industry news
Subscribe Now

INU Researchers Develop Novel Deep Learning-Based Detection System for Autonomous Vehicles

The new system, aided by the Internet of things, improves the detection capabilities of autonomous vehicles even under unfavorable conditions.
Autonomous vehicles require object detection systems to navigate traffic and avoid obstacles on the road. However, current detection methods often suffer from diminished detection capabilities due to bad weather, unstructured roads, or occlusion. Now, a team of researchers have developed a novel Internet-of-Things-enabled deep learning-based end-to-end 3D object detection system with improved detection capabilities even under unfavorable conditions. This study marks a significant step in autonomous vehicle object detection technology.
 
Autonomous vehicles hold the promise of tackling traffic congestion, enhancing traffic flow through vehicle-to-vehicle communication, and revolutionizing the travel experience by offering comfortable and safe journeys. Additionally, integrating autonomous driving technology into electric vehicles could contribute to more eco-friendly transportation solutions.
A critical requirement for the success of autonomous vehicles is their ability to detect and navigate around obstacles, pedestrians, and other vehicles across diverse environments. Current autonomous vehicles employ smart sensors such as LiDARs (Light Detection and Ranging) for a 3D view of the surroundings and depth information, RADaR (Radio Detection and Ranging) for detecting objects at night and cloudy weather, and a set of cameras for providing RGB images and a 360-degree view, collectively forming a comprehensive dataset known as point cloud. However, these sensors often face challenges like reduced detection capabilities in adverse weather, on unstructured roads, or due to occlusion.
To overcome these shortcomings, an international team of researchers led by Professor Gwanggil Jeon from the Department of Embedded Systems Engineering at Incheon National University (INU), Korea, has recently developed a groundbreaking Internet-of-Things-enabled deep learning-based end-to-end 3D object detection system. “Our proposed system operates in real time, enhancing the object detection capabilities of autonomous vehicles, making navigation through traffic smoother and safer,” explains Prof. Jeon. Their paper was made available online on October 17, 2022, and published in Volume 24, Issue 11 of the journal IEEE Transactions on Intelligent Transport Systems on November 2023.
 
The proposed innovative system is built on the YOLOv3 (You Only Look Once) deep learning object detection technique, which is the most active state-of-the-art technique available for 2D visual detection. The researchers first used this new model for 2D object detection and then modified the YOLOv3 technique to detect 3D objects. Using both point cloud data and RGB images as input, the system generates bounding boxes with confidence scores and labels for visible obstacles as output.
To assess the system’s performance, the team conducted experiments using the Lyft dataset, which consisted of road information captured from 20 autonomous vehicles traveling a predetermined route in Palo Alto, California, over a four-month period. The results demonstrated that YOLOv3 exhibits high accuracy, surpassing other state-of-the-art architectures. Notably, the overall accuracy for 2D and 3D object detection were an impressive 96% and 97%, respectively.
Prof. Jeon emphasizes the potential impact of this enhanced detection capability: “By improving detection capabilities, this system could propel autonomous vehicles into the mainstream. The introduction of autonomous vehicles has the potential to transform the transportation and logistics industry, offering economic benefits through reduced dependence on human drivers and the introduction of more efficient transportation methods.
Furthermore, the present work is expected to drive research and development in various technological fields such as sensors, robotics, and artificial intelligence. Going ahead, the team aims to explore additional deep learning algorithms for 3D object detection, recognizing the current focus on 2D image development.
In summary, this groundbreaking study could pave the way for a widespread adoption of autonomous vehicles and, in turn, a more environment-friendly and comfortable mode of transport.
***
Reference
Title of original paper: A Smart IoT Enabled End-to-End 3D Object Detection System for Autonomous Vehicles
Journal: IEEE Transactions on Intelligent Transport Systems

Leave a Reply

featured blogs
Jul 17, 2025
Why do the links in Outlook emails always open in the Microsoft Edge web browser, even if you have another browser set as your default?...

Libby's Lab

Libby's Lab - Scopes out Littelfuse C&K Aerospace AeroSplice Connectors

Sponsored by Mouser Electronics and Littelfuse

Join Libby and Demo in this episode of “Libby’s Lab” as they explore the Littelfuse C&K Aerospace Aerosplice Connectors, available at Mouser.com! These connectors are ideal for high-reliability easy-to-use wire-to-wire connections in aerospace applications. Keep your circuits charged and your ideas sparking!

Click here for more information

featured paper

AI-based Defect Detection System that is Both High Performance and Highly Accurate Implemented in Low-cost, Low-power FPGAs

Sponsored by Altera

Learn how MAX® 10 FPGAs enable real-time, high-accuracy AI-based defect detection at the industrial edge without a GPU. This white paper explores a production-proven solution that delivers 24× higher accuracy, 488× lower latency, and 20× lower power than traditional approaches, with a compact footprint ideal for embedded vision systems.

Click to read more

featured chalk talk

Qorvo Accelerating Matter Product Development with Qorvo QPG6200
Sponsored by Mouser Electronics and Qorvo
In this episode of Chalk Talk, Tim Allemeersch from Qorvo and Amelia Dalton explore the challenges of Matter application development and how Qorvo can help you navigate the landscape of Matter development. They also investigate the benefits of Qorvo’s QPG6200 IC and how you can get started using this integrated circuit for your next Matter design.
Jul 16, 2025
1,641 views