Radar sensor based machine learning approach for precise vehicle position estimation

Abstract

Estimating vehicles’ position precisely is essential in Vehicular Adhoc Networks (VANETs) for their safe, autonomous, and reliable operation. The conventional approaches used for vehicles’ position estimation, like Global Positioning System (GPS) and Global Navigation Satellite System (GNSS), pose significant data delays and data transmission errors, which render them ineffective in achieving precision in vehicles’ position estimation, especially under dynamic environments. Moreover, the existing radar-based approaches proposed for position estimation utilize the static values of range and azimuth, which make them inefficient in highly dynamic environments. In this paper, we propose a radar-based relative vehicle positioning estimation method. In the proposed method, the dynamic range and azimuth of a Frequency Modulated Continuous Wave radar is utilized to precisely estimate a vehicle’s position. In the position estimation process, the speed of the vehicle equipped with the radar sensor, called the reference vehicle, is considered such that a change in the vehicle’s speed changes the range and azimuth of the radar sensor. For relative position estimation, the distance and relative speed between the reference vehicle and a nearby vehicle are used. To this end, only those vehicles are considered that have a higher possibility of coming in contact with the reference vehicle. The data recorded by the radar sensor is subsequently utilized to calculate the precision and intersection Over Union (IOU) values. You Only Look Once (YOLO) version 4 is utilized to calculate precision and IOU values from the data captured using the radar sensor. The performance is evaluated under various real-time traffic scenarios in a MATLAB-based simulator. Results show that our proposed method achieves 80.0% precision in position estimation and obtains an IOU value up to 87.14%, thereby outperforming the state-of-the-art.

A bi-level framework for real-time crash risk forecasting using artificial intelligence-based video analytics

“…Whilst a detailed description of video processing and its schematics are omitted from this paper, interested readers are referred to our earlier studies 27 , 28 . Succinctly, the YOLO algorithm was used for object detection in a traffic scene 29 , whereas the DeepSORT algorithm tracked the movement of the detected objects (both motorised and non-motorised). The trajectories obtained from automated analysis were meticulously examined and corrected for any measurement/calibration error.…”

Integration of MoS2 Memtransistor Devices and Analogue Circuits for Sensor Fusion in Autonomous Vehicle Target Localization

“…Sensor fusion involves the close knitted integration and processing of data from multiple sensors for a more comprehensive and accurate understanding of the environment. − It is a crucial aspect of autonomous driving technology. , A variety of sensors, including light detection and ranging (LiDAR), millimeter-wave radar (Radar), and cameras, are extensively utilized to capture diverse information about the vehicle’s surroundings. − However, individual sensors are easily subject to various interferences such as changing weather conditions, electromagnetic disturbances, laser obstruction etc., significantly affecting the measurement accuracy and reliability of the entire system. , Late fusion in autonomous driving involves processing data from various sensors independently and merging their outputs at a later stage . It is particularly useful in addressing the aforementioned challenges and is expected to revolutionize future autonomous driving technology.…”

CNN with New Spatial Pyramid Pooling and Advanced Filter-Based Techniques: Revolutionizing Traffic Monitoring via Aerial Images

“…These solutions offer the advantage of furnishing precise and varied information, encompassing details such as speed and heading direction. However, the drawbacks include the typically substantial installation size and the computational power required [4][5][6]. In recent times, advancements in computing hardware performance, coupled with the development of sophisticated machine learning techniques, have facilitated the reliable recognition of vehicles in images or video streams through machine vision approaches.…”