Stray dogs behavior detection in urban area video surveillance streams

Smart city solutions are increasingly important in the context of continuous population grow. The approach presented in this paper provides a solution for automatic detection of stray dog attacks in urban areas. It is based on existing video-camera urban infrastructure and uses movement feature extraction and classification algorithms in order to discriminate between normal and dangerous behavior for a group of stray dogs. The output can be further used for an emergency on-line alert system.