https://scholar.dgist.ac.kr/handle/20.500.11750/11771 2026-04-04T11:17:44Z 2026-04-04T11:17:44Z Jeon, Hyeonjae Seo, Junghyun Kim, Taesoo Son, Sungho Lee, Jungki Choi, Gyeungho Lim, Yongseob https://scholar.dgist.ac.kr/handle/20.500.11750/58135 2026-01-08T21:40:12Z 2025-03-31T15:00:00Z

Title: RainSD: Rain style diversification module for image synthesis enhancement using feature-level style distribution Author(s): Jeon, Hyeonjae; Seo, Junghyun; Kim, Taesoo; Son, Sungho; Lee, Jungki; Choi, Gyeungho; Lim, Yongseob Abstract: Autonomous driving technology nowadays targets to level 4 or beyond, but the researchers are faced with some limitations for developing reliable driving algorithms in diverse challenges. To promote the spread of autonomous vehicles widely, it is important to address safety issues in this technology. Among various safety concerns, the sensor blockage problem by severe weather conditions can be one of the most frequent threats for multi-task learning-based perception algorithms during autonomous driving. To handle this problem, the importance of generating proper datasets is becoming more significant. In this paper, a synthetic road dataset with sensor blockage generated from real road dataset BDD100K is suggested in the format of BDD100K annotation. Rain streaks for each frame were made using an experimentally established equation and translated utilizing the image-to-image translation network based on style transfer. Using this dataset, the degradation of the diverse multitask networks for autonomous driving, such as lane detection, driving area segmentation, and traffic object detection, has been thoroughly evaluated and analyzed. The tendency of performance degradation of deep neural network-based perception systems for autonomous vehicles has been analyzed in depth. Finally, we discuss the limitation and future directions of deep neural network-based perception algorithms and autonomous driving dataset generation based on image-to-image translation. © 2025

2025-03-31T15:00:00Z 전현재 박성정 손성호 이정기 안진웅 최경호 임용섭 https://scholar.dgist.ac.kr/handle/20.500.11750/57801 2025-07-25T02:47:07Z 2024-11-30T15:00:00Z

Title: CARLA 시뮬레이터 기반 합성 평가 데이터셋을 활용한 극한 폭우 상황에서의 심층 신경망을 이용한 차선 인식 성능 평가 Author(s): 전현재; 박성정; 손성호; 이정기; 안진웅; 최경호; 임용섭 Abstract: Autonomous driving technology nowadays targets to level 4 or beyond, but the researchers are faced with some limitations for developing reliable driving algorithms in diverse challenges. To promote the autonomous vehicles to spread widely, it is important to properly deal with the safety issues on this technology. Among various safety concerns, the sensor blockage problem by severe weather conditions can be one of the most frequent threats for lane de-tection algorithms during autonomous driving. To handle this problem, the importance of the generation of proper datasets is becoming more significant. In this paper, a synthetic lane dataset with sensor blockage is suggested in the format of lane detection evaluation. Rain streaks for each frame were made by an experimentally established equation. Using this dataset, the degradation of the diverse lane detection methods has been verified. The trend of the per-formance degradation of deep neural network- based lane detection methods has been analyzed in depth. Finally, the limitation and the future directions of the network-based methods were presented.

2024-11-30T15:00:00Z Seo, Junghyun Wang, Sungjun Jeon, Hyeonjae Kim, Taesoo Jin, Yongsik Kwon, Soon Kim, Je-Seok Lim, Yongseob https://scholar.dgist.ac.kr/handle/20.500.11750/57347 2025-07-25T02:45:37Z 2024-09-30T15:00:00Z

Title: LuminanceGAN: Controlling the brightness of generated images for various night conditions Author(s): Seo, Junghyun; Wang, Sungjun; Jeon, Hyeonjae; Kim, Taesoo; Jin, Yongsik; Kwon, Soon; Kim, Je-Seok; Lim, Yongseob Abstract: There are diverse datasets available for training deep learning models utilized in autonomous driving. However, most of these datasets are composed of images obtained in day conditions, leading to a data imbalance issue when dealing with night condition images. Several day-to-night image translation models have been proposed to resolve the insufficiency of the night condition dataset, but these models often generate artifacts and cannot control the brightness of the generated image. In this study, we propose a LuminanceGAN, for controlling the brightness degree in night conditions to generate realistic night image outputs. The proposed novel Y-control loss converges the brightness degree of the output image to a specific luminance value. Furthermore, the implementation of the self-attention module effectively reduces artifacts in the generated images. Consequently, in qualitative comparisons, our model demonstrates superior performance in day-to-night image translation. Additionally, a quantitative evaluation was conducted using lane detection models, showing that our proposed method improves performance in night lane detection tasks. Moreover, the quality of the generated indoor dark images was assessed using an evaluation metric. It can be proven that our model generates images most similar to real dark images compared to other image translation models. © 2024 Elsevier B.V.

2024-09-30T15:00:00Z Sadiq, Bilal Lim, Sungjin Jin, Yongsik Choi, Gyeungho Lim, Yongseob https://scholar.dgist.ac.kr/handle/20.500.11750/57244 2025-07-25T03:34:03Z 2024-10-31T15:00:00Z

Title: MPC-Based Exponential Weight Laguerre Function With Non-Singular Terminal SMC for Four-Wheel Independent Drive Electric Vehicles Author(s): Sadiq, Bilal; Lim, Sungjin; Jin, Yongsik; Choi, Gyeungho; Lim, Yongseob Abstract: This article describes a complete control method that uses Laguerre exponentially weighted model predictive control (LEMPC) to help four-wheel independent drive electric vehicles stay stable and follow their paths. The proposed method incorporates an enhanced direct yaw moment control using a robust non-singular terminal sliding mode control framework. We evaluated traditional, Laguerre, and exponentially weighted model predictive control methodologies (TMPC, LMPC, and LEMPC), respectively, with comparisons of reduced computational load and complexity while maintaining path tracking. The weighted Laguerre model predictive control exhibits improved robustness and reduced computational time and load. The suggested strong non-singular terminal sliding mode control (NTSMC) combined with LEMPC improved control and stability in a wide range of maneuvering situations and levels of uncertainty. The synergistic impact of NTMSC with LEMPC was examined to improve path tracking efficacy and dynamic stability under diverse road conditions and disturbances. The effectiveness of the control strategy in handling and stability of vehicle at high speed while maintaining efficient path tracking was validated by simulation conducted in MATLAB/Simulink along with high-fidelity co-Simulink Carsim environment. © IEEE.

2024-10-31T15:00:00Z