Object Detection For Sensor Data Classification Using Quantum Discrete Transform

Abstract

This research work aims to investigate how quantum discrete transform can be successfully employed as object detector in the context of remote sensing. The sensors must share the strictly limited computation capacity of a computer. To have the computation speeds required from real-time applications, the system must have a short computation delay while maintaining the quality of the output, e.g., the accuracy of the object detection. This research work proposes a quantum discrete transform-based computation scheme that can be implemented on computer of sensor networks composed of sensors. The scheme can consider regions where objects exist as more likely to be ones of higher spatial importance. It will process data from each region according to the spatial importance of that region. By prioritizing regions with high spatial importance, the computation delay involved in the object detection can be reduced. This research work will be underlining the potentialities of applying quantum computing to real time object detection from sensor data and gives the theoretical and experimental background for future investigations. newlineThe application of quantum technology for remote sensing has been considered for at least last 20 years. An active imaging information transmission technology for satellite-borne quantum remote sensing is proposed in past, providing solutions and technical basis for realizing active imaging technology relying on quantum mechanics principles. Quantum technology is also used in interferometric synthetic aperture radars. A residue connection problem in the phase unwrapping procedure as quadratic unconstrained binary optimization problem, can be solved by using the D-Wave quantum annealer. A quantum annealer application has been explored in past for subset feature selection and the classification of hyperspectral images. In this research work quantum discrete transform is proposed and analyzed which can be used for object detection in the data collected from sensors. In this research work various object d