Jaeyeul Kim

Mr. Jaeyeul Kim

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 June 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JKJaeyeul Kim
Jaeyeul Kim
JWJungwan Woo
Jungwan Woo
SISunghoon Im
Sunghoon Im
Detecting traffic participants is an essential and age-old problem in autonomous driving. Recently, the recognition of moving objects has emerged as a major issue in this field for safe driving. In this paper, we present RVMOS, a LiDAR Range-View-based Moving Object Segmentation framework that segments moving objects given a sequence of range-view images. In contrast to the conventional method, our network incorporates both motion and semantic features, each of which encodes the motion of objects and the surrounding circumstance of the objects. In addition, we design a new feature extraction module suitably designed for range-view images. Lastly, we introduce simple yet effective data augmentation methods: time interval modulation and zero residual image synthesis. With these contributions, we achieve a 19% higher performance (mIoU) with 10% faster computational time (34 FPS on RTX 3090) than the state-of-the-art method with the SemanticKitti benchmark. Extensive experiments demonstrate the effectiveness of our network design and data augmentation scheme.

1 September 2020 in IEEE Access
Verified
Journal Article
Open access
JKJaeyeul Kim
Jaeyeul Kim
JHJong-Eun Ha
Jong-Eun Ha
Visual surveillance aims to reliably extract foreground objects. Traditional algorithms usually use a background model image which is generated through the probabilistic modeling of changes over time and space. They detect foreground objects by comparing a background model image with a current image. Hard shadows, illumination changes, camouflage, camera jitter, and ghost object motion make the robust detection of foreground objects difficult in visual surveillance. Recently, various methods based on deep learning have been applied to visual surveillance. It has been shown that deep learning approaches can stably extract salient features, and they give a superior result compared to traditional algorithms. However, they show a good performance only for scenes that are similar to a scene used in training. Without retraining on a new scene, they give a worse result compared to traditional algorithms. In this paper, we propose a stable foreground object detection algorithm through the integration of a background model image used in traditional methods and deep learning methods. A background model image generated by SuBSENSE and multiple images are used as the input of a fully convolutional network. Also, it is shown that it is possible to improve a generalization power by training the proposed network using diverse scenes from an open dataset. We show that the proposed algorithm can have a superior result compared to deep learning-based and traditional algorithms in a new scene without retraining the network. The performance of the proposed algorithm is evaluated using various datasets such as the CDnet 2014, SBI, LASIESTA, and our own datasets. The proposed algorithm shows improvement of 17.5%, 8.9%, and 4.3%, respectively, in FM score compared to three deep learning-based algorithms.

14 February 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JKJaeyeul Kim
Jaeyeul Kim
JWJungwan Woo
Jungwan Woo
USUkcheol Shin
Ukcheol Shin
JOJean Oh
Jean Oh
SISunghoon Im
Sunghoon Im
Understanding the motion states of the surrounding environment is critical for safe autonomous driving. These motion states can be accurately derived from scene flow, which captures the three-dimensional motion field of points. Existing LiDAR scene flow methods extract spatial features from each point cloud and then fuse them channel-wise, resulting in the implicit extraction of spatio-temporal features. Furthermore, they utilize 2D Bird's Eye View and process only two frames, missing crucial spatial information along the Z-axis and the broader temporal context, leading to suboptimal performance. To address these limitations, we propose Flow4D, which temporally fuses multiple point clouds after the 3D intra-voxel feature encoder, enabling more explicit extraction of spatio-temporal features through a 4D voxel network. However, while using 4D convolution improves performance, it significantly increases the computational load. For further efficiency, we introduce the Spatio-Temporal Decomposition Block (STDB), which combines 3D and 1D convolutions instead of using heavy 4D convolution. In addition, Flow4D further improves performance by using five frames to take advantage of richer temporal information. As a result, the proposed method achieves a 45.9% higher performance compared to the state-of-the-art while running in real-time, and won 1st place in the 2024 Argoverse 2 Scene Flow Challenge.

7 October 2020 in IEEE Access
Verified
Journal Article
Open access
JKJaeyeul Kim
Jaeyeul Kim
JHJong-Eun Ha
Jong-Eun Ha
Extrinsic calibration of a camera and a LiDAR is necessary to fuse information from each sensor. The real trajectory of the LiDAR is not visible on an image, therefore the accuracy of the extrinsic calibration is usually checked by evaluating residuals of constraints. In this paper, we present an improved extrinsic calibration algorithm of a camera and a 2D LiDAR using an additional dummy camera removing IR cut filter, which make it possible to observe the real trajectory of LiDAR. Some previous algorithms used the real trajectory of LiDAR for the extrinsic calibration. However, they used IR filter directly on the calibrating camera by adjusting exposure time, which can affect the result of the extrinsic calibration.We use an initial solution using the Hu algorithm which makes extrinsic calibration possible by using just one shot of data. The Hu algorithm gives a sensitive result according to pose variation between a system consisted of a camera and a LiDAR and a calibration structure, which is verified using the real trajectory of LiDAR. We cope with this problem by refining the initial solution through nonlinear minimization in a 3D space using the real trajectory of LiDAR. Experimental results show that the proposed algorithm gives an improved solution.


10 September 2021 in IEEE Access
Verified
Journal Article
Open access
JKJaeyeul Kim
Jaeyeul Kim
JHJong-Eun Ha
Jong-Eun Ha
Proper consideration of the temporal domain and the spatial domain is essential to perform robust foreground object detection in visual surveillance. However, there are difficulties in considering long-term temporal information with CNN-based methods. To solve this limitation, classical algorithms and some deep learning-based algorithms have used a background model image. However, acquiring a sophisticated background model image is also one of the complex problems. Most of the algorithms take a lot of time to initialize the background model image and generate many errors in the presence of a static foreground. This paper proposes an algorithm for generating a background model image using a deep-learning-based segmenter to solve this problem. The proposed method shows a 66.25% lower mean square error (MSE) than the background subtraction (BGS) algorithm and 79.25% lower than the latest deep learning algorithm in the SBI dataset. In addition, in the deep learning-based segmenter that uses a background image as input, replacing the background image of BGS algorithm with the background image of the proposed method shows a 38.63% reduction in the false detection rate (PWC).