Junho Koh

Junho Koh

Auto-generated profile, based on publicly available information

Junho Koh

Autonomous Driving Development Center, Hyundai Motors, Seongnam-si, Republic of Korea

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
25 May 2019
Verified
Book Chapter
Closed access
PDF file
JKJaekyum Kim
Jaekyum Kim
JKJunho Koh
Junho Koh
YKYecheol Kim
Yecheol Kim
JCJaehyung Choi
Jaehyung Choi
Youngbae HwangYoungbae Hwang
Youngbae Hwang
JCJun Won Choi
Jun Won Choi

13 May 2024
Verified
Conference Paper
Open access
KPKonyul Park
Konyul Park
YKYecheol Kim
Yecheol Kim
JKJunho Koh
Junho Koh
BPByungwoo Park
Byungwoo Park
JCJun Won Choi
Jun Won Choi
Developing high-performance, real-time architectures for LiDAR-based 3D object detectors is essential for the successful commercialization of autonomous vehicles. Pillar-based methods stand out as a practical choice for onboard deployment due to their computational efficiency. However, despite their efficiency, these methods can sometimes underperform compared to alternative point encoding techniques such as Voxel-encoding or PointNet++. We argue that current pillar-based methods have not sufficiently captured the fine-grained distributions of LiDAR points within each pillar structure. Consequently, there exists considerable room for improvement in pillar feature encoding. In this paper, we introduce a novel pillar encoding architecture referred to as Fine-Grained Pillar Feature Encoding (FG-PFE). FG-PFE utilizes Spatio-Temporal Virtual (STV) grids to capture the distribution of point clouds within each pillar across vertical, temporal, and horizontal dimensions. Through STV grids, points within each pillar are individually encoded using Vertical PFE (V-PFE), Temporal PFE (T-PFE), and Horizontal PFE (H-PFE). These encoded features are then aggregated through an Attentive Pillar Aggregation method. Our experiments conducted on the nuScenes dataset demonstrate that FG-PFE achieves significant performance improvements over baseline models such as PointPillar, CenterPoint-Pillar, and PillarNet, with only a minor increase in computational overhead.

1 October 2022 in Transaction of the Korean Society of Automotive Engineers
Verified
Journal Article
Open access
JBJongwook Bae
Jongwook Bae
YLYoungwoo Lee
Youngwoo Lee
JKJunho Koh
Junho Koh
JLJaeyoung Lee
Jaeyoung Lee
JCJun Won Choi
Jun Won Choi

28 August 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
JKJunho Koh
Junho Koh
YLYoungwoo Lee
Youngwoo Lee
JKJungho Kim
Jungho Kim
DLDongyoung Lee
Dongyoung Lee
JCJun Won Choi
Jun Won Choi
Multi-view camera-based 3D perception can be conducted using bird’s eye view (BEV) features obtained through perspective view-to-BEV transformations. Several studies have shown that the performance of these 3D perception methods can be further enhanced by combining sequential BEV features obtained from multiple camera frames. However, even after compensating for the ego-motion of an autonomous agent, the performance gain from temporal aggregation is limited when combining a large number of image frames. This limitation arises due to dynamic changes in BEV features over time caused by object motion. In this paper, we introduce a novel temporal 3D perception method called OnlineBEV, which combines BEV features over time using a recurrent structure. This structure increases the effective number of combined features with minimal memory usage. However, it is critical to spatially align the features over time to maintain strong performance. OnlineBEV employs the Motion-guided BEV Fusion Network (MBFNet) to achieve temporal feature alignment. MBFNet extracts motion features from consecutive BEV frames and dynamically aligns historical BEV features with current ones using these motion features. To enforce temporal feature alignment explicitly, we use Temporal Consistency Learning Loss, which captures discrepancies between historical and target BEV features. Experiments conducted on the nuScenes benchmark demonstrate that OnlineBEV achieves significant performance gains over the current best method, SOLOFusion. OnlineBEV achieves 63.9% NDS on the nuScenes test set, recording state-of-the-art performance in the camera-only 3D object detection task.