Lost in Time: Temporal Analytics for Long-Term Video Surveillance

Abstract

Video surveillance is a well researched area of study with substantial work done in the aspects of object detection, tracking and behavior analysis. With the abundance of video data captured over a long period of time, we can understand patterns in human behavior and scene dynamics through data-driven temporal analytics. In this work, we propose two schemes to perform descriptive and predictive analytics on long-term video surveillance data. We generate heatmap and footmap visualizations to describe spatially pooled trajectory patterns with respect to time and location. We also present two approaches for anomaly prediction at the day-level granularity: a trajectory-based statistical approach, and a time-series based approach. Experimentation with one year data from a single camera demonstrates the ability to uncover interesting insights about the scene and to predict anomalies reasonably well.

Gi oss politikken tilbake i helsepolitikken!

“…Sub-Saharan countries, including Angola, Ghana, Kenya, Mozambique, Nigeria, Zambia, and Zimbabwe have asked for financial assistance or are in talks to do so. 73 …”

“…In addition, the estimated effects of well-being inequality on life satisfaction are significantly larger for those individuals who agree with the statement that income inequalities should be reduced. 73 Furthermore, well-being inequality performs much better than income inequality in one of the key causal roles previously found for income inequality-as a factor explaining differences in social trust. 74 Thus we find that well-being inequality is likely to damage social trust, itself an important index of the strength and quality of the social fabric.…”