Deep Learning for Intelligent Surveillance Systems
1University of Alicante, Alicante, Spain
2Universidad Tecnologica de Panama, Panama City, Spain
3Google, Mountain View, USA
Deep Learning for Intelligent Surveillance Systems
Description
Surveillance systems, mainly composed of cameras, are today widespread in both indoor and outdoor environments. The purpose of these systems can be security, activity detection, or recognition and prediction of behaviour, among others. Examples of applications for which it may be useful are public safety, traffic surveillance, or monitoring of people's activities.
There are many lines of research to make this type of system a reality. For example, the identification and tracking of objects and the analysis of behaviour in intelligent surveillance are still affected by a number of practical problems. Recent advances in computer vision, and especially with deep learning techniques, offer new perspectives for these systems, increasing their capabilities and initiating new directions of research in this field. Convolutional neural networks have shown high performance in image recognition and their combination with recurrent neural networks enables temporal information understanding, and so the development of these techniques can have a significant impact on intelligent surveillance systems.
The aim of this Special Issue is to provide a platform to publish advances in intelligent surveillance systems, especially with deep learning techniques. We welcome the submission of original research articles, reviews of the state of the art, and works exploring new challenges in the field.
Potential topics include but are not limited to the following:
- Emotion and gesture recognition
- Object tracking and segmentation
- Scene understanding and human behaviour analysis
- Scene understanding and human behaviour analysis
- Person re-identification
- Activity detection and recognition
- Human computer/robot interaction
- Crowd dynamics and crowd analysis
- Wildlife entity detection and tracking