Abstract: A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.

Abstract: A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.

Abstract: A single-site color image, such as a Bayer CCD image, is converted to a color space image using the resource of a Graphics Processing Unit (GPU). The Bayer image is loaded into the GPU along with commands to cause the texture engine in the GPU to use the Bayer image as a source texture and to compute, for each pixel in a destination image having same dimensions as the single-site color camera image, interpolated neighbor pixel values from the single-site color camera image for the remainder of said colors. A code image can be used to provide, for each pixel in the destination image, a value for each combination of color space image color and each Bayer image color. Each pixel is then computed as a sum of a product of each code image. value and a corresponding value selected from the corresponding source texture pixels and an interpolation of neighboring source texture pixels.

Abstract: A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.

Abstract: A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.

Abstract: A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.

Abstract: A method for determining a similarity score of a target object with respect to a model object. The target object is in a plane and the model object is represented by a model feature vector. The method comprises generating regions of the plane according to a first mass distribution of the target object and a second mass distribution of a part of the target object. Each of the generated regions has a corresponding mass distribution indicator. The method further comprises calculating a target feature vector for the target object according to at least one of the corresponding mass distribution indicators. Finally, the method computes the similarity score using the target feature vector and the model feature vector.

Abstract: A geometric hashing method usable by a machine vision system for model-based recognition of an object. More specifically, in a computer having a texture engine, a method of pattern matching for recognition of objects within an image. The method comprises the following steps: deriving at least one target primitive representative of the image; forming at least one basis from at least one target primitive; in the texture engine, determining, for each one of the at least one basis, an affine invariant representation of the at least one target primitives; and identifying, using the affine invariant representation, at least one predefined model primitives that at least partially matches the at least one target primitives.

Abstract: A method for recognizing an object in a target image using model primitives comprising an additive primitive and a subtractive primitive; weights are assigned to the additive and subtractive primitives; a target primitive is derived for the object; associations are determined between the target primitive and the model primitives; a similarity score is computed for the target primitive with respect to the model primitives; the similarity score is increased for each association between the target primitive and the additive primitive and decreased for each association between the target primitive and the subtractive primitive; the weights determine an amount by which the similarity score is increased or decreased for each of the associations.

Abstract: A method for determining a similarity score of a target object with respect to a model object. The target object is in a plane and the model object is represented by a model feature vector. The method comprises generating regions of the plane according to a first mass distribution of the target object and a second mass distribution of a part of the target object. Each of the generated regions has a corresponding mass distribution indicator. The method further comprises calculating a target feature vector for the target object according to at least one of the corresponding mass distribution indicators. Finally, the method computes the similarity score using the target feature vector and the model feature vector.

Abstract: A model-based object recognition system operates to recognize an object on a predetermined world surface within a world space. An image of the object is acquired. This image is a distorted projection of the world space. The acquired image is processed to locate one or more local features of the image, with respect to an image coordinate system of the image. These local features are mapped a world coordinate system of the world surface, and matched to a model defined in the world coordinate system. Annotations can be arranged as desired relative to the object in the world coordinate system, and then inverse-mapped into the image coordinate system for display on a monitor in conjunction with the acquired image. Because models are defined in world coordinates, and pattern matching is also performed in world coordinates, one model definition can be used by multiple independent object recognition systems.