no code implementations • 24 Feb 2022 • Hyeonsoo Jang, YeongMin Ko, Younkwan Lee, Moongu Jeon
Our methods not only outperform the state-of-the-art works across all metrics but also efficient in terms of cost, memory, and computation.
no code implementations • 14 Oct 2021 • Younkwan Lee, Jihyo Jeon, YeongMin Ko, Byunggwan Jeon, Moongu Jeon
Visual perception in autonomous driving is a crucial part of a vehicle to navigate safely and sustainably in different traffic conditions.
2 code implementations • 4 Sep 2020 • Yechan Kim, Younkwan Lee, Moongu Jeon
Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets.
no code implementations • 3 Apr 2020 • Younkwan Lee, Jihyo Jeon, Jongmin Yu, Moongu Jeon
Specifically, we present a lower bound for the mutual information constraint between shared feature embedding and input that is considered to be able to extract common contextual information across tasks while preserving essential information of each task jointly.
10 code implementations • 16 Feb 2020 • Yeongmin Ko, Younkwan Lee, Shoaib Azam, Farzeen Munir, Moongu Jeon, Witold Pedrycz
In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and computing power of the target system.
Ranked #40 on Lane Detection on CULane
1 code implementation • 30 Jan 2020 • Jongmin Yu, Duyong Kim, Younkwan Lee, Moongu Jeon
To end this, we propose an unsupervised approach to detecting road defects, using Adversarial Image-to-Frequency Transform (AIFT).
no code implementations • 10 Oct 2019 • Younkwan Lee, Juhyun Lee, Yoojin Hong, YeongMin Ko, Moongu Jeon
Recent road marking recognition has achieved great success in the past few years along with the rapid development of deep learning.
1 code implementation • 10 Oct 2019 • Younkwan Lee, Jiwon Jun, Yoojin Hong, Moongu Jeon
Although most current license plate (LP) recognition applications have been significantly advanced, they are still limited to ideal environments where training data are carefully annotated with constrained scenes.
Ranked #3 on License Plate Recognition on AOLP-RP
no code implementations • 9 Oct 2019 • Younkwan Lee, Juhyun Lee, Hoyeon Ahn, Moongu Jeon
In this paper, we present an algorithm for real-world license plate recognition (LPR) from a low-quality image.
Ranked #1 on License Plate Recognition on AOLP-RP