A segmentation-based Radio Tomographic Imaging approach for interference reduction in hostile industrial environments

This paper presents and evaluates a passive device-free tracking system for localization of objects or persons. The system works with a continuous evaluation of the received signal strengths of connection links between fixed installed anchor nodes. Out of the evaluated measurements, an image of the scene can be generated based on Radio Tomographic Imaging (RTI). The major contribution of this paper is an application of segmentation algorithms for sharpening the image by reducing noise and interference. The applied combination of image segmentation with a connected component labeling algorithm enables an evaluation of certain areas in the image to estimate the position and the number of objects in the room. Finally, the application of particle filtering smoothes the estimated position and leads to a reliable and accurate position estimation, which is comparable with active solutions. As interference and noise in the link measurements caused by multipath propagation effects can harm the achievable accuracy, the foreseen application area - an industrial environment- poses a huge challenge, as the radio channel is highly affected by the metallic infrastructures.