Multi-Frequency Based CSI Compression for Vehicle Localization in Intelligent Transportation System

With the advent of the new era of 6G, new applications of smart factories and intelligent transportation systems based on real-time wireless sensing technology will confront great demands and challenges. In the intelligent transportation system, it is essential to realize services such as localization and intrusion detection for intelligent vehicles. To build a wide range of positioning network based on large-scale wireless networks, it is of great challenge to simultaneously solve the problem of unacceptable delay and bandwidth requirements caused by a large number of channel state information (CSI) data transmission. Therefore, we propose a novel algorithm, named PAOFIT, where a projection transformation aided CSI curve fitting compression algorithm is firstly proposed to decrease data distortions by improving the orthogonality of signal subspace and noise subspace, and an adaptive weighted average fitting order judgment algorithm is proposed to calculate the fitting order needed in the curve fitting process. Then, localization parameter, time of flight (ToF) are estimated by CSI reconstruction and parameter estimation. Finally, the location of the target is obtained by substituting these parameters into time difference of arrival (TDoA) wireless localization technology. Extensive experimental results verify that, compared with the existing compression algorithms, the proposed PAOFIT has a better performance in terms of compression ratio, median positioning error, residual and execution time.

I. Introduction

In recent years, with the development of 6G network, completely new applications such as deep human-machine interaction, intelligent plants, intelligent medical treatment, and smart transport are being given birth, and the integration of communication and perception has gradually become the focus of industry and academia [1]. In smart traffic control and management, the acquisition and subsequent processing of traffic data influence the localization of smart vehicles as well as the management of invasion detection and so on. Moreover, due to the fusion of communication and perception, part of the perceptual operations performed at a terminal can be transferred to base station execution, thus reducing the communication load between base stations and terminals. In addition, wireless sensing is utilized to acquire rich environmental information to improve the communication system. What’s more, it will open new scenarios for network services and also provide a data portal for building smart digital world [2], [3]. For large-scale wireless traffic networks, the most obvious feature is that the amount of vehicle data increases dramatically, which makes the cost of storing and transmitting CSI in the localization of smart vehicles greatly increase, the speed and efficiency decrease, and the real time of the targeting be affected. Therefore, it is imperative to reduce the cost of storing and transmitting CSI through data compression and ensure the accuracy of data reconstruction. The solution to these problems will benefit the development of wireless sensing technologies such as CSI based invasion detection, activity recognition, localization and so on in smart traffic control and management. In addition, using compression algorithm to compress and reconstruct channel state information is of great significance for parameter estimation and real-time location in intelligent transportation systems. By quickly and fully utilizing the channel information provided by CSI, accurate vehicle positioning and navigation are realized to support the development and application of intelligent transportation systems.