Multi-modal Data based Semi-Supervised Learning for Vehicle Positioning

TL;DR

This paper introduces a semi-supervised learning framework that combines channel state information and RGB images to improve vehicle positioning accuracy in outdoor systems, reducing error by up to 30%.

Contribution

It proposes a novel SSL framework that leverages unlabeled CSI data and images for vehicle positioning, with a two-stage training process including pretraining and fine-tuning.

Findings

Reduces positioning error by up to 30%.

Effectively utilizes unlabeled CSI and image data.

Improves accuracy over baseline models without pretraining.

Abstract

In this paper, a multi-modal data based semi-supervised learning (SSL) framework that jointly use channel state information (CSI) data and RGB images for vehicle positioning is designed. In particular, an outdoor positioning system where the vehicle locations are determined by a base station (BS) is considered. The BS equipped with several cameras can collect a large amount of unlabeled CSI data and a small number of labeled CSI data of vehicles, and the images taken by cameras. Although the collected images contain partial information of vehicles (i.e. azimuth angles of vehicles), the relationship between the unlabeled CSI data and its azimuth angle, and the distances between the BS and the vehicles captured by images are both unknown. Therefore, the images cannot be directly used as the labels of unlabeled CSI data to train a positioning model. To exploit unlabeled CSI data and images, a SSL framework that consists of a pretraining stage and a downstream training stage is proposed. In the pretraining stage, the azimuth angles obtained from the images are considered as the labels of unlabeled CSI data to pretrain the positioning model. In the downstream training stage, a small sized labeled dataset in which the accurate vehicle positions are considered as labels is used to retrain the model. Simulation results show that the proposed method can reduce the positioning error by up to 30% compared to a baseline where the model is not pretrained.