A Feature Extraction Metod for Multimedia data Analysis in Robot Wireless Sensor Networks

Multimedia sensor networking technologies have developed very rapidly in the last ten years. Robot wireless sensor networks are an increasingly capable platform and show great potential in environments from future battlefields to disaster discovery. Robot wireless sensor networks can enhance multimedia surveillance and provide the foundation for strategies based on multi-modal sensor integration. We illustrate this concept with an example feature extraction approach for image or video data: lines are extracted as image features from images transformed using the Hough transform technique. This approach enables features to be combined and constrained by their structure, allowing for example region correspondence mapping between images from different sensors or the same sensor in different time phases.