|
1. |
A method of pedestrian detection based on rhythm of walking |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 1-11
Satoshi Yasutomi,
Hideo Mori,
Noriaki Kiyohiro,
Preview
|
PDF (929KB)
|
|
摘要:
AbstractIt is important for mobile robots and security purposes to discriminate a pedestrian among moving objects in a video. This paper proposes a method which discriminates a pedestrian from other objects by using periodic motions of the feet, and the characteristics of the rhythm of pace and stride. This method uses brightness changes in sequential images of a moving object contacting with the ground, and extracts the main component of the frequency using a power spectrum estimation. Therefore, the method is independent of pedestrian's appearance such as clothes, build, and hair style. The system realizing this method consists of three processes: moving object detection which uses the difference between successive image frames; tracking of the moving object using a moving model with an extended Kahman filter and an observation model; and detection of the pedestrian based on rhythm of walking using the difference of brightness between images on successive frames. The whole process is performed in real time. Experiments using real scenes confirm the effectiveness of the proposed method: 446 pedestrians out of 470 were successfully detected (detection rate 94.9%), and 101 persons out of 106 were successfully detected as non‐pedestrians (96.2%
ISSN:0882-1666
DOI:10.1002/scj.4690270201
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
2. |
Signal source localization from spatio‐temporal biomagnetic data by signal subspace method |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 12-25
Hiroyuki Kudo,
Tsuneo Saito,
Takashi Maemura,
Preview
|
PDF (1041KB)
|
|
摘要:
AbstractNew methods are proposed to localize multiple current dipoles from spatio‐temporal biomagnetic data obtained with SQUID magnetometers. The proposed methods are based on subspace fitting (SF) and weighted subspace fitting (WSF) frameworks that have been developed originally in the field of array signal processing. When time series from multiple dipoles are strongly correlated or multiple dipoles are closely spaced, these methods outperform the multiple signal classification (MUSIC) proposed by Mosher et al. [1]. Results are presented using these methods for simulated data and experimental magnetocardiogram data. The WSF criterion produced significantly better results compared with the MUSIC and the SF criteri
ISSN:0882-1666
DOI:10.1002/scj.4690270202
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
3. |
Novice program recognition/diagnosis system based on goal/plan concepts |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 26-40
Kenji Kaijiri,
Preview
|
PDF (883KB)
|
|
摘要:
AbstractStudies on program understanding/recognition have been conducted from various points of view, including debugging. However, the target, the range and the kind of recognition, differ according to objectives. A new problem description method and a new recognition method whose objective is to help novices learn program design and debugging is proposed here. This method has the following characteristics:It uses the algorithm level problem description. It is called the problem solution tree.The problem solution tree has positional information regarding goals.It uses a variety of matching methods to enable matching with many erroneous student programs.It uses a partial recognition strategy to diagnose programs with which full matching failed.The system recognized that approximately 85 percent of the novice samples are not well formed.
ISSN:0882-1666
DOI:10.1002/scj.4690270203
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
4. |
Evolving sse: A new population‐oriented search scheme based on schemata processing |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 41-52
Akiko N. Aizawa,
Preview
|
PDF (980KB)
|
|
摘要:
AbstractA new population‐oriented search algorithm called Stochastic Schemata Exploiter (SSE) is proposed here. Similarly to genetic algorithms (GAs), SSE also performs search in the space of solutions by a schemata processing mechanism; however, SSE is characterized by an emphasis on local search. So far, the adaptive global search ability of GAs has been viewed positively. In contrast, SSE takes the point of view that, when applied to actual optimization problems, the GA adaptive global search ability is not necessarily effective; instead, the global search is started by simplifying the population‐oriented search of GAs and reducing the number of control parameters. After reviewing herein the schemata processing in GAs, the property of schemata exploitation is defined, a schemata exploitation search algorithm is devised and the proposed method is evaluated and compared with a simple GA using GA‐easy and GA‐hard test p
ISSN:0882-1666
DOI:10.1002/scj.4690270204
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
5. |
A method for estimating gap junctional conductance between the retinal horizontal cells |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 53-63
Hiroyuki Ishii,
Shiro Usui,
Masao Yamamoto,
Satoshi Suzuki,
Yoshimi Kamiyama,
Preview
|
PDF (950KB)
|
|
摘要:
AbstractGap junction between retinal horizontal cells plays an important role in generating the center‐surround antagonistic receptive field. However, there are technical difficulties involved in measurement of the gap junctional conductance from membrane potential of horizontal cells using the ionic current model. To evaluate the proposed method, the gap junctional conductance was estimated from test data generated by the horizontal cell layer model. Conductance can be estimated with high accuracy. This method is also applied to experimental data recorded from the L‐type cell of carp ret
ISSN:0882-1666
DOI:10.1002/scj.4690270205
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
6. |
Experimental study of recognition rate in statistical pattern classification based on finite size of design sample set |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 64-74
Tetsuo Takeshita,
Shigeyuki Nozawa,
Jun‐Ichiro Toriwaki,
Preview
|
PDF (836KB)
|
|
摘要:
AbstractWhen two classes of patterns follow the multidimensional normal distribution, the following procedure is considered. The same number of finite samples is extracted from each set of patterns. The covariance matrices and the average vectors are estimated. Using the estimated parameters, the linear discriminant function or the quadratic discriminant function is assessed by testing how correctly other samples extracted from the same set can be recognized. The authors found a method in which the above method is iterated to examine the deterioration of the recognition ratio due to the finiteness of the learning samples and to calculate the average recognition ratio.Next, the relations among the dimension of the feature patterns, the number of learning samples and the average recognition ratio are examined and compared to the expression for the approximate recognition ratio (theoretical formula) by Raudys and Fukunaga et al. The limit of application of the evaluation formula is indicated. The deterioration of the recognition ratio is examined, and it is shown that the error ratio is higher in the Bayes decision, and the error ratio becomes closer to the ‐distribution when the dimension of the feature vector is increase
ISSN:0882-1666
DOI:10.1002/scj.4690270206
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
7. |
A speaker‐adaptation technique for context‐dependent models represented by hidden markov networks |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 75-86
Jun‐Ichi Takami,
Shigeki Sagayama,
Preview
|
PDF (903KB)
|
|
摘要:
AbstractThis study aims at the realization of a speaker‐independent speech recognition system based on the speaker adaptation with a supervisor. This paper describes the highly accurate speaker‐adaptation technique using a small number of training samples. When a small number of speech samples are used for adaptation there arise problems that sufficient information cannot be obtained to update simultaneously a large number of model parameters, and an estimation error is included to the statistical bias of the samples.From such a viewpoint, this paper proposes a speaker‐adaptation technique using the hidden Markov network (HMnet), which employs a smaller number of model parameters than the mixed continuous‐distributed phoneme HMM, which is independent of the phoneme context, while realizing an equal or better recognition performance. As the adaptation technique, the moving vector field smoothing (VFS) method is used. This method can realize simultaneously the interpolation for the unadapted model parameters to cope with the small number of samples and the correction of the estimation in the speaker adaptation. The standard speaker pre‐selection method also is investigated in order to improve the accuracy of the speaker a
ISSN:0882-1666
DOI:10.1002/scj.4690270207
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
8. |
Implementation of multistep fuzzy reasoning shell |
|
Systems and Computers in Japan,
Volume 27,
Issue 2,
1996,
Page 87-101
Isao Hayashi,
Eiichi Naito,
Hiroyoshi Nomura,
Noboru Wakami,
Motohide Umano,
Preview
|
PDF (984KB)
|
|
摘要:
AbstractRecently, there have been many trials conducted to develop fuzzy inference systems that can handle the subjective decision of the expert. A problem in the fuzzy control system is that it is an inference composed of only a single step, and cannot be applied to the decision‐making assist or diagnosis, where the inference is made in multisteps. Another point is that the rules of the inference cannot be described for each knowledge source, which has been the conventional inference shell (deterministic inference shell).This paper proposes a fuzzy inference shell which can realize the multistep inference using the blackboard model. The proposed shell uses its own rule description language to represent the knowledge, and the description can be made by combining the new method with the conventional deterministic inference.Using the divided knowledge blocks, the multi‐step fuzzy inference can be realized using the blackboard model. The search function also is provided that can track the inference path in the multistep inference. This paper describes the basic configuration of such a sh
ISSN:0882-1666
DOI:10.1002/scj.4690270208
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
|