Synthetic Sensor Data Generation Exploiting Deep Learning Techniques and Multimodal Information

Abstract

In recent years, deep learning techniques have revolutionized the field of data generation and manipulation, including the creation of synthetic sensor data. The ability to generate large quantities of diverse, high-quality data has significant implications in fields such as autonomous driving, robotics, and computer vision. Synthetic sensor data generation using deep learning techniques involves training a model to generate data that closely resembles real-world sensor data. This is achieved by feeding the model large amounts of real-world data and using it to learn the underlying patterns and structures in the data. Once trained, the model can then generate new data that are similar in quality and complexity to the original data, but with added variations and noise to increase diversity and realism. Several deep learning techniques as generative adversarial networks (GANs), variational autoencoders (VAEs), and recurrent neural networks (RNNs) have shown impressive results in generating synthetic data for a range of sensors, including lidar, radar, and camera. In this paper, deep learning techniques based on Autoregressive Convolutional Recurrent Neural Networks (CRNN) for Multivariate Time Series Prediction have been exploited to generate synthetic data for Ultra Wide Band (UWB) and for Ultra High Frequency Radio Frequency Identification (UHF-RFID) sensors. The neural network presented here incorporates measurements from sensors and heterogeneous information such as the position of the antennas and tags in the environment in order to generate synthetic data that can be used to augment real-world data, increasing the diversity and robustness of datasets. The deep generation approaches presented here can help researchers to generate datasets to validate algorithms and methodologies without the need for expensive and time-consuming data collection.

Topics & Concepts