Subjective and Objective Quality Assessment of High-Motion Sports Videos At Low-Bitrates

Authorities as well as emergency and rescue services have an increasing interest in "intelligent" support systems to ensure public safety, which includes in particular behavioral analysis of pedestrians by using video surveillance systems. in order to accommodate possible worries of citizens concerning their personal rights, the demand for data privacy friendly approaches using as few information as possible arises. in this paper, we examine existing approaches tackling the recognition of anomalous or salient behavior based solely on person pose information within the context of real-world surveillance applications. Particularly, we chose two existing state-of-the-art approaches and evaluate them on two public and an internal dataset in order to examine the overall performance of these methods for the desired task. Furthermore, we present an own approach achieving comparable results to the aforementioned methods. Finally, we extend the aforementioned methods with a memory extension for modelling normal behavior, which yields on average a 4.3% higher recognition performance.