Yu-Shiuan Tsai

Dr. Yu-Shiuan Tsai

National Taiwan Ocean University, Keelung, Taiwan
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
10 August 2020 in Mathematics
Verified
Journal Article
Open access
PDF file
YTYu-Shiuan Tsai
Yu-Shiuan Tsai
LHLi-Heng Hsu
Li-Heng Hsu
YHYi-Zeng Hsieh
Yi-Zeng Hsieh
SLShih-Syun Lin
Shih-Syun Lin
In recent years, the breakthrough of neural networks and the rise of deep learning have led to the advancement of machine vision, which has been commonly used in the practical application of image recognition. Automobiles, drones, portable devices, behavior recognition, indoor positioning and many other industries also rely on the integrated application, and require the support of deep learning and machine vision. As for these technologies, there is a high demand for the accuracy related to the recognition of portraits or objects. The recognition of human figures is also a research goal that has drawn great attention in various fields. However, the portrait will be affected by various factors such as height, weight, posture, angle and whether it is covered or not, which affects the accuracy of recognition. This paper applies the application of deep learning to portraits with different poses and angles, especially the actual distance of a single lens for the shadowed portrait (depth estimation), so that it can be used for automatic control of drones in the future. Traditional methods for calculating depth using images are mainly divided into three types: one—single-lens estimation, two—lens estimation, and three—optical band estimation. In view of the fact that both the second and third categories require relatively large and expensive equipment to effectively perform distance calculations, numerous methods for calculating distance using a single lens have recently been produced. However, whether it is the use of traditional “units of distance measurement calibration”, “defocus distance measurement”, or the “three-dimensional grid space messages distance measurement method”, all of these face corresponding difficulties and problems. Additionally, they have to deal with outside disturbances and process the shadowed image. Therefore, under the new research method, OpenPose, which is proposed by Carnegie Mellon University, this paper intends to propose a depth algorithm for a single-lens occluded portrait to estimate the actual portrait distance for different poses, angles of view and obscuration.

27 April 2025 in The Journal of Supercomputing
Verified
Journal Article
Open access
PDF file
YTYu-Shiuan Tsai
Yu-Shiuan Tsai
CTChia-Tung Tsai
Chia-Tung Tsai
JHJian-Hong Huang
Jian-Hong Huang
Underwater imaging faces challenges such as light attenuation, scattering, and water turbidity, which degrade image quality and hinder accurate organism recognition. The detecting underwater objects dataset, with resolutions from 586 × 482 to 3840 × 2160 pixels, highlights significant object scale variation, including a high proportion of small objects (27.38%). This study introduces the underwater attention-parallel residual bi-fusion feature pyramid network model, which improves detection accuracy for small- and medium-sized objects in complex underwater environments. The proposed model incorporates a spatial pyramid pooling module with attention mechanisms to enhance multi-scale feature representation and integrates the normalized Wasserstein distance into the loss function for better detection flexibility. Experimental results demonstrate that the model outperforms state-of-the-art methods, achieving a mean average precision at intersection over union threshold of 0.5 of 88.8% and a mean average precision at intersection over union threshold range of 0.5–0.95 of 68.3%, representing a 2.5–9% improvement over baseline models. Furthermore, the model achieved a precision of 85.5%, recall of 82.9%, and an F1-score of 0.8417. These results highlight the model’s robustness and effectiveness, offering significant contributions to underwater biodiversity studies, environmental assessments, and marine ecosystem management. By addressing scale variability and achieving high accuracy even for rare species such as scallops, the proposed model supports practical applications in underwater monitoring and conservation.

1 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
YTYu-Shiuan Tsai
Yu-Shiuan Tsai
AMAlvin V. Modales
Alvin V. Modales
HLHung-Ta Lin
Hung-Ta Lin
Distance and depth detection plays a crucial role in intelligent robotics. It enables drones to understand their working environment to avoid collisions and accidents immediately and is very important in various AI applications. Image-based distance detection usually relies on the correctness of geometric information. However, the geometric features will be lost when the object is rotated or the camera lens image is distorted. This study proposes a training model based on a convolutional neural network, which uses a single-lens camera to estimate humans’ distance in continuous images. We can partially restore depth information loss using built-in camera parameters that do not require additional correction. The normalized skeleton feature unit vector has the same characteristics as time series data and can be classified very well using a 1D convolutional neural network. According to our results, the accuracy for the occluded leg image is over 90% at 2 to 3 m, 80% to 90% at 4 m, and 70% at 5 to 6 m.

20 September 2021 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
YPYing-Hung Pu
Ying-Hung Pu
PCPo-Sheng Chiu
Po-Sheng Chiu
YTYu-Shiuan Tsai
Yu-Shiuan Tsai
MLMeng-Tsung Liu
Meng-Tsung Liu
YHYi-Zeng Hsieh
Yi-Zeng Hsieh
SLShih-Syun Lin
Shih-Syun Lin

10 August 2005
Verified
Conference Paper
Closed access
THT.S. Horng
T.S. Horng
JJJ.K. Jau
J.K. Jau
YTYu-Shiuan Tsai
Yu-Shiuan Tsai
CHC.S. Huang
C.S. Huang
This paper presents a state-of-the-art technique for broadband modeling of on-chip passive components. The proposed decomposition and reconstruction methodology can efficiently and accurately establish the broadband SPICE model for an arbitrary multi-port reciprocal component over an extremely large bandwidth. The idea is to decompose a multi-port network into a number of one-port networks which can be lumped modeled simply and easily. Then a reconstruction process, based on the modified T-equivalent circuit topology, is invented to combine these one-port lumped models into a broadband multi-port model. In this modeling study, the S parameters for a series of passive components including spiral inductors, MIM capacitors, bifilar transformers and baluns, fabricated using a 0.18 /spl mu/m RF-CMOS foundry process, have been measured up to 20 GHz. The modeled S parameters agree quite satisfactorily with the measured results over the entire measurement frequency range.

7 August 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YTYu-Shiuan Tsai
Yu-Shiuan Tsai
SCSi-Jie Chen
Si-Jie Chen
In terms of gait recognition, face recognition is currently the most commonly used technology with high accuracy. However, in an image, there is not necessarily a face. Therefore, face recognition cannot be used if there is no face at all. However, when we cannot obtain facial information, we still want to know the person’s identity. Thus, we must use information other than facial features to identify the person. Since each person’s behavior will be somewhat different, we hope to learn the difference between one specific human body and others and use this behavior to identify the human body because deep learning technology advances this idea. Therefore, we used OpenPose along with LSTM for personal identification. We found that using people’s walking posture is feasible for identifying their identities. Presently, the environment for making judgments is limited, in terms of height, and there will be restrictions on distance. In the future, using various angles and distances will be explored. This method can also solve the problem of half-body identification and is also helpful for finding people.