Presenter

Mr Abel Diaz Berenguer - VUB-ETRO [Email]

Abstract

Automatically understanding human behavior is one of the most fundamental research topic towards socially aware vision-based autonomous systems. There is an increasing interest in incorporating the social signal perspective into the learning systems pipeline. This dissertation focuses on developing and incorporating computational mechanisms of Computer Vision and Machine Learning to analyze and predict human behavior in crowded scenes automatically. Our research specifically addresses public safety assisted by autonomous video surveillance systems aiming to decrease the human labor dedicated to video monitoring.

Our research efforts concentrate on the information processing pipeline for learning systems that cope with human trajectory prediction and human behavior analysis in crowded scenes. We contribute to human trajectory prediction in crowded scenes with
(i) a novel latent variable model aware of the human-human and human-contextual interactions to predict plausible trajectories. Furthermore,
(ii) a novel latent location-velocity recurrent model that predicts future variable and feasible trajectories. Towards human anomalous behavior detection, we adopt two unsupervised approaches based on the scene dominant behavior and trajectories underlying properties to address trajectory-based anomaly detection. Besides, we contribute with
(iii) a supervised approach capable of attaining discriminative sequence-based feature representations to recognize whether video sequences depict violent human behavior.
Extensive experiments on publicly available datasets, demonstrate the effectiveness of our proposals.


Online via Teams:
https://teams.microsoft.com/l/meetup-join/19%3ameeting_OWMxNTNiOGQtZGZjOC00Y2IxLTg3ZjUtYTJjZGNmMmIxNTc3%40thread.v2/0?context=%7b%22Tid%22%3a%22695b7ca8-2da8-4545-a2da-42d03784e585%22%2c%22Oid%22%3a%2237757df7-4050-47fe-8384-aded7e9e79c3%22%7d

Short CV

Master in Applied Informatics, UCI, 2014