Naoyuki Tsuruta

Tracking of 3D multi-part objects using multiple viewpoint time-varying sequences

Presents a shape and pose estimation method for 3D multi-part objects, the purpose of which is to easily map objects from the real world into virtual environments. In general, complex 3D multi-part objects cause unwanted self-occlusion and non-rigid motion. To deal with the problem, we employ multiple viewpoint time-varying sequences, since there is enough information to estimate the parameters in the sensory data. In our framework, to minimize the error between the selected image feature points and the estimated model parameters, we employ a model fitting procedure which can adaptively select corresponding pairs. We have demonstrated that our system works well both for single part objects and for multiple-part objects using real image data.

Multi-part Non-rigid Object Tracking Based on Time Model-Space Gradients

This paper presents a shape and pose estimation method for 3D multi-part objects, the purpose of which is to easily map objects from the real world into virtual environments. In general, complex 3D multi-part objects cause undesired self-occlusion and non-rigid motion. To deal with the problem, we assume the following constraints:

Image reconstruction using high-level constraints

In this paper, we propose a strategy to improve the performance of image reconstruction using a selective attention mechanism in a multi-layered neural network. The selective attention mechanism enables us to use top-down information as high-level and global constraints. The traditional algorithms using regularization techniques are quite sensitive to values of parameters, and it is quite difficult to select their appropriate values, because the algorithms use low-level and local constraints. Our strategy uses high-level and global constraints, and modifies the values of parameters locally and automatically.

A framework of image understanding based on PDP model. Proposition of ICE (image centered) system

One of the most important tasks in image understanding is to map visual information into symbolic concepts which describe an input scene. However, the mapping presents the following difficulties: 1) how to resolve the ambiguity in visual information; 2) how to reduce the redundancy of visual information; and 3) how to describe the scene efficiently using symbolic concepts. In this paper, we propose the ICE system, which is a framework of computer vision addressing the above three problems. We show a multilayered model based on the hypercolumn with selective attention mechanism can solve the first two problems. Then we describe how the ICE system is structurally constructed on the basis of the multilayered model.

A model generation method for object recognition task by pictorial examples

In this paper, we describe a method to construct automatically, from a series of images of objects, a model of an object class. The model is described by a set of 2 dimensional features of segmented regions and the relations among them. To make models of objects, we introduce the concept of the segmentation tree-which represents image segmentation at various levels of abstraction-and also a model generation method based on a series of segmentation trees. Using this segmentation tree, we can cope with the problem of diversity of segmentation patterns and can easily make stable object-models.<<ETX>>