No abstract

The proposed unusual video event detection method is based on unsupervised clustering of object trajectories, which are modeled by hidden Markov models (HMM). The novelty of the method includes a dynamic hierarchical process incorporated in the trajectory clustering algorithm to prevent model overfitting and a 2-depth greedy search strategy for efficient clustering.

The interleaver, which combines the outputs of turbo decoders, is essential in determining the performance of turbo codes and is the main source of decoder computation and implementation complexity. ABSTRACT | The discovery of turbo codes and the subsequent rediscovery of low-density parity-check (LDPC) codes represent major milestones in the field of channel coding. Recent advances in the design and theory of turbo codes and their relationship to LDPC codes are discussed. Several new interleaver designs for turbo codes are presented which illustrate the important role that the interleaver plays in these codes. The relationship between turbo codes and LDPC codes is explored via an explicit formulation of the parity-check matrix of a turbo code, and simulation results are given for sum product decoding of a turbo code.

The clustering-based approach for detecting abnormalities in surveillance video requires the appropriate definition of similarity between events. The HMM-based similarity defined previously falls short in handling the overfitting problem. We propose in this paper a multi-sample-based similarity measure, where HMM training and distance measuring are based on multiple samples. These multiple training data are acquired by a novel dynamic hierarchical clustering (DHC) method. By iteratively reclassifying and retraining the data groups at different clustering levels, the initial training and clustering errors due to overfitting will be sequentially corrected in later steps. Experimental results on real surveillance video show an improvement of the proposed method over a baseline method that uses singlesample-based similarity measure and spectral clustering.

No abstract

No abstract

Abstract-Our work addresses the problem of analyzing and understanding dynamic video scenes. A two-level motion pattern mining approach is proposed. At the first level, activities are modeled as distributions over patch-based features, including spatial location, moving direction, and speed. At the second level, traffic states are modeled as distributions over activities. Both patterns are shared among video clips. Compared to other works, one advantage of our method is that moving speed is considered to describe visual word. The other advantage is that traffic states are detected and assigned to every video frame. These enable finer semantic interpretation, more precise video segmentation, and anomaly detection. Specifically, every video frame is labeled by a certain traffic state, and the video is segmented frame by frame accordingly. Moving pixels in each frame, which do not belong to any activity or cannot exist in the corresponding traffic state, are detected as anomalies. We have successfully tested our approach on some challenging traffic surveillance sequences containing both pedestrian and vehicle motions.

No abstract