Cooperative Perception of Roadside Unit and Onboard Equipment with Edge Artificial Intelligence for Driving Assistance [supporting datasets]
-
2021-11-29
-
Details:
-
Alternative Title:Data for Cooperative Perception of Road-Side Unit and On-board Equipment with Edge Artificial Intelligence for Driving Assistance [Dataset title]
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
DOI:
-
Resource Type:
-
Geographical Coverage:
-
Corporate Publisher:
-
Abstract:Recently, 2D detection in images has made significant progress owing to the emergence of a convolutional neural network (CNN), which can extract high-level features from the images. However, detecting objects in 3D instead of 2D space is an essential topic when building perception systems for autonomous driving. An autonomous vehicle (AV) needs to perceive the objects present in the 3D scene from its sensors to plan its motion safely. Therefore, a series of solutions based on Stereo Cameras, Light Detection, and Ranging (LiDAR) is proposed in existing connected and autonomous vehicle (CAV) systems to provide 3D location information to the vehicles. However, all the technologies suffer from a fatal challenge on edge computing: computing resource limitation. As a result, even though powerful, heavy, and expensive on-vehicle computers are equipped with CAVs, some unavoidable calculation errors or delays often happen and result in some severe consequences. To address the challenge and provide more reliable real-time localization services for the CAVs, the team proposed a smart roadside unit (SRSU) for driving or parking assistance with advanced computer vision technologies. The SRSU sensor is a multi-source traffic sensing roadside unit developed by the Smart Transportation Applications and Research Laboratory (STAR Lab) at the University of Washington (UW). It can transmit data through 4G/5G data plan or Long Range (LoRa) and Narrow Band Internet of Things (NB-loT) data communication protocols. In this research, the smart roadside unit, Mobile Unit for Traffic Sensing (MUST) developed by the research team, is employed for both data analysis and communication with surrounding vehicles.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type: