Hiroshi Murase

In contrast to the traditional approach, visual recognition is formulated as one of matching appearance rather than shape. For any given robot vision task, all possible appearance variations define its visual workspace. A set of images is obtained by coarsely sampling the workspace. The image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the visual workspace is represented as a continuous appearance manifold. Given an unknown input image, the recognition system first projects the image to eigenspace. The parameters of the vision task are recognized based on the exact location of the projection on the appearance manifold. An efficient algorithm for finding the closest manifold point is described. The proposed appearance representation has several applications in robot vision. As examples, a precise visual positioning system, a real-time visual tracking system, and a real-time temporal inspection system are described.

We propose a weather recognition method from in-vehicle camera images that uses a subspace method to judge rainy weather by detecting raindrops on the windshield. "Eigendrops" represent the principal components extracted from raindrop images in the learning stage. Then the method detects raindrops by template matching. In experiments using actual video sequences, our method showed good detection ability of raindrops and promising results for rainfall judgment from detection results.

A real-time vision system is described that can recognize 100 complex three-dimensional objects. In contrast to traditional strategies that rely on object geometry and local image features, the present system is founded on the concept of appearance matching. Appearance manifolds of the 100 objects were automatically learned using a computer-controlled turntable. The entire learning process was completed in 1 day. A recognition loop has been implemented that performs scene change detection, image segmentation, region normalizations, and appearance matching, in less than 1 second. The hardware used by the recognition system includes no more than a CCD color camera and a workstation. The real-time capability and interactive nature of the system have allowed numerous observers to test its performance. To quantify performance, we have conducted controlled experiments on recognition and pose estimation. The recognition rate was found to be 100% and object pose was estimated with a mean absolute error of 2.02 degrees and standard deviation of 1.67 degrees.