CVOct 11, 2018

Globally Continuous and Non-Markovian Activity Analysis from Videos

arXiv:1810.04954v124 citations
Originality Incremental advance
AI Analysis

This work addresses video activity analysis for behavior understanding and anomaly detection, representing an incremental advancement with a novel temporal modeling approach.

The paper tackles unsupervised activity recognition in videos by discovering recurring patterns with globally continuous and non-Markovian temporal modeling, resulting in improved data fitting and anomaly detection compared to previous methods.

Automatically recognizing activities in video is a classic problem in vision and helps to understand behaviors, describe scenes and detect anomalies. We propose an unsupervised method for such purposes. Given video data, we discover recurring activity patterns that appear, peak, wane and disappear over time. By using non-parametric Bayesian methods, we learn coupled spatial and temporal patterns with minimum prior knowledge. To model the temporal changes of patterns, previous works compute Markovian progressions or locally continuous motifs whereas we model time in a globally continuous and non-Markovian way. Visually, the patterns depict flows of major activities. Temporally, each pattern has its own unique appearance-disappearance cycles. To compute compact pattern representations, we also propose a hybrid sampling method. By combining these patterns with detailed environment information, we interpret the semantics of activities and report anomalies. Also, our method fits data better and detects anomalies that were difficult to detect previously.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes