Deep Residual Network With Subclass Discriminant Analysis For Crowd Behavior Recognition

Mandal, Bappaditya; Fajtl, Jiri; Argyriou, Vasileios; Monekosso, Dorothy; Remagnino, Paolo

Abstract

In this work, we extract rich representations of crowd behavior from video using a fine-tuned deep convolutional neural residual network. Using spatial partitioning trees we create subclasses within the feature maps from each of the crowd behavior attributes (classes). Features from these subclasses are then regularized using an eigen modeling scheme. This enables to model the variance appearing from the intra-subclass information. Low dimensional discriminative features are extracted after using the total subclass scatter information. Dynamic time warping is used on the cosine distance measure to find the similarity measure between videos. A 1-nearest neighbor (NN) classifier is used to find the respective crowd behavior attribute classes from the normal videos. Experimental results on large crowd behavior video database show the superior performance of our proposed framework as compared to the baseline and current state-of-the-art methodologies for the crowd behavior recognition task.

Citation

Mandal, B., Fajtl, J., Argyriou, V., Monekosso, D., & Remagnino, P. (2018, October). Deep Residual Network With Subclass Discriminant Analysis For Crowd Behavior Recognition. Presented at 2018 IEEE International Conference on Image Processing, Athens

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2018 IEEE International Conference on Image Processing
• Start Date: Oct 7, 2018
• End Date: Oct 10, 2018
• Acceptance Date: May 4, 2018
• Publication Date: Sep 6, 2018
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Series Title: IEEE International Conference on Image Processing
• DOI: https://doi.org/10.1109/ICIP.2018.8451190
• Keywords: crowd behavior recognition, feature extraction, discriminant analysis, residual network
• Public URL: https://keele-repository.worktribe.com/output/411216
• Publisher URL: https://doi.org/10.1109/ICIP.2018.8451190