{"title":"Driving vision systems by communication","authors":"T. Graf, A. Knoll","doi":"10.1109/ICIIS.1999.810359","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810359","url":null,"abstract":"Proposes a new multi-agent system architecture which is dedicated to building distributed computer vision systems. This architecture incorporates a communication language which provides a great degree of flexibility: firstly, the language permits the construction of flexible and self-organizing vision systems; secondly, it is capable of expressing complex facts and tasks; thirdly, it is simple, i.e. human-readable and writable; and lastly, the messages provided by the communication language can be interpreted efficiently. We describe in detail the basic concepts of the multi-agent system architecture, including the communication language as well as the agent architecture and the interaction strategy. As a testbed for the proposed architecture, we have modelled an object recognition system as a society of autonomous agents which organize themselves according to a given recognition task by employing communication.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123799060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Application of hidden Markov models to gene prediction in DNA","authors":"M. M. Yin, J.T.L. Wang","doi":"10.1109/ICIIS.1999.810222","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810222","url":null,"abstract":"Programs currently available for gene prediction from within genomic DNA are far from being powerful enough to elucidate the gene structure completely. We develop a hidden Markov model (HMM) to represent the degeneracy features of splicing junction donor sites in eucaryotic genes. The HMM system is fully trained using an expectation maximization algorithm and the system performance is evaluated using the 10-way cross-validation method. Experimental results show that our HMM system can correctly classify more than 95% of the candidate sequences into the right categories. More than 91% of the true donor sites and 97% of the false donor sites in the test data are classified correctly. These results are very promising, considering that only the local information in DNA is used. This model will be a very important component of effective and accurate gene structure detection system currently being developed in our lab.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128435430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A generic formal plan recognition theory","authors":"G. Camilleri","doi":"10.1109/ICIIS.1999.810344","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810344","url":null,"abstract":"Plan recognition is the task of inferring intentions (in terms of plans) from the actions or utterances of observed actors (Kautz, 1986). In this paper, we provide a new logical formalization of plan recognition, which allows us to clearly specify, validate and design the plan recognition process (useful in several domains such as: discourse understanding, human computer interaction, and so on). However, depending on the applications different recognition strategies are used (top-down, bottom-up, and so on). Therefore, to describe the possible strategies, we only chose to formalize the reasoning basic steps of plan recognition. Moreover, only the specific aspects of the recognition problem are formalized and fixed. Therefore, the other aspects can be determined to satisfy the system needs. To illustrate our formalism, we describe two strategies of plan recognition used in many applications. We also present an algorithm useful to the discourse understanding.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114513831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Segmentation of range and intensity image sequences by clustering","authors":"B. Heisele, W. Ritter","doi":"10.1109/ICIIS.1999.810265","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810265","url":null,"abstract":"Presents a method for segmenting temporal sequences of range and intensity images. The paper addresses two problems: fusion of intensity and range data for image segmentation, and visual tracking of segments over time. Our method is based on clustering in a 4D feature space which contains intensity and geometric features. The problem of tracking segments over time is solved by adaptive image sequence clustering. The main idea is to use the cluster centers of the previous image to initialize clustering for the current image. This link between consecutive clustering steps allows one to track clusters over time without explicit correspondence analysis. First experiments show that our method can successfully segment and track objects independent of their shapes and motions.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128049313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Velocity estimation using semi-local features","authors":"Liya Chen, E. Teoh","doi":"10.1109/ICIIS.1999.810292","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810292","url":null,"abstract":"Computing the velocity field, or motion estimation is one of the most important issues in computer vision, and it is widely used in the areas of navigation, visual surveillance, video database, etc. This problem has received a great deal of attentions over the last few years. This paper proposed a novel affine invariant feature set which localization ability is adjustable, and based on this developed a velocity estimation algorithm. It can be used in motion detection, motion segmentation, and motion based recognition.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130118602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Environmental simulations using multiagent systems","authors":"J. Soulié, P. Marcenac","doi":"10.1109/ICIIS.1999.810363","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810363","url":null,"abstract":"This paper presents an interesting architecture to model the environment in multiagent simulations. The originality of our approach is that unlike the majority of multiagent systems, we do not perform tasks dedicated to the environment and tasks dedicated together in the same entity. This is why we separate an agent into two entities: the brain that is in charge of reasoning, and the body that is in charge of the perceptions and actions in the environment. We then propose a mechanism which decreases the complexity of the environment. For that, we define two new notions: environment porosity and aggregation operation. We then applied this framework to the motion of a shoal of swordfish.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"50 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124530885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using artificial physics to control agents","authors":"William M. Spears, Diana F. Gordon","doi":"10.1109/ICIIS.1999.810278","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810278","url":null,"abstract":"We introduce a novel framework called \"artificial physics\", which provides distributed control of large collections of agents. The agents react to artificial forces that are motivated by natural physical laws. This framework provides an effective mechanism for achieving self-assembly, fault-tolerance, and self-repair. Examples are shown for various regular geometric configurations of agents. A further example demonstrates that self-assembly via distributed control can also perform distributed computation.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116354500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Doulamis, N. Doulamis, K. Ntalianis, S. Kollias
{"title":"Unsupervised semantic object segmentation of stereoscopic video sequences","authors":"A. Doulamis, N. Doulamis, K. Ntalianis, S. Kollias","doi":"10.1109/ICIIS.1999.810342","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810342","url":null,"abstract":"In this paper, we present an efficient technique for unsupervised semantically meaningful object segmentation of stereoscopic video sequences. Using this technique we extract semantic objects using the additional information a stereoscopic pair of frames provides. Each pair is analyzed and the disparity field, occluded areas and depth map are estimated. The key algorithm, which is applied on the stereo pair of images and performs the segmentation, is a powerful low-complexity multiresolution implementation of the RSST algorithm. Color segment fusion is employed using the depth segments as a kind of constraint. Finally experimental results are presented which demonstrate the high-quality of semantic object segmentation this technique achieves.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129721064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Locomotion control using environment information inputs","authors":"J. Juang","doi":"10.1109/ICIIS.1999.810259","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810259","url":null,"abstract":"A learning scheme is developed to control bipedal locomotion on different sloping surfaces. This scheme uses three neural networks: a neural network controller, a neural network emulator, and a slope information neural network. The neural network controller is pre-trained by a reference trajectory on horizontal surface. The emulator is pre-trained to identify the robotic dynamics. The slope information neural network provides compensated control signals to the robot on different slope angles by using the control signals on horizontal surface from the pre-trained controller. The training rule is a backpropagation algorithm with time delay. The proposed technique can generate gaits on different sloping surfaces by following reference trajectory with desired step length, crossing height and walking speed.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128286277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient concurrency control algorithm for high-dimensional index structures","authors":"S. Song, Jaesoo Yoo","doi":"10.1109/ICIIS.1999.810339","DOIUrl":"https://doi.org/10.1109/ICIIS.1999.810339","url":null,"abstract":"In this paper we propose an efficient concurrency control algorithm based on the link technique of R/sup Link/-Tree for high-dimensional index structures. Unlike the R/sup Link/-Tree concurrency control algorithm, it does not employ lock-coupling while ascending the index trees to process node splits and MBR (minimum bounding region) updates. Additionally, the algorithm provides the concurrency control mechanisms for forced reinsertion operations that are used to improve search performance in multi-dimensional index trees. We show through experiments that our proposed method outperforms the existing R/sup Link/-Tree algorithm.","PeriodicalId":263561,"journal":{"name":"Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127225597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}