LSTM-based System for Multiple Obstacle Detection using Ultra-wide Band Radar

Mimouna, Amira; Khalifa, Anouar Ben; Alouani, Ihsen; Taleb‐Ahmed, Abdelmalik; Rivenq, Atika; Amara, Najoua Essoukri Ben

doi:10.5220/0010386904180425

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[99] proposes a network called DANet, which, by the extraction of temporal and multi-scale spatial features, detects objects in range-angle radar images. [101] applies Recurrent Neural Networks in the processing of Ultra-Wide Band radar signals for road obstacle detection. [103] introduce a Radar-based real-time Fig.…”

Section: B Radarmentioning

confidence: 99%

Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics

Manfio¹,

Osório²

2023

Preprint

View full text Add to dashboard Cite

One of the main paths towards the reduction of traffic accidents is the increase in vehicle safety through driver assistance systems or even systems with a complete level of autonomy. In these types of systems, tasks such as obstacle detection and segmentation, especially the Deep Learning-based ones, play a fundamental role in scene understanding for correct and safe navigation. Besides that, the wide variety of sensors in vehicles nowadays provides a rich set of alternatives for improvement in the robustness of perception in challenging situations, such as navigation under lighting and weather adverse conditions. Despite the current focus given to the subject, the literature lacks studies on radar-based and radar-camera fusionbased perception. Hence, this work aims to carry out a study on the current scenario of camera and radar-based perception for ADAS and autonomous vehicles. Concepts and characteristics related to both sensors, as well as to their fusion, are presented. Additionally, we give an overview of the Deep Learning-based detection and segmentation tasks, and the main datasets, metrics, challenges, and open questions in vehicle perception.

show abstract

Section: B Radarmentioning

confidence: 99%

Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics

Manfio¹,

Osório²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, the combination of multiple deep learning models has been investigated to generate data from multiple sensors, incorporating techniques such as Generative Adversarial Networks (GANs) [66], [67], [68] and [69]. In the context of robotics and autonomous systems, deep learning techniques, such as Convolutional Neural Networks (CNNs) [70], [71] and [72], have been employed for the 3D localization of RFID antennas [73] and the detection of obstacles using Ultra Wide Band with Long Short-Term Memory Neural Networks, as demonstrated in [74], [75] and [76] . In [77] the authors addressed the problem of synthetic sensor data generation exploiting an autoregressive convolutional recurrent neural network model (CRNN); the neural network presented there incorporates measurements from sensors and heterogeneous information to generate synthetic data that can be used to augment real-world data, increasing diversity and robustness of datasets.…”

Section: A Related Workmentioning

confidence: 99%

Synthetic Sensor Measurement Generation With Noise Learning and Multi-Modal Information

Romanelli,

Martinelli

2023

IEEE Access

View full text Add to dashboard Cite

Deep learning has transformed data generation, particularly in creating synthetic sensor data. This capability is invaluable in fields like autonomous driving, robotics, and computer science. To achieve this, we train models using real data, enabling them to replicate sensor data closely. These models introduce variations and noise, enhancing diversity and realism. Prominent techniques, including generative adversarial networks (GANs), variational autoencoders (VAEs), and recurrent neural networks (RNNs), excel in generating synthetic sensor data. Our paper focuses on Autoregressive Convolutional Recurrent Neural Networks (CRNN) for Multivariate Time Series Prediction. We incorporate Denoising Autoencoders (DAE) to mimic real-world noise characteristics. Our model is trained and validated using Ultra Wide Band (UWB) and Ultra High-Frequency Radio Frequency Identification (UHF-RFID) sensor data. It integrates sensor measurements and diverse information sources to produce synthetic data complementing realworld data. While demonstrated with UHF-RFID and UWB sensors, these techniques extend to industrial automation, healthcare and environmental monitoring. While our methodology exhibits broad potential, we present practical demonstrations with UHF-RFID and UWB sensors. Our deep neural network model allows researchers to construct datasets for algorithm validation, eliminating the need for costly and time-consuming data collection.

show abstract

Synthetic Sensor Data Generation Exploiting Deep Learning Techniques and Multimodal Information

Romanelli

Martinelli

2023

IEEE Sens. Lett.

View full text Add to dashboard Cite

LSTM-based System for Multiple Obstacle Detection using Ultra-wide Band Radar

Cited by 3 publications

References 0 publications

Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics

Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics

Synthetic Sensor Measurement Generation With Noise Learning and Multi-Modal Information

Synthetic Sensor Data Generation Exploiting Deep Learning Techniques and Multimodal Information

Contact Info

Product

Resources

About