Abstract: An image synthesizing device for synthesizing a second image of an object in a predetermined illumination condition from a first image of the object includes an illumination condition estimation section for estimating an illumination condition from a luminance value of the first image, and a normal information estimation section estimates normal information containing a normal direction of the object, with regard to a predetermined pixel in the first image. An error component information estimation section estimates information of an error component in the predetermined illumination condition, an image synthesizing section synthesizes the second image of the object in the predetermined illumination condition, and the normal information estimation section estimates normal information of a predetermined pixel from information of a plurality of the pixels in the first image.

Abstract: A normal line information estimation device for estimating normal line information of an object from an image of the object. The normal line information estimation device includes an illumination direction estimation section for estimating an illumination direction with respect to the object in the image from a luminance value of the image; a normal line information estimation section for estimating the normal line information of the object in the image based on the illumination direction; and a specular reflection component estimation section for estimating a specular reflection component of the image from the normal line information of the object and the illumination direction with respect to the object. The normal line information estimation section estimates the normal line information again from the image from which a specular reflection component has been removed in the specular reflection component section.

Abstract: A parameter estimation method for estimating a parameter by estimating maximum a posteriori probability for input data. Operation for the input data is expressed by an inner product for the input data and the inner product is replaced by a Kernel function. By using the calculation result of the kernel function, a parameter is estimated. The method includes a step (offline operation) for learning a correlation between a plurality of learning input data in which a parameter to be estimated is known and the parameter corresponding to each of the learning input data; and a step (online operation) for estimating the parameter for the estimating input data in which a parameter to be estimated is unknown, by using the learned correlation.

Abstract: The present invention provides a human detection device which detects a human contained in a moving picture, and includes the following: a spatiotemporal volume generation unit which generates a three-dimensional spatiotemporal image in which frame images that make up the moving picture in which a human has been filmed are arranged along a temporal axis; a spatiotemporal fragment extraction unit which extracts a real image spatiotemporal fragment, which is an image appearing in a cut plane or cut fragment when the three-dimensional spatiotemporal image is cut, from the generated three-dimensional spatiotemporal image; a human body region movement model spatiotemporal fragment output unit which generates and outputs, based on a human movement model which defines a characteristic of the movement of a human, a human body region movement spatiotemporal fragment, which is a spatiotemporal fragment obtained from a movement by the human movement model; a spatiotemporal fragment verification unit which verifies betwe

Abstract: An image synthesizing device for synthesizing a second image of an object in a predetermined illumination condition from a first image of the object includes an illumination condition estimation section for estimating an illumination condition from a luminance value of the first image, a normal information estimation section for estimating normal information containing a normal direction of the object, about a predetermined pixel in the first image, an error component information estimation section for estimating information of an error component in the predetermined illumination condition, and an image synthesizing section for synthesizing the second image of the object in the predetermined illumination condition, and the normal information estimation section estimates normal information of a predetermined pixel from information of a plurality of the pixels in the first image.

Abstract: A normal line information estimation device for estimating normal line information of an object from an image of the object. The normal line information estimation device includes an illumination direction estimation section for estimating an illumination direction with respect to the object in the image from a luminance value of the image; a normal line information estimation section for estimating the normal line information of the object in the image based on the illumination direction; and a specular reflection component estimation section for estimating a specular reflection component of the image from the normal line information of the object and the illumination direction with respect to the object. The normal line information estimation section estimates the normal line information again from the image from which a specular reflection component has been removed in the specular reflection component section.

Abstract: A parameter estimation method for estimating a parameter by estimating maximum a posteriori probability for input data. Operation for the input data is expressed by an inner product for the input data and the inner product is replaced by a Kernel function. By using the calculation result of the kernel function, a parameter is estimated. The method includes a step (offline operation) for learning a correlation between a plurality of learning input data in which a parameter to be estimated is known and the parameter corresponding to each of the learning input data; and a step (online operation) for estimating the parameter for the estimating input data in which a parameter to be estimated is unknown, by using the learned correlation.

Abstract: The present invention provides a human detection device which detects a human contained in a moving picture, and includes the following: a spatiotemporal volume generation unit which generates a three-dimensional spatiotemporal image in which frame images that make up the moving picture in which a human has been filmed are arranged along a temporal axis; a spatiotemporal fragment extraction unit which extracts a real image spatiotemporal fragment, which is an image appearing in a cut plane or cut fragment when the three-dimensional spatiotemporal image is cut, from the generated three-dimensional spatiotemporal image; a human body region movement model spatiotemporal fragment output unit which generates and outputs, based on a human movement model which defines a characteristic of the movement of a human, a human body region movement spatiotemporal fragment, which is a spatiotemporal fragment obtained from a movement by the human movement model; a spatiotemporal fragment verification unit which verifies betwe