Yeeun Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yeeun Kim has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Hyun Myung
School of Electrical Engineering, KAIST (Korea Advanced Institute of Science and Technology), Daejeon, Republic of Korea
6 shared publications - Hyunjun Lim
Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea
2 shared publications - Alex Junho Lee
Robotics Lab, Research and Development Division, Hyundai Motor Company, Uiwang, South Korea
1 shared publication - Byeongho Yu
School of Electrical Engineering KAIST (Korea Advanced Institute of Science and Technology) 34141 Daejeon Republic of Korea
1 shared publication - Eungchang Mason Lee
School of Electrical Engineering, KAIST (Korea Advanced Institute of Science and Technology), Daejeon, Republic of Korea
1 shared publication - Hae-Won Park
Korea Advanced Institute of Science and Technology
1 shared publication
Latest Publications
- Open Access
CHADET: Cross-Hierarchical-Attention for Depth-Completion Using Unsupervised Lightweight Transformer
Depth information which specifies the distance between objects and current position of the robot is essential for many robot tasks such as navigation. Recently, researchers have proposed depth completion frameworks to provide dense depth maps that offer comprehensive information about the surrounding environment. However, existing methods show significant trade-offs between computational efficiency and accuracy during inference. The substantial memory and computational requirements make them unsuitable for real-time applications, highlighting the need to improve the completeness and accuracy of depth information while improving processing speed to enhance robot performance in various tasks. To address these challenges, in this paper, we propose CHADET(cross-hierarchical-attention depth-completion transformer), a lightweight depth-completion network that can generate accurate dense depth maps from RGB images and sparse depth points. For each pair, its feature is extracted from the depthwise blocks and passed to the equally lightweight transformer-based decoder. In the decoder, we utilize the novel cross-hierarchical-attention module that refines the image features from the depth information. Our approach improves the quality and reduces memory usage of the depth map prediction, as validated in both KITTI, NYUv2, and VOID datasets.
Open AccessCHADET: Cross-Hierarchical-Attention for Depth-Completion Using Unsupervised Lightweight Transformer
Depth information which specifies the distance between objects and current position of the robot is essential for many robot tasks such as navigation. Recently, researchers have proposed depth completion frameworks to provide dense depth maps that offer comprehensive information about the surrounding environment. However, existing methods show significant trade-offs between computational efficiency and accuracy during inference. The substantial memory and computational requirements make them unsuitable for real-time applications, highlighting the need to improve the completeness and accuracy of depth information while improving processing speed to enhance robot performance in various tasks. To address these challenges, in this paper, we propose CHADET(cross-hierarchical-attention depth-completion transformer), a lightweight depth-completion network that can generate accurate dense depth maps from RGB images and sparse depth points. For each pair, its feature is extracted from the depthwise blocks and passed to the equally lightweight transformer-based decoder. In the decoder, we utilize the novel cross-hierarchical-attention module that refines the image features from the depth information. Our approach improves the quality and reduces memory usage of the depth map prediction, as validated in both KITTI, NYUv2, and VOID datasets.
- 22 November 2024
- Published by Springer Nature
- p. 251-257
Inertial-Joint Learning-Aided Robust Pose Estimation for Legged Robots
- 22 November 2024
- Published by Springer Nature
- p. 251-257
Inertial-Joint Learning-Aided Robust Pose Estimation for Legged Robots
- Open Access
eCDT: Event Clustering for Simultaneous Feature Detection and Tracking-
Contrary to other standard cameras, event cameras interpret the world in an entirely different manner; as a collection of asynchronous events. Despite event camera's unique data output, many event feature detection and tracking algorithms have shown significant progress by making detours to frame-based data representations. This paper questions the need to do so and proposes a novel event data-friendly method that achieve simultaneous feature detection and tracking, called event Clustering-based Detection and Tracking (eCDT). Our method employs a novel clustering method, named as k-NN Classifier-based Spatial Clustering and Applications with Noise (KCSCAN), to cluster adjacent polarity events to retrieve event trajectories.With the aid of a Head and Tail Descriptor Matching process, event clusters that reappear in a different polarity are continually tracked, elongating the feature tracks. Thanks to our clustering approach in spatio-temporal space, our method automatically solves feature detection and feature tracking simultaneously. Also, eCDT can extract feature tracks at any frequency with an adjustable time window, which does not corrupt the high temporal resolution of the original event data. Our method achieves 30% better feature tracking ages compared with the state-of-the-art approach while also having a low error approximately equal to it.
Open AccesseCDT: Event Clustering for Simultaneous Feature Detection and Tracking-
Contrary to other standard cameras, event cameras interpret the world in an entirely different manner; as a collection of asynchronous events. Despite event camera's unique data output, many event feature detection and tracking algorithms have shown significant progress by making detours to frame-based data representations. This paper questions the need to do so and proposes a novel event data-friendly method that achieve simultaneous feature detection and tracking, called event Clustering-based Detection and Tracking (eCDT). Our method employs a novel clustering method, named as k-NN Classifier-based Spatial Clustering and Applications with Noise (KCSCAN), to cluster adjacent polarity events to retrieve event trajectories.With the aid of a Head and Tail Descriptor Matching process, event clusters that reappear in a different polarity are continually tracked, elongating the feature tracks. Thanks to our clustering approach in spatio-temporal space, our method automatically solves feature detection and feature tracking simultaneously. Also, eCDT can extract feature tracks at any frequency with an adjustable time window, which does not corrupt the high temporal resolution of the original event data. Our method achieves 30% better feature tracking ages compared with the state-of-the-art approach while also having a low error approximately equal to it.
- 1 April 2022
- Published by Springer Nature
- p. 284-290
Point and Line Feature-Based VIO for Mobile Devices
- 1 April 2022
- Published by Springer Nature
- p. 284-290
Point and Line Feature-Based VIO for Mobile Devices
- 14 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 4456-4463
STEP: State Estimator for Legged Robots Using a Preintegrated Foot Velocity Factor
Wepropose a novel state estimator for legged robots, STEP, achieved through a novel preintegrated foot velocity factor. In the preintegrated foot velocity factor, the usual non-slip assumption is not adopted. Instead, the end effector velocity becomes observable by exploiting the body speed obtained from a stereo camera. In other words, the preintegrated end effector’s pose can be estimated. Another advantage of our approach is that it eliminates the necessity for a contact detection step, unlike the typical approaches. The proposed method has also been validated in harsh-environment simulations and real-world experiments containing uneven or slippery terrains.
- 14 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 4456-4463
STEP: State Estimator for Legged Robots Using a Preintegrated Foot Velocity Factor
Wepropose a novel state estimator for legged robots, STEP, achieved through a novel preintegrated foot velocity factor. In the preintegrated foot velocity factor, the usual non-slip assumption is not adopted. Instead, the end effector velocity becomes observable by exploiting the body speed obtained from a stereo camera. In other words, the preintegrated end effector’s pose can be estimated. Another advantage of our approach is that it eliminates the necessity for a contact detection step, unlike the typical approaches. The proposed method has also been validated in harsh-environment simulations and real-world experiments containing uneven or slippery terrains.
- 5 August 2021
- Published by Springer Nature
- p. 171-184
ALVIO: Adaptive Line and Point Feature-Based Visual Inertial Odometry for Robust Localization in Indoor Environments
- 5 August 2021
- Published by Springer Nature
- p. 171-184
ALVIO: Adaptive Line and Point Feature-Based Visual Inertial Odometry for Robust Localization in Indoor Environments
- 13 April 2019
- Published by Springer Nature
- p. 199-206
Spike Encoding Modules Using Neuron Model in Neural Networks
- 13 April 2019
- Published by Springer Nature
- p. 199-206
Spike Encoding Modules Using Neuron Model in Neural Networks