This paper presents an approach for the detection and localization of abnormal events in pedestrian areas. The goal is to design a model to detect abnormal events in video sequences using motion and appearance information. Motion information is represented through the use of the velocity and acceleration of optical flow and the appearance information is represented by texture and optical flow gradient. Unlike literature methods, our proposed approach provides a general solution to detect both global and local abnormal events. Furthermore, in the detection stage, we propose a classification by local regions. Experimental results on UMN and UCSD datasets confirm that the detection accuracy of our method is comparable to state-of-the-art methods.

Object recognition in the field of computer vision is a constant challenge to achieve better precision in less time. In this research, is proposed a new 3D descriptor, to work with depth cameras called CPPFL, based on the PPF descriptor from [1]. This proposed descriptor takes advantage of color information and groups it more effectively and lightly than the CPPF descriptor from [2], which uses the color information too. Also, it is proposed as an alternative descriptor called CPPFL+, which differs in the construction taking advantage of the same concept of grouping colors, so it gains a “plus” in speed. This change makes the descriptor more efficient compared to PPF and CPPF descriptors. Optimizing the object recognition process [3], it can reach a rate of ten frames per second or more depending on the size of the object. The proposed descriptor is more tolerant to illuminations changes since the hue of a color is more relevant than the other components.

Background In order to detect threats to public health and to be well-prepared for endemic and pandemic illness outbreaks, countries usually rely on event-based surveillance (EBS) and indicator-based surveillance systems. Event-based surveillance systems are key components of early warning systems and focus on fast capturing of data to detect threat signals through channels other than traditional surveillance. In this study, we develop Natural Language Processing tools that can be used within EBS systems. In particular, we focus on information extraction techniques that enable digital surveillance to monitor Internet data and social media. Results We created an annotated Spanish corpus from ProMED-mail health reports regarding disease outbreaks in Latin America. The corpus has been used to train algorithms for two information extraction tasks: named entity recognition and relation extraction. The algorithms, based on deep learning and rules, have been applied to recognize diseases, hosts, and geographical locations where a disease is occurring, among other entities and relations. In addition, an in-depth analysis of micro-average F1 metrics shows the suitability of our approaches for both tasks. Conclusions The annotated corpus and algorithms presented could leverage the development of automated tools for extracting information from news and health reports written in Spanish. Moreover, this framework could be useful within EBS systems to support the early detection of Latin American disease outbreaks.