Abstract: The classification and segmentation system of the current invention makes use of information from pixels of an image, namely the magnitude of the pixels, to run specific analytics to classify and segment the image pixels into different groups. This invention includes a system for processing an image, the system including an input device, a processor, a memory and a monitor. The input device is configured to receive image data, where the image data includes pixels and each pixel has a magnitude. The memory has instructions stored in it that, when executed by the processor, cause the processor to run calculations. The calculations include: calculating the log-magnitudes from the magnitudes of at least a plurality of the pixels, calculating standard deviations of the log-magnitudes for subsets of the plurality of pixels and compute an integral of the standard deviations over a desired range. The pixels are classified into different groups based on a value of the integral relative to one or more integral values.

Abstract: The classification and segmentation system of the current invention makes use of information from pixels of an image, namely the magnitude of the pixels, to run specific analytics to classify and segment the image pixels into different groups. This invention includes a system for processing an image, the system including an input device, a processor, a memory and a monitor. The input device is configured to receive image data, where the image data includes pixels and each pixel has a magnitude. The memory has instructions stored in it that, when executed by the processor, cause the processor to run calculations. The calculations include: calculating the log-magnitudes from the magnitudes of at least a plurality of the pixels, calculating standard deviations of the log-magnitudes for subsets of the plurality of pixels and compute an integral of the standard deviations over a desired range. The pixels are classified into different groups based on a value of the integral relative to one or more integral values.

Abstract: An automatic target recognition system with adaptive metric selection. The novel system includes an adaptive metric selector for selecting a match metric based on the presence or absence of a particular feature in an image and a matcher for identifying a target in the image using the selected match metric. In an illustrative embodiment, the adaptive metric selector is designed to detect a shadow in the image and select a first metric if a shadow is detected and not cut off, and select a second metric otherwise. The system may also include an automatic target cuer for detecting targets in a full-scene image and outputting one or more target chips, each chip containing one target. The adaptive metric selector adaptively selects the match metric for each chip separately, and may also adaptively select an appropriate chip size such that a shadow in the chip is not unnecessarily cut off.

Abstract: A synthetic aperture radar acquires an image of one or more objects and identifies them as targets. The objects are located in the proximity of clutter within the image such of trees, or a tree line. The radar acquires a SAR image having pixels descriptive of the clutter and the object(s). Regions having object pixels are identified within the synthetic aperture image using an object identification (algorithm), where the object identification (algorithm) utilizes one or more historically known target characteristics and one or more measured characteristic to obtain an output. Boundaries are identified for the one or more objects within the output using an object isolation, such as, for example, a Watershed transform. Clutter pixels are identified external to the one or more objects. The clutter pixels are suppressed from the synthetic aperture image thereby generating a clutter reduced image containing the one or more objects.

Abstract: An automatic target recognition system with adaptive metric selection. The novel system includes an adaptive metric selector for selecting a match metric based on the presence or absence of a particular feature in an image and a matcher for identifying a target in the image using the selected match metric. In an illustrative embodiment, the adaptive metric selector is designed to detect a shadow in the image and select a first metric if a shadow is detected and not cut off, and select a second metric otherwise. The system may also include an automatic target cuer for detecting targets in a full-scene image and outputting one or more target chips, each chip containing one target. The adaptive metric selector adaptively selects the match metric for each chip separately, and may also adaptively select an appropriate chip size such that a shadow in the chip is not unnecessarily cut off.

Abstract: A synthetic aperture radar acquires an image of one or more objects and identifies them as targets. The objects are located in the proximity of clutter within the image such of trees, or a tree line. The radar acquires a SAR image having pixels descriptive of the clutter and the object(s). Regions having object pixels are identified within the synthetic aperture image using an object identification (algorithm), where the object identification (algorithm) utilizes one or more historically known target characteristics and one or more measured characteristic to obtain an output. Boundaries are identified for the one or more objects within the output using an object isolation, such as, for example, a Watershed transform. Clutter pixels are identified external to the one or more objects. The clutter pixels are suppressed from the synthetic aperture image thereby generating a clutter reduced image containing the one or more objects.

Abstract: A synthetic aperture radar acquires an image of one or more objects and identifies them as targets. The objects are located in the proximity of clutter within the image such of trees, or a tree line. The radar acquires a SAR image having pixels descriptive of the clutter and the object(s). Regions having object pixels are identified within the synthetic aperture image using an object identification (algorithm), where the object identification (algorithm) utilizes one or more historically known target characteristics and one or more measured characteristic to obtain an output. Boundaries are identified for the one or more objects within the output using an object isolation, such as, for example, a Watershed transform. Clutter pixels are identified external to the one or more objects. The clutter pixels are suppressed from the synthetic aperture image thereby generating a clutter reduced image containing the one or more objects.

Abstract: Targets imaged by radar systems typically have shadows associated with them. Target detection and identification is enhanced by analyzing the shadow characteristics of a suspected target. Features of the shadow cast by the suspected target enhance the identification process. Authenticating the suspected target shadow as being indeed cast by the target comprises a) Generating a radar image using radar returns, the radar image containing both the target and its suspected target shadow; b) Forming a pentagonal perimeter adjacent to the target (within the radar image), the pentagonal perimeter chosen to contain the suspected target shadow, the pentagonal perimeter separating the target from its suspected target shadow; c) Testing the suspected target shadow within said pentagonal perimeter to authenticate that the suspected target shadow is cast by the target. One aspect of the testing performed on the suspect target shadow uses a 2 by 2 dilation and majority filter.

Abstract: A Radon transform based method that provides for target azimuth aspect estimation and target shape measurement. A Radon transform is applied to a binary (N×N pixels) target chip to extract target features that are then used to measure length, width, and diagonal features of the target. In parallel, these features are used to estimate the azimuth aspect angle, or size, of the target. The method is effective in discriminating targets from clutter. The method is also very time efficient and highly flexible in its operation because the features can automatically account for any target rotation or shift. The present invention also provides for a target acquisition system that employs the Radon transform based method for target azimuth aspect estimation.