Ryuichi Oka Professor |
Mohamed Hamada Associate Professor |
Keitaro Naruse Assistant Professor |
Yuichi Yaguchi Assistant Lecturer |
Yu Nakajima Assistant Instructor |
First and foremost, the Image Processing Laboratory engages in research and development of image-based pattern recognition including some areas of Artificial Intelligence, database organisation, retrieval, and robotics. More specifically, as can be seen from the background information and the recent research publications of the members of the laboratory, 2-dimensional Continuous Dynamic Programming for non-linear image matching, 3D image reconstruction, object tracking in a time-varying image, image retrieval from video data, and extracion of the Internet community are our current focus.
Related to the recent progress of the web, a huge amount of multimedia data without index becomes available to store in our PC's. However, no sophistcated methodology to manage such data has been developed so far. So that we are solicited to attach an index to each data. Our research aim is to develop algorithms to realize automatic annotation to real word data for integrated retrieval of multimedia information. The algorithms include self-organisation and transformation among representation of multimedia and feature extraction and recognition of real data. Real world data includes video, still image, speech, music, sound, and text each of which has not been indexed by labels.
An example of multimedia integration retrieval called “CrossMediator” developed by ten-year project (1992-2002) RWC of METI (Japan). Some parts of CrossMediator have been in the commercial market by through a private company. Prof. R.Oka was a chief of group which developed "CrossMediator". Our laboratory will pursue to develop more sophisticated functions which might reveal a new generation of the Internet. Speech retreival system used in CrossMediator is used for developing new types of commercial products. At the present time we use two kinds of index for searching video data. One is used to obtain the target media from Youtube by using index. The other one is used for searching parts of the target data which are not indexed.
One of the recent progress is developing a set of algorithms for spotting recognition and tracking objects in a time-varying image. These algorithms enable to realize automatic anonotation of video image capturing moving objects. The most promissing algorithm called 2-dimensional Continuous Dynamic programming (2DCDP) was proposed by our laboratory. This enables to perform full pixel matching between images. The full pixel correspondene is used for reconstructing 3D shape from at least 3 images obtained from different viewpoints and also gives a quite precise features like optical flow from a motion image. The 2DCDP is also applicable to non-linear registration for medical images to extract different parts between normal CT imagesand abnormal CT images.
Another recent progress is developing a spotting algorithm for song wave retrieval. A large amount of song wave data is available for anyone along with the progress of storage hardware of music data. But the progress of technology for accessing the song wave data seems quite slow so that we must use conventional and not sophistcated tools. Our new software can provide users a convenient way to find and rerieve the song wave data by singing an arbitrary part of it which he/she wants to hear.
The Internet is regarded as a network composed of virtual communities. Visualization of the community is becoming an important research target. Our lab is developing a sophistcated algorithm based on so-called Associated hyper-linked word space (A-space). We use the algorithm to detect clusters each of which corresponds a virtual community. Visualization of each virtual community is realized by showing the content extracted from the web pages included the community.
On the other hand, we have carried out several research projects related to complex systems in which many independent components interact with each other and emerge global phenomena. Particularly, we have conducted on multiple robot control, and energy efficient walking control in biped robots.
With respect to multiple robot control, we have analyzed the dynamics of multiple mobile robots as a swarm under the mixture condition of long and short range communication, and evaluated the required amount of communication for the multiple robot control. Particularly, we have investigated the relation between the speed of convergence and the graph spectra induced from the swarm robot network, and we have developed a stable and fast swarm robot control method. As implementing actual multiple mobile robots, we need a sensing system. In this project, we have developed a sensing and position estimating system for the robots, and evaluated the accumulated errors.
In terms of the walking control of biped robots, we have set the problem to walk down steep hills, which is known as steps of walking robots fall into chaotic and unstable one. We have developed a control method for the problem, and evaluated it with numerical experiments. The results show it is capable to walk down the steep slopes stably with less control energy consumption. is capable to walk down the steep slopes stably with less control energy consumption.
Mohamed Hamada and Sayota Sato. A Game-based Learning System for Theory of Computation Using Lego NXT Robot. Elsevier Procedia Computer Science, 2011(4):1944-1952, 2011.
This paper introduces an interactive simulator and a robot-based game associated with it for active learning in theory of computation related courses. The simulator is implemented in Java language and the automaton game based robot is build by the Lego NXT Robot set.
Shigekazu Fukui Keitaro Naruse and Jie Luo. Mutual Localization of Multiple Sensor Node Robots. Journal of Advanced Computational Intelligence and Intelligent Informatics, 15(9):1269-1276, 2011.
The objective of this paper is to develop a localization systemof cooperativemultiple mobile robots, in which each robot is assumed to observe a set of known landmarks and equipped with an omnidirectional camera. In this paper, it is assumed that a robot can detect other robots by using the omnidirectional camera, share its estimated position with others, and utilize shared positions for its localization. In other words, each robot can be viewed as an additional mobile landmark to a set of stationary landmarks. A foremost concern is how well this system performs localization under a limited amount of information. This paper presents an investigation of self localization error of each robot in a group using Extended Kalman Filter to solve the localization problem with the insufficient landmarks and inaccurate position information.
Keitaro Naruse and Tatsuya Sato. Neighbor Topology for Dynamic Plane Coverage in Swarm Leading Control. International Journal of Artificial Life Research, 3(1):60-76, 2011.
The objective of this paper is to solve the dynamic plane coverage problem by the movement of multiple robots, for example, sprinkling water to a large field by several vehicles or aircrafts, in which all of the points in the field should be covered by the robots in an almost equal density. One of the ways to solve it is the swarm leading control method, in which one of the robots, called a target, moves along a path in the field, and all the other robots move around the target with a fixed distance. In the process, the topology of the robots affects to the efficiency of the dynamic plane coverage problem. If the topology is a tight one, the swarm can be stable but the coverage area can be limited in a small area. On the other hand, if it is a loose one, an opposite thing can be happened. In this paper, the relation between the topology and the efficiency is discussed numerically.
Jun Ma, Long Zheng, Mianxiong Dong, Xiangian He, Minyi Guo, Yuichi Yaguchi, and Ryuichi Oka. A segmentation- free method for image classification based on pixelwise matching. Journal of Computer and System Science, page not specifed, 2011.
Categorical classification for real-world images is a typical problem in the field of computer vision. This task is extremely easy for a human due to our visual cortex systems. However, developing a similarity recognition model for computer is still a difficult issue. Although numerous approaches have been proposed for solving the tough issue, little attention is given to the pixel-wise techniques for recognition and classification. In this paper, we present an innovative method for recognizing real-world images based on pixel matching between images. A method called two-dimensional continuous dynamic programming (2DCDP) is adopted to optimally capture the corresponding pixels within nonlinearly matched areas in an input image and a reference image representing an object without advance segmentation procedure. Direction pattern (a set of scalar patterns based on quantization of vector angles) is made by using a vector field constructed by the matching pixels between a reference image and an input image. Finally, the category of the test image is deemed to be that which has the strongest correlation with the orientation patterns of the input image and its reference image. Experimental results show that the proposed method achieves a competitive and robust performance on the Caltech 101 image dataset.
Kazuma Suzuki and Keitaro Naruse. Robustness of Semi-Passive Dynamic Walking Models for Steep Slopes. In Proceedings of 3rd International Conference on Awareness Science and Technology (iCast2011), pages 299-304, 2011.
Passive Dynamic Walker can descend a shallow slope only using an initial velocity and the gravity. It has good energy efficiency because it does not require any actuator. However, it has been known that it cannot walk on a steep slope. Controlled walking models, called “ semi-passive dynamic walkers ” are considered in this research to accomplish stable walking on the steep slope. The experimental model is defined as the compass shaped model which has control to the hip joint and ankle joint. Three different controlled models are tested to investigate the characteristics of walking. As the result the controlled model accomplishes steep slope walking and it has some robustness to the angle of the slope if sufficient torque is added.
Tatsuya Sato and Keitaro Naruse. Relation to Connectivity and Covered Area in Dynamic Plan Covering by Swarm Robotics. In Proceedings of 3rd International Conference on Awareness Science and Technology (iCast2011), pages 170-179, 2011.
The dynamic plane covering by swarm robots is a problem to make a trajectory of move multiple robots in a given field so that the trajectory covers the field, which often appears in agricultural works such as water spraying. We solve the problem by applying the swarm robot concepts in the way that a single robot called a leader moves around in the field and all the other robots called followers try to catch up the leader. The advantage of this solution is that we only need to specify a trajectory of the leader and we expect the scalability of the number of the robots. On the other hand, we have to carefully design the trajectory of the leader and the connectivity network between the followers so that all the robots are always connected and under control. This paper presents the relation between the connectivity network, the control stability, and the covered field both analytically and numerically.
Keitaro Naruse and Tatsuya Sato. Neighbor Topology for Dynamic Plane Coverage in Swarm Leading Control. In Proceeding of The 15th Asia Pacific Symposium on Intelligent and Evolutionary Systems 2011, pages 170 179, 2011.
The objective of this paper is to solve the dynamic plane coverage problem by the movement of multiple robots, for example, sprinkling water to a large field by several vehicles or aircrafts, in which all of the points in the field should be covered by the robots in an almost equal density. One of the ways to solve it is the swarm leading control method, in which one of the robots, called a target, moves along a path in the field, and all the other robots, move around the target with a fixed distance. In the process, the topology of the robots affects to the efficiency of the dynamic plane coverage problem. If the topology is a tight one, the swarm can be stable but the coverage area can be limited in a small area. On the other hand, if it is a loose one, an opposite thing can be happened. In this paper, the relation between the topology and the efficiency is discussed numerically.
Taku Kuwabara Keitaro Naruse and Tatsuya Sato. Connectivity and Stability in Robotic Swarm System with Anisotropic Neighbors. In Proceeding of 2011 IEEE/SICE International Symposium on System Integration (SII2011), pages 697-701, 2011.
Most of robotic systems introduce an isotropic neighbor area, such as a circle, for robot communication and interaction because it reflects a natural property of some physical sensors and devices. On the other hand, it has reported that starling birds in nature employ anisotropic neighbor, for example an ellipse, for neighbor observation. In this paper, we introduce the anisotropic neighbor to a robotic swarm system, and we investigate how it affects to the connectivity and stability of the system.
Yuichi Yaguchi, Takashi Matsuzaki, Toshimitsu Suzuki, Yukihiro Yoshida, Yuichi Okuyama, Kazuaki Takahashi, and Ryuichi Oka. A Freeviewpoint TV System. In MVA2011 IAPR Conference on Machine Vision Applications, pages 116-119, June 2011.
We propose an implementation of a model-based free-viewpoint TV (FTV) system using only three uncalibrated cameras. FTV is next-generation media that enables us to see a scene from any viewpoint. A modelbased approach for realizing FTV requires real-time 3D object capture using multiple cameras. Here, we propose a system for reconstructing 3D object surfaces using the so-called 2D continuous dynamic programming (2DCDP) method with factorization. 2DCDP is a powerful technique for full-pixel optimal matching. It provides pixel correspondences between the images captured by the three cameras. The proposed system works well as a promising FTV system.
Shinya Mizoe, Yuichi Yaguchi, Kazuaki Takahashi, Kazuhiro Ota, and Ryuichi Oka. Reconstructing 3D Land Surface From a Sequence of Aerial Images. In MVA2011 IAPR Conference on Machine Vision Applications, pages 365-368, June 2011.
This paper proposes a method for reconstructing a 3D surface landscape from an aerial image sequence captured by a single noncalibrated camera. Reconstructing a 3D surface landscape is more difficult than constructing a landscape of buildings or objects in a room because of the lack of available information about camera parameters, the need for mosaicking of 3D surface elements, and the introduction of nonrigid objects. Therefore, conventional methods are not directly applicable. In order to solve these problems, we apply socalled 2-Dimensional Continuous Dynamic Programming (2DCDP) to obtain full pixel trajectories between successive image frames in a sequence of aerial images. Then we apply Tomasiof aerial images. Then we apply Tomasi?Kanade Factorization to the full pixel Kanade Factorization to the full pixel trajectories to reconstruct the 3D surface. We also develop a mosaicking technique for connecting all of the partially reconstructed surfaces. The experimental results show that our proposed method is very promising for reconstructing 3D surfaces, including a forest, a mountain, a lake and several houses. We conduct experiments to compare our method against a SIFT-based method using two sets of data, namely, artiour method against a SIFT-based method using two sets of data, namely, arti?cial cial and real image sequence data.
Tatsuya Sato and Keitaro Naurse. Connectivity and Stability in Dynamic Plan Covering by Swarm Robots. In Proceedings of the 2011 JSEM Conference on Robotics and Mechatronics, 2011.
Kazuma Suzuki Takayuki Suzuki and Keitaro Naurse. Robustness of the Compass Biped Modek with Control in a Smooth Surface. In Proceedings of the JSPE 2011 Fall Conference, 2011.
Takuma Daicho and Keitaro Naurse. Information Propagation Model in Multi-Layered Communities in Twitter. In Proceedings of the SICE System Integration Division Conference 2011, 2011.
Takuma Kuwabarao and Keitaro Naurse. Connectivity and Stability in Swarm Agents with Anisotoropic Negihbor. In Proceedings of the SICE System Integration Division Conference 2011, 2011.
Kazuma Suzuki and Keitaro Naurse. Gain Analysis and Control of a COmpass-like Biped Model on Steep Slopes. In Proceedings of the JSPE 2012 Spring Conference, 2012.
Emika Sato, other eight authors, and Keitaro Naurse. Development of Accomodation Facility Selection Recommendation System. In Proceedings of the SICE System Integration Division Conference 2011, 2011.
Toshimitsu Suzuki, Jun Ma, Takashi Matsuzaki, Yuichi Yaguchi, and Ryuichi Oka. Non-linear Registration for Multi-Object Posture Image (in Japanese). In Proceedings of MIRU2011, July 2011.
Yuichi Yaguchi, Naoya Horiguchi, and Ian Wilson. Mapping phonemes to midsagittal tongue images for pronounciation learning. In IEICE Technical Report PRMU2011-221, February 2012.
Takashi Matsuzaki, Toshimitsu Suzuki, Yuichi Yaguchi, Ryuichi Oka, and Kazuaki Takahashi. Mozaiking 3D Reconstruction Images for Realizing Free Viewpoint TV (in Japanese). In Proceedings of MIRU2011, July 2011.
Ryuichi Oka. Spotting Recognition of Time-Space Patterns From a Motion Image. In IEICE Technical Report PRMU2011-188,SP2011-103, February 2012.
Ryuichi Oka. Image Processing Using Continuous Dynamic Programming. In IEEJ Technical Report IP-12-013,ISS-12-055, March 2012.
Mohamed Hamada, Kuseke Nishikawa, and John Brine. A Study of a Learning Style Index to support Intelligent and Adaptive Learning Systems, pages 101-125. A book of the Springer series: Smart Innovation, Systems and Technologies. Springer, 2012.
This chapter is concerned with the study, implementation, and application of a webbased learning style index. We also describe a case study on the integration of the learning style index into an adaptive and intelligent e-learning system.
Keitaro Naruse. Alliance for Growth, Tokeiren Business Center, 2012/01-2012/12.
Mohamed Hamada, 2011.
Program Committee member of IEEE ICALT 2011
Mohamed Hamada, 2011.
Program Committee member of the ACM ISWSA 2011
Mohamed Hamada, 2012. Editorial Board member of the Nova Science Publisher
Mohamed Hamada, 2012. Organizing Committee member of the IEEE MCSoC 2012
Keitaro Naruse, 2011.
Geust editor: Journal of ACISC/AWSE
Keitaro Naruse, 2011.
IPSJ Tohoku branch committee
Keitaro Naruse, 2011.
Session Organizer, SICE SI Division Conference
Keitaro Naruse, 2011.
RSJ Young researcher award selection committee
Keitaro Naruse, 2011.
iCast 2011 Program committee
Sayota Sato. Robot Based Simulator for Automata Theory. Master thesis, Graduate School of Computer Science and Engineering, 2012.
Thesis Adviser: M. Hamada
Takahiro Mitsui. A Japanese learning application for iPhone. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: M. Hamada
Kenji Matsumoto. Technical Japanese App for iPhone. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: M. Hamada
Shigekazu Fukui. A Cooperative Multi-Robot System wit hMacroscopic Position Beliefs and Analysis on RSSI-based Measurement. Master thesis, Graduate School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Hiroya Yamamoto. Control of Ostrich-like Knee Joint Biped Robot Based on Passive Dynamic Walking. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Emika Sato. Development of accommodation facility selection recommendation system. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Jun Kanno. walking model with semicircular feet based on PDW for a small stair step. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Taku Kuwabara. Numerical Analysis of connectivity and stability of the flocks by the anisotropic neighborhood. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Hiroshi Nagashima. Multi-Robots Dynamic Area Covering with Artificial Pheromone. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Takuma Daicho. Modeling and Analysis of Information Propagation in Multi-layered Communities in Twitter. Master thesis, Graduate School of Computer Science and Engineering, 2012.
Thesis Adviser: K. Naruse
Hapugahage Thilak Chaminda. A smart reminder system for couplingpaired activities. Ph.D. thesis, Graduate School of Computer Science and Engineering, 2012. Ph.D Sub
Thesis Adviser: Keitaro Naruse
Sho Anma. Spherical Image Viewer for Searching Similar Images. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: Y. Yaguchi
Ryosuke Yabuki. Mesen: Development A Input System Using Eye Sight. Graduation thesis, School of Computer Science and Engineering, 2012.
Thesis Adviser: Y. Yaguchi
2012 THE UNIVERSITY OF AIZU ALL RIGHTS RESERVED