Publications (7)0 Total impact
- [show abstract] [hide abstract]
ABSTRACT: A novel evolutionary algorithm called probability evolutionary algorithm (PEA), and a method based on PEA for visual tracking of human motion are presented. PEA is inspired by estimation of distribution algorithms and quantum-inspired evolutionary algorithm, and it has a good balance between exploration and exploitation with very fast computation speed. The individual in PEA is encoded by the probability vector, defined as the smallest unit of information, for the probabilistic representation. The observation step is used in PEA to obtain the observed states of the individual, and the update operator is used to evolve the individual. In the PEA based human tracking framework, tracking is considered to be a function optimization problem, so the aim is to optimize the matching function between the model and the image observation. Since the matching function is a very complex function in high-dimensional space, PEA is used to optimize it. Experiments on 2D and 3D human motion tracking demonstrate the effectiveness, significance and computation efficiency of the proposed human tracking method.Pattern Recognition Letters. 01/2008; 29:1877-1886.
- [show abstract] [hide abstract]
ABSTRACT: We have proposed a method to detect and quantitatively extract anomalies from surveillance videos. Using our method, anomalies are detected as patterns based on spatio-temporal features that are outliers in new feature space. Conventional anomaly detection methods use features such as tracks or local spatio-temporal features, both of which provide insufficient timing information. Using our method, the principal components of spatio-temporal features of change are extracted from the frames of video sequences of several seconds duration. This enables anomalies based on movement irregularity, both position and speed, to be determined and thus permits the automatic detection of anomal events in sequences of constant length without regard to their start and end. We used a 1-class SVM, which is a non-supervised outlier detection method. The output from the SVM indicates the distance between the outlier and the concentrated base pattern. We demonstrated that the anomalies extracted using our method subjectively matched perceived irregularities in the pattern of movements. Our method is useful in surveillance services because the captured images can be shown in the order of anomality, which significantly reduces the time needed.Ieice Transactions - IEICE. 01/2008;
Conference Proceeding: MCMC based multi-body tracking using full 3D model of both target and environment[show abstract] [hide abstract]
ABSTRACT: In this paper, we present a new approach for the stable tracking of variable interacting targets under severe occlusion in 3D space. We formulate the state of multiple targets as a union state space of each target, and recursively estimate the multi-body configuration and the position of each target in 3D space by using the framework of Trans-dimensional Markov Chain Monte Carlo(MCMC). The 3D environmental model, which replicates the real-world 3D structure, is used for handling occlusions created by fixed objects in the environment, and reliably estimating the number of targets in the monitoring area. Experiments show that our system can stably track multiple humans that are interacting with each other and entering and leaving the monitored area.Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Conference on; 10/2007
Conference Proceeding: Detecting the Degree of Anomal in Security Video.[show abstract] [hide abstract]
ABSTRACT: We have developed a method that can discriminate anomalous image sequences for more efficiently utiliz- ing security videos. To match the wide popularity of se- curity cameras, the method is independent of the cam- era setting environment and video contents. We use the spatio-temporal feature obtained by extracting the areas of change from the video. To create the input for the discrimination process, we reduce the dimen- sionality of the data by PCA. Discrimination is based on a 1-class SVM, which is a non-supervised learning method, and its output is the degree of anomaly of the sequence. In experiments we apply the method to videos obtained by a network camera; the results show the feasibility of indexing anomalous sequences from security videos.Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2007), May 16-18, 2007, Tokyo, Japan; 01/2007
Conference Proceeding: Human Tracking by Particle Filtering Using Full 3D Model of Both Target and Environment[show abstract] [hide abstract]
ABSTRACT: This work presents a new approach based on particle filtering to directly estimate the 3D positions of humans. Our system can predict occlusions due to other movements because we track humans in a 3D space, not on a 2D image plane. In addition, we introduce a 3D environmental model as the background model for tracking. This makes it easier to handle occlusions due to fixed objects in the environment. The 3D environmental model is automatically constructed by our original method from video sequences. Experiments show that our system is stable under occlusions due to the movements of both other subjects and fixed objectsPattern Recognition, 2006. ICPR 2006. 18th International Conference on; 01/2006
- Systems and Computers in Japan. 01/2006; 37:32-46.
- [show abstract] [hide abstract]
ABSTRACT: For 3-D building reconstructions of urban areas, we present a fully automatic shape recovery method that uses 3-D points acquired from aerial image sequences. This paper focuses on shape recovery of flat rooftops that are parallel to the ground. We recover each rooftop from a set of 3-D points located at nearly the same height. Such 3-D point sets are made by merging point sets under the MDL (Minimum Description Length) principle, which finds suitably concise point sets for 3-D building models. Often, only parts of rooftop shapes can be recovered because of the 3-D position errors being generated in the points. To refine the recovered shapes, we merge the parts under a heuristic condition in which shapes will have a pair of orthogonally oriented edges. To optimize parameters and estimate the viability of our method, we defined a success rate, called the cover ratio, as the area in which the recovered shape and a correct shape (given as reference data) overlap to the combined area of the recovered and correct shapes. Experimental results showed that our method achieved a cover ratio of 75.25%, and through improved cover ratio we also confirmed effectiveness of shape refinement. We also found that even if only one-ninth of the reference data could be used in the optimization of parameters, the cover ratio was 70.96%. The experimental results we obtained showed that our point-based method was effective in enabling the recovery of buildings in urban areas.