data with a store of reference acoustic data to provide one or more subsets of items against which the captured image data can be compared to identify the product item.
摘要:
A method for fusing 2D fluoroscopic images with 2D angiographic images for real-time interventional procedure guidance includes using a 2-dimensional angiographic image to detect injection of a contrast agent into an anatomical structure, where the contrast agent first appears in a detected image frame, subtracting a background image from the detected image frame and binarizing the subtracted image frame to segment the anatomical structure from the subtracted image frame, registering the segmented anatomical structure with a predefined shape model of the anatomical structure to generate an anatomical mask, generating an anatomical probability map from the anatomical mask using intensity information from the subtracted image frame, where the anatomical probability map expresses a probability of a pixel in the subtracted image frame belonging to the anatomical structure, and fusing the angiographic image with one or more subsequently acquired 2-dimensional fluoroscopic images of the anatomical structure using the anatomical probability map.
摘要:
Approaches are described for managing the processing of image or video data captured by a portable computing device. The device provides a set of images to a remote server executing “in the cloud”. The set of images can include a reference image and at least one other image captured subsequent or prior to the reference. Upon receiving the set of images at the remote server operating, the remote server can process the images to determine a similarity between the reference image and each of the other images. Thereafter, each image having a similarity value above a similarity value threshold can be aligned with the reference image, and the pixel values for corresponding locations in each of the images can be combined to create a processed image. The processed images can be provided to the computing device from the remote server, where the user can decide to accept or discard the image.
摘要:
An image processing system combines higher-resolution panchromatic images and lower resolution multispectral images using a hyperspherical color space pan-sharpening technique. By converting the multispectral images into a hyperspherical color space, the intensities of the multispectral images can be intensity matched to the intensities of the panchromatic image and then retransformed back to the original color space. The intensity matching can utilize a number of techniques, including, but not limited to, direct substitution of the intensities of the panchromatic image for the intensities of the multispectral images, modification of the intensities of the multispectral images based on predefined statistical models and modification of the intensities of the multispectral images based on dynamically generated statistical models and a selected sharpening parameter β.
摘要:
A method and system is disclosed for tracking object clusters. The method comprises obtaining a first sensor image and a second sensor image. Angular measurements between objects of the first sensor image are determined. Angular measurements between objects of the second sensor image are also determined. Angular measurements from the first sensor image are compared to angular measurements of the second image, and correlated object clusters are identified. The sensor system includes a command and decision unit that receives a first sensor image and a second sensor image. The command and decision unit determines angular measurements for the first sensor image, and determines angular measurements for the second sensor image. The command and decision unit compares the angular measurements for the first sensor image to the angular measurements for the second sensor image, and identifies correlated object clusters based on the comparison.
摘要:
An electro-optical system and method are provided for analyzing images of a scene to identify the presence of a target color, such as human skin tones. The system includes a thermal detector for obtaining a thermal image of the scene within a thermal waveband. The system also includes at least one additional detector for obtaining at least one additional image of the scene at an additional waveband different from the thermal waveband. The system also includes a controller. The controller is configured to: process the thermal image to identify portions of the scene having a temperature exceeding a threshold value; process the additional image to identify portions of the scene having a target color; and output a positive response if a same portion of the scene is identified in the thermal image and the additional image.
摘要:
A methodology for detecting image anomalies in a target area for classifying objects therein, in which at least two images of the target area are obtained from a sensor representing different polarization components. The methodology can be used to classify and/or discriminate manmade objects from natural objects in a target area, for example. A data cube is constructed from the at least two images with the at least two images being aligned, such as on a pixel-wise basis. A processor computes the global covariance of the data cube and thereafter locates a test window over a portion of the data cube. The local covariance of the contents of the test window is computed and objects are classified within the test window when an image anomaly is detected in the test window. For example, an image anomaly may be determined when a matrix determinant ratio of the local covariance and the global covariance exceeds a probability ratio threshold. The window can then be moved, e.g., by one or more pixels to form a new test window in the target area, and the above steps repeated until all of the pixels in the data cube have been included in at least one test window.
摘要:
A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.
摘要:
According to an illustrative embodiment, a method for detecting a document includes capturing a first plurality of images of a document at a first wavelength of electromagnetic radiation, capturing a second plurality of images of the document at a second wavelength of electromagnetic radiation, and assembling the first and second pluralities of images to form one or more images of the document.