Abstract: Apparatus that performs automatic gain control (AGC) for an electronic imaging camera, especially in outdoor surveillance applications. A fiber optic link is used to collect ambient light and couple this light onto a small portion of a light sensing array of the camera. A reference voltage produced by the light sensing array in response to the light from the fiber is used by AGC circuits in the camera to control the integration time of light sensing elements of the array, the gain of the camera's video amplifier, and lens aperture, if necessary. These camera gain controls are adjusted to maintain the reference voltage derived from the light provided by the fiber optic link to be within a predefined range as the ambient light level varies due to weather conditions and time of day. Methods of providing automatic gain control correction are also disclosed.

Abstract: An automated license plate locator and reader (10) which provides novel methods for 1) correcting for perspective distortion (16), 2) locating the license plate (20), 3) reading the license plate (22) and 4) improving the confidence rating of the output signal (228). The novel method for accommodating a wide range of viewing geometries involves warping the image to eliminate perspective distortion of the plate resulting from roadside camera placement. The novel method for locating plates involves correlating an "idealized" edge template of a license plate with an edge-enhanced version of the image. Edge enhancement and shadow reduction is achieved by applying a Laplacian operator over the input image. Performance is further improved by filtering out distracting edges within the resulting correlation surface and then locating the highest peaks within this filtered correlation surface. The location of the highest peaks provides the location of the plate.

Abstract: A video image processor (100) for processing video images performing the steps of generating video images (103) with a multi-spectral video source (102), converting analog color data contained in the generated video images (103) to digital color data for subsequent signal processing, extracting the digital color data from designated areas of the generated video images and utilizing the extracted digital color data for identifying a color distinguishable from a background color. Thus, the video image processor (100) processes the generated video images and has an intrinsic immunity to the effects of shadows by exploiting multi-spectral color information to distinguish, for example, a passing vehicle from the roadway 116. In a preferred embodiment, the video image processor (100) includes a multi-spectral video source (102) for generating the video images.

Abstract: Image data compression is implemented by partitioning an image into relatively small blocks of pixels, matching each block to an orthogonal icon, and extracting attributes associated with the icon. A table of these orthogonal icons and attributes represents a data compressed image. Each block is processed separately from all other blocks. Orthogonal processing is used to preserve orthogonal features while attenuating non-orthogonal features. An optimum set of orthogonal icons and an optimum set of attributes for each icon further improves data compression and fidelity. The optimal set of orthogonal icons includes a flat icon, an edge icon, a ribbon icon, a corner icon, and a spot icon. An optimal set of attributes includes average intensities, intensity transition position and separation, and angle of the principal axes.

Abstract: Image data is processed by a low level feature detection processor that extracts low level features from an image. This is accomplished by converting a matrix of image data into a matrix of orthogonal icons that symbolically represent the image scene using a predetermined set of attributes. The orthogonal icons serve as the basis of processing by means of a high level graph matching processor which employs symbolic scene segmentation, description, and recognition processing that is performed subsequent to the low level feature detection. This processing generates attribute graphs representative of target objects present in the image scene. High level graph matching compares predetermined attributed reference graphs to the sensed graphs to produce a best common subgraph between the two based on the degree of similarity between the two graphs. The high level graph matching generates a recognition decision based on the value of the degree of similarity and a predetermined threshold.

Abstract: Data decompression of an image is implemented by reconstructing blocks of pixels from a table that stores orthogonal icons and related attributes representing a data compressed image. Each block of pixels is processed independently of all other blocks. Orthogonal processing is employed to reconstruct orthogonal features that relate to manufactured elements in an image. An optimum set of orthogonal icons and an optimum set of attributes for each icon are employed to further improve data decompression and fidelity. The optimal set of orthogonal icons includes a flat icon, an edge icon, a ribbon icon, a corner icon and a spot icon. The optimal set of attributes includes average intensities, intensity transition position and separation, and angle of the principal axis.

Abstract: In the disclosed image-analysis scheme, a processing window of M by N pixels is successively scanned in single-pixel steps over a sensed image, with the centroid of the image data contained in each window position then being determined. When a pixel-by-pixel tabulation is made of the number of times each pixel has been determined to be the windowed-data centroid, those pixels having the higher tabulated centroid counts will tend to be the intra-image locations of any objects which are smaller than about M/2 by N/2 pixels.