Human pose estimation has recently made significant progress with the adoption of deep convolutional neural networks and many applications have attracted tremendous interest in recent years. However, many of these applications require pose estimation for human crowds, which still is a rarely addressed problem. For this purpose this work explores methods to optimize pose estimation for human crowds, focusing on challenges introduced with larger scale crowds like people in close proximity to each other, mutual occlusions, and partial visibility of people due to the environment. In order to address these challenges, multiple approaches are evaluated including: the explicit detection of occluded body parts, a data augmentation method to generate occlusions and the use of the synthetic generated dataset JTA [3]. In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications.

Anomaly detection plays in many fields of research, along with the strongly related task of outlier detection, a very important role. Especially within the context of the automated analysis of video material recorded by surveillance cameras, abnormal situations can be of very different nature. For this purpose this work investigates Generative-Adversarial-Network-based methods (GAN) for anomaly detection related to surveillance applications. The focus is on the usage of static camera setups, since this kind of camera is one of the most often used and belongs to the lower price segment. In order to address this task, multiple subtasks are evaluated, including the influence of existing optical flow methods for the incorporation of short-term temporal information, different forms of network setups and losses for GANs, and the use of morphological operations for further performance improvement. With these extension we achieved up to 2.4% better results. Furthermore, the final method reduced the anomaly detection error for GANbased methods by about 42.8%.

D. Du et al. related fields. The collected dataset is formed by 3, 360 images, including 2, 460 images for training, and 900 images for testing. Specifically, we manually annotate persons with points in each video frame. There are 14 algorithms from 15 institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: http://www.aiskyeye.com/.

The number of video cameras in public places increases due to different reasons such as detecting dangers (e.g., thefts, robberies, terrorist attacks) and security breaches in crowds. The application of video surveillance systems is sometimes evaluated ambivalently; therefore, the presented study focuses on factors influencing the acceptance of a privacy-friendly, smart video surveillance system. Overall, 216 persons aged between 18 and 81 years participated in an online survey. In terms of the perceived usefulness, there are significant interactions of public spaces × gender and public spaces × time of day. In addition, the assessment of different privacy levels of a video surveillance system differ significantly in terms of perceived risk. Interestingly, men rate the risk concerning their own privacy significantly higher than women do. Participants rate the presented system as fairly useful and slightly risky for their own privacy. The findings of the presented exploratory study provide insight into how people perceive smart video surveillance. These findings have the potential to support the conditions of the use of smart video surveillance systems and to address the possibly affected individuals. smart video surveillance; intelligent video surveillance; machine learning; human pose estimation; privacy protection; online survey; exploratory study; time of day; public areas; gender; perceived privacy risk