摘要:
A system for automatically tracking the location of a vehicle includes a visual image detector mounted on the vehicle for producing as the vehicle moves along a route digitized strips of image data representing successive panoramic views of scenery about the vehicle at respective locations along the route. A sparse tracking subsystem processes and stores only selected ones of the image data strips representing substantially spaced apart successive locations along the route, for use as a sparse database. A dense tracking subsystem processes and stores as a dense database every successive one of the image data strips representing location along the route, whereby the dense tracking subsystem provides more accurate location of the vehicle when it retraces some portion of the route than the sparse tracking subsystem. After the sparse and dense databases are established, the location of the vehicle in real time as it retraces the route is performed by the dense tracking subsystem matching current image data strips from the visual image detector with the dense database strips to determine the location of the vehicle, as long as the vehicle stays on the pre-established route. If the vehicles strays from the route, the system senses the deviation and switches to the sparse tracking system to search a broader area in less time than the dense tracking system to attempt to relocate the vehicle along the route, after which the system switches back to the dense tracking subsystem.
摘要:
A reflective rotund lens is positioned for projecting a panoramic picture of its horizontal surroundings at a given elevation onto a CCD array, for converting the picture into "pixel form" or an image signal. The image signal is digitized via an A/D converter circuit. A digital signal processor system is programmed for extracting a strip of pixel locations representative of an image ring mapped to pixel locations via superimposition upon the image, whereby all pixel locations outside of the image ring are eliminated by passing the pixels thereof through said A/D converter circuit at a rate higher than the conversion rate of the A/D converter circuit.
摘要:
A reflective rotund lens is positioned for projecting a panoramic picture of its horizontal surroundings at a given elevation onto a CCD array, for converting the picture into “pixel form” or an image signal. The image signal is digitized via an A/D converter circuit. A digital signal processor system is programmed for extracting a strip of pixel locations representative of an image ring mapped to pixel locations via superimposition upon the image, whereby all pixel locations outside of the image ring are eliminated by passing the pixels thereof through said A/D converter circuit at a rate higher than the conversion rate of said A/D converter circuit.
摘要:
A visual gyroscope system for detecting turns and straight line travel of a vehicle includes a visual image detector mounted on the vehicle, for producing sequential and successive digitized image data strips containing information identifying scenery about the vehicle at associated successive locations along the route travelled, A processor is programmed to extract from image detector each successive pair of image data strips, and rotate the second occurring strip of each pair until it matches the first occurring strip to obtain the incremental rotation and direction of rotation of the vehicle in its travel between strips. The incremental rotations between strips are accumulated and summed to obtain the total rotation upon completion of a turn, and along with the direction of rotation, identification of a right turn, left turn, u-turn, or straight line travel. Dead reckoning navigation is also provided via the inclusion of an odometer, for providing distance readings for the distance travelled between each successive image data strip.
摘要:
A method for detecting polyp candidates in tagged stool or non-tagged stool images without performing stool subtraction, includes: applying a filter to locations in image data of a colon including tagged or non-tagged stool to generate a response image based on a gradient magnitude, angle, and radius in relation to another location in the image data for each of the locations, wherein the locations are indicated in the response image as tagged or non-tagged stool based on their density or brightness within the response image; and selecting locations in the response image above a threshold as polyp candidates.
摘要:
A system and method for determining a location and a direction for viewing a protrusion, comprising: casting a plurality of rays in an outward direction from a point, wherein the point is inside a protrusion; selecting at least one of the plurality of rays for determining a location and a direction for viewing the protrusion; and determining the location and the direction for viewing the protrusion using the selected at least one of the plurality of rays.
摘要:
A computer-assisted diagnosis method for assisting diagnosis of anatomical structures in a digital volumetric medical image of at least one lung includes identifying an anatomical structure of interest in the volumetric digital medical image. The anatomical structure of interest is automatically segmented, in real-time, in a predefined volume of interest (VOI). Quantitative measurements of the anatomical structure of interest are automatically computed, real-time. A result of the segmenting step and a result of the computing step are displayed, in real-time. A likelihood that the anatomical structure of interest corresponds to a disease or an area warranting further investigation is estimating, in real-time, based on predefined criteria and the quantitative measurements. A warning is generated, in real-time, when the likelihood is above a predefined threshold.
摘要:
An exemplary embodiment of the present invention includes a method of visualizing an airway of a bronchial tree. The method includes generating a tree model from an airway segmentation of a bronchial tree, determining a lumen, a wall thickness, and an adjacent artery for a branch of the tree model, determining whether the lumen of the branch has a first abnormal state and the wall thickness of the branch has a second abnormal state based on the adjacent artery, and illustrating the branch in one of a plurality of visually distinct styles based on the first and second abnormal states.
摘要:
A system and method for 3D visualization of a pair of lungs are provided. The method comprises: segmenting image data of the pair of lungs and lung parenchyma; generating a 3D map as a function of the segmented image data; and rendering the 3D map as a color-coded semi-transparent 3D volume, wherein an opaque region highlights an area of interest.
摘要:
A method for providing automatic detection of curvature of a spine and computation of specific angles in images of the spine includes automatically displaying the curvature of the spine as a line in an image of the spine, and computing at least one of a first angle or a second angle based on the line of the curvature of the spine.