Proceedings of the third ACM international workshop on Video surveillance & sensor networks
A System for Learning Statistical Motion Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multi-stage Competitive Neural Networks Approach for Motion Trajectory Pattern Learning
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Intelligent Decision Technologies
International Journal of Robotics Research
Incremental learning of statistical motion patterns with growing hidden Markov models
IEEE Transactions on Intelligent Transportation Systems
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
A macro-observation scheme for abnormal event detection in daily-life video sequences
EURASIP Journal on Advances in Signal Processing - Special issue on advanced image processing for defense and security applications
Behavior pattern extraction by trajectory analysis
Frontiers of Computer Science in China
Motion trajectory clustering for video retrieval using spatio-temporal approximations
VISUAL'05 Proceedings of the 8th international conference on Visual Information and Information Systems
TSFSOM: transmembrane segments prediction by fuzzy self-organizing map
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
International Journal of Computational Vision and Robotics
Self-Organising maps for classification with metropolis-hastings algorithm for supervision
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
A novel loop closure detection method in monocular SLAM
Intelligent Service Robotics
Computer Vision and Image Understanding
Patient's motion recognition based on SOM-decision tree
WASA'13 Proceedings of the 8th international conference on Wireless Algorithms, Systems, and Applications
Hi-index | 0.00 |
Activity understanding in visual surveillance has attracted much attention in recent years. In this paper, we present a new method for learning patterns of object activities in image sequences for anomaly detection and activity prediction. The activity patterns are constructed using unsupervised learning of motion trajectories and object features. Based on the learned activity patterns, anomaly detection and activity prediction can be achieved. Unlike existing neural network based methods, our method uses a whole trajectory as an input to the network. This makes the network structure much simpler. Furthermore, the fuzzy set theory based method and the batch learning method are introduced into the network learning process, and make the learning process much more efficient. Two sets of data acquired, respectively, from a model scene and a campus scene are both used to test the proposed algorithms. Experimental results show that the fuzzy self-organizing neural network (fuzzy SOM) is much more efficient than the Kohonen self-organizing feature map (SOFM) and vector quantization in both speed and accuracy, and the anomaly detection and activity prediction algorithms have encouraging performances.