Ken'ichi Morooka

Active modeling of 3-D objects: planning on the next best pose (NBP) for acquiring range images

We propose a new method of creating a complete model of a curved object from multiple range images acquired by showing it at different poses. The pose of the object is changed by a manipulator in order to view the object from some specified viewpoints. The pose is planned after each new image is merged into a unified representation. A rating function for the planning is defined to take into consideration the factors such as possibility of merging new data, registration accuracy and control point selection.

The effect of CyberDome, a novel 3-dimensional dome-shaped display system, on laparoscopic procedures

BackgroundLaparoscopic surgeons require extended experience of cases to overcome the lack of depth perception on a two-dimensional (2D) display. Although a three-dimensional (3D) display was reported to be useful over two decades ago, 3D systems have not been widely used. Recently, we developed a novel 3D dome-shaped display (3DD) system, CyberDome.Study designIn the present study, a total of 23 students volunteered. We evaluated the effects of the 3DD system on depth perception and laparoscopic procedures in comparison with the 2D, a conventional 3D (3DP) or the 2D high definition (HD) systems using seven tasks.ResultsThe 3DD system significantly improved depth perception and laparoscopic performance compared with the 2D system in six new tasks. We further found that the 3DD system shortened the execution time and reduced the number of errors during suturing and knot tying. The 3DD system also provided more depth perception than the 3DP and 2D HD systems.ConclusionsThe novel 3DD system is a promising tool for providing depth perception with high resolution to laparoscopic surgeons.

Real-Time Nonlinear FEM with Neural Network for Simulating Soft Organ Model Deformation

This paper presents a new method for simulating the deformation of organ models by using a neural network. The proposed method is based on the idea proposed by Chen et al. that a deformed model can be estimated from the superposition of basic deformation modes. The neural network finds a relationship between external forces and the models deformed by the forces. The experimental results show that the trained network can achieve a real-time simulation while keeping the acceptable accuracy compared with the nonlinear FEM computation.

Next Best Viewpoint (NBV) Planning for Active Object Modeling Based on a Learning-by-Showing Approach

The paper presents a method of creating a complete model of a curved object from a sequence of range images acquired by a fixed range finder. To accomplish the modeling fast and accurately in an optimal manner, we propose a new online viewpoint planning algorithm to choose the next best viewpoint (NBV) based on the already obtained partial model. The NBV is determined by evaluating factors such as possibility of merging new data, local shape changes, registration accuracy and control point distribution.

Computations on a spherical view space for efficient planning of viewpoints in 3-D object modeling

Viewpoint planning plays an important role in automatic 3D model generation. Previously (H, Zha et al., 1997), we proposed a viewpoint planning method to determine the next-best-viewpoint (NBV) for incremental model construction. Based on a current partial model, this algorithm provides quantitative evaluations on the suitability of viewpoints as the NBV. Since the evaluation is performed for all potential viewpoints, the NBV planning is very time-consuming. We present a novel method of discretizing a spherical view space by a look-up array which will highly facilitate the NBV evaluations. Two main issues are addressed: 1) a uniform tessellation of the spherical space and its mapping onto the 2D array; 2) incremental updating computations far evaluating viewpoints as the NBV. The efficiency of the method is verified by algorithmic analyses and experiments using a real modeling system.

Grasp planning for constricted parts of objects approximated with quadric surfaces

This paper presents a grasp planner which allows a robot to grasp the constricted parts of objects in our daily life. Even though constricted parts can be grasped more firmly than convex parts, previous planners have not sufficiently focused on grasping this part. We develop techniques for quadric surface approximation, grasp posture generation, and stability evaluation for grasping constricted parts. By modeling an object into multiple quadric surfaces, the planner generates a grasping posture by selecting one-sheet hyperbolic surfaces or two adjacent ellipsoids as constricted parts. When a grasping posture being generated, the grasp stability is evaluated based on the distribution of the stress applied to an object by the fingers. We perform several simulations and experiments to verify the effectiveness of our proposed method.

Self-organizing deformable model: a new method for fitting mesh model to given object surface

This paper presents a new method for projecting a mesh model of a source object onto a surface of an arbitrary target object. A deformable model, called Self-organizing Deformable Model(SDM), is deformed so that the shape of the model is fitted to the target object. We introduce an idea of combining a competitive learning and an energy minimization into the SDM deformation. Our method is a powerful tool in the areas of computer vision and computer graphics. For example, it enables to map mesh models onto various kinds of target surfaces like other methods for a surface parameterization, which have focused on specified target surface. Also the SDM can reconstruct shapes of target objects like general deformable models.

Next best viewpoint (NBV) planning for active object modeling based on a learning-by-showing approach

The paper presents a method of creating a complete model of a curved object from a sequence of range images acquired by a fixed range finder. To accomplish the modeling fast and accurately in an optimal manner, we propose a new online viewpoint planning algorithm to choose the next best viewpoint (NBV) based on the already obtained partial model. The NBV is determined by evaluating factors such as possibility of merging new data, local shape changes, registration accuracy and control point distribution.

Floor Sensing System Using Laser Reflectivity for Localizing Everyday Objects and Robot

This paper describes a new method of measuring the position of everyday objects and a robot on the floor using distance and reflectance acquired by laser range finder (LRF). The information obtained by this method is important for a service robot working in a human daily life environment. Our method uses only one LRF together with a mirror installed on the wall. Moreover, since the area of sensing is limited to a LRF scanning plane parallel to the floor and just a few centimeters above the floor, the scanning covers the whole room with minimal invasion of privacy of a resident, and occlusion problem is mitigated by using mirror. We use the reflection intensity and position information obtained from the target surface. Although it is not possible to identify all objects by additionally using reflection values, it would be easier to identify unknown objects if we can eliminate easily identifiable objects by reflectance. In addition, we propose a method for measuring the robots pose using the tag which has the encoded reflection pattern optically identified by the LRF. Our experimental results validate the effectiveness of the proposed method.

Fast 3D reconstruction of human shape and motion tracking by parallel fast level set method

This paper presents a parallel algorithm of the Level Set Method named the Parallel Fast Level Set Method, and its application for real-time 3D reconstruction of human shape and motion. The Fast Level Set Method is an efficient implementation algorithm of the Level Set Method and has been applied to several applications such as object tracking in video images and 3D shape reconstruction using multiple stereo cameras. In this paper, we implement the Fast Level Set Method on a PC cluster and develop a real-time motion capture system for arbitrary viewpoint image synthesis. To obtain high performance on a PC cluster, efficient load-balancing and resource allocation algorithms are crucial problems. We develop a novel optimization technique of load distribution based on the estimation of moving direction of object boundaries. In this technique, the boundary motion is estimated in the framework of the Fast Level Set Method, and the optimum load distribution is predicted and performed according to the estimated boundary motion and the current load balance. Experiments of human shape reconstruction and arbitrary viewpoint image synthesis using the proposed system are successfully carried out.