TY - JOUR
T1 - A hierarchical autoencoder learning model for path prediction and abnormality detection
AU - Dotti, Dario
AU - Popa, Mirela
AU - Asteriadis, Stylianos
N1 - Funding Information:
This work has been funded by the European Union ’ Horizon 2020 Research and Innovation Program under Grant Agreement N ∘ 690090 (ICT4Life project).
Funding Information:
This work has been funded by the European Union’ Horizon 2020 Research and Innovation Program under Grant Agreement N∘ 690090 (ICT4Life project).
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2020/2
Y1 - 2020/2
N2 - In this paper, we introduce an unsupervised hierarchical framework for modeling trajectories in surveillance scenarios. Inspired by the object recognition field, a novel feature representation optimized for a neural network learning architecture is proposed. Low levels of the hierarchy capture local spatio-temporal motion attributes such as spatial orientation and speed, while higher levels contribute to obtaining richer semantic information. The bottom-up construction of the hierarchical framework exploits the inherent statistical correlations between neighboring elements using an increasing spatio-temporal grid. Cross-entropy based optimization in combination with autoencoders is used to learn weights for subsequent hierarchical layers. Finally, the Bayesian probabilistic framework built on top of the hierarchical model is proposed for applications such as long-term path prediction and abnormality detection. We demonstrate the efficiency of the proposed model on both indoor and outdoor datasets, achieving results comparable with state-of-the-art methods. (C) 2019 Elsevier B.V. All rights reserved.
AB - In this paper, we introduce an unsupervised hierarchical framework for modeling trajectories in surveillance scenarios. Inspired by the object recognition field, a novel feature representation optimized for a neural network learning architecture is proposed. Low levels of the hierarchy capture local spatio-temporal motion attributes such as spatial orientation and speed, while higher levels contribute to obtaining richer semantic information. The bottom-up construction of the hierarchical framework exploits the inherent statistical correlations between neighboring elements using an increasing spatio-temporal grid. Cross-entropy based optimization in combination with autoencoders is used to learn weights for subsequent hierarchical layers. Finally, the Bayesian probabilistic framework built on top of the hierarchical model is proposed for applications such as long-term path prediction and abnormality detection. We demonstrate the efficiency of the proposed model on both indoor and outdoor datasets, achieving results comparable with state-of-the-art methods. (C) 2019 Elsevier B.V. All rights reserved.
KW - Motion features
KW - Autoencoder
KW - Hierarchical learning
KW - Behavior understanding
KW - Abnormality detection
KW - Path prediction
U2 - 10.1016/j.patrec.2019.06.030
DO - 10.1016/j.patrec.2019.06.030
M3 - Article
SN - 0167-8655
VL - 130
SP - 216
EP - 224
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -