Gyuhee Park

Mr. Gyuhee Park

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 July 2024 in Sensors
Verified
Journal Article
Open access
PDF file
GPGyuhee Park
Gyuhee Park
JKJunho Koh
Junho Koh
JKJisong Kim
Jisong Kim
JMJun Moon
Jun Moon
JCJun Won Choi
Jun Won Choi
Recently, the growing demand for autonomous driving in the industry has led to a lot of interest in 3D object detection, resulting in many excellent 3D object detection algorithms. However, most 3D object detectors focus only on a single set of LiDAR points, ignoring their potential ability to improve performance by leveraging the information provided by the consecutive set of LIDAR points. In this paper, we propose a novel 3D object detection method called temporal motion-aware 3D object detection (TM3DOD), which utilizes temporal LiDAR data. In the proposed TM3DOD method, we aggregate LiDAR voxels over time and the current BEV features by generating motion features using consecutive BEV feature maps. First, we present the temporal voxel encoder (TVE), which generates voxel representations by capturing the temporal relationships among the point sets within a voxel. Next, we design a motion-aware feature aggregation network (MFANet), which aims to enhance the current BEV feature representation by quantifying the temporal variation between two consecutive BEV feature maps. By analyzing the differences and changes in the BEV feature maps over time, MFANet captures motion information and integrates it into the current feature representation, enabling more robust and accurate detection of 3D objects. Experimental evaluations on the nuScenes benchmark dataset demonstrate that the proposed TM3DOD method achieved significant improvements in 3D detection performance compared with the baseline methods. Additionally, our method achieved comparable performance to state-of-the-art approaches.

30 April 2025 in The Journal of Korean Institute of Information Technology
Verified
Journal Article
Closed access
GPGyuhee Park
Gyuhee Park
JCJun Won Choi
Jun Won Choi
3D 환경에서의 정확한 인식은 자율 주행, 로봇 공학과 같은 분야에서 매우 중요합니다. 그러나 실제 환경에서는 날씨 변화, 센서 구성 차이 그리고 지리적 요인으로 인해 데이터 분포가 크게 변화 할 수 있고, 이러한 변화로 인해 3D 인식 신경망의 성능이 저하되는 경우가 많습니다. 이 한계를 극복하기 위하여 도메인 적응 기법이 제안되었으며, 이는 제한된 환경에서의 레이블된 데이터를 활용하여 타겟 도메인에서의 성능을 향상시키기 위해 소스 도메인의 풍부한 학습 데이터를 효과적으로 활용하는 기법입니다. 본 연구에서는 먼저 LiDAR 인식 신경망과 도메인 적응의 기본 개념을 설명한 후, 이어서 도메인 적응 기술을 증강 기반, 지도 기반, 수도 레이블 기반으로 분류하여 자율 주행에 맞춤화된 접근 방식에 대한 자세한 통찰력을 기술합니다.