Panasonic Corporation

Arasanathan Thayananthan

Roberto Cipolla

Masahiro Iwasaki

An image processing apparatus robustly performs segmentation on an image including an object such as a moving person with its deformation. The image processing apparatus includes: an image inputting unit which receives temporally successive images; a motion analyzing unit which calculates motions of blocks using at least two temporally different images and calculates, based on the motions of the blocks, temporal motion trajectories of the blocks in the temporally successive images; a distance calculating unit which calculates a distance indicating a similarity of the motions of the blocks, using a temporal motion trajectory of a block i and a temporal motion trajectory of a block other than the block i calculated by the motion analyzing unit; and a nonlinear space processing unit which projects the distance calculated by the distance calculating unit into a nonlinear space and performs the segmentation on a result of the projection in the nonlinear space.

Image processing method and image processing apparatus

An image processing device which simultaneously secures and extracts a background image, at least two object images, a shape of each object image and motion of each object image, from among plural images, the image processing device including an image input unit () which accepts input of plural images; a hidden parameter estimation unit () which estimates a hidden parameter based on the plural images and a constraint enforcement parameter, which indicates a condition of at least one of the hidden parameters, using an iterative learning method; a constraint enforcement parameter learning unit () which learns a constraint enforcement parameter related to the hidden parameter using an estimation result from the hidden parameter estimation unit as a training signal; and a complementary learning unit () which causes the estimation of the hidden parameter and the learning of the constraint enforcement parameter, which utilize the result from the learning of the hidden parameter, to be iterated.

Growing community of inventors

Essex, United Kingdom

Arasanathan Thayananthan