Timothy Chen

Mr. Timothy Chen

National Taiwan University, Taipei, Taiwan
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
23 May 2023 in IEEE Access
Verified
Journal Article
Open access
Peng-Yuan KaoPeng-Yuan Kao
Peng-Yuan Kao
HCHsiu-Jui Chang
Hsiu-Jui Chang
KTKuan-Wei Tseng
Kuan-Wei Tseng
TCTimothy Chen
Timothy Chen
HLHe-Lin Luo
He-Lin Luo
YHYi-Ping Hung
Yi-Ping Hung
Camera, inertial measurement unit (IMU), and ultra-wideband (UWB) sensors are commonplace solutions to unmanned aerial vehicle (UAV) localization problems. The performance of a localization system can be improved by integrating observations from different sensors. In this paper, we propose a learning-based UAV localization method using the fusion of vision, IMU, and UWB sensors. Our model consists of visual–inertial (VI) and UWB branches. We combine the estimation results of both branches to predict global poses. To evaluate our method, we augment a public VI dataset with UWB simulations and conduct a real-world experiment. The experimental results show that our method provides more robust and accurate results than VI/UWB-only localization.

15 September 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Peng-Yuan KaoPeng-Yuan Kao
Peng-Yuan Kao
RZRong-Rong Zhang
Rong-Rong Zhang
TCTimothy Chen
Timothy Chen
YHYi-Ping Hung
Yi-Ping Hung
Absolute pose regression (APR) for camera localization is a single-shot approach that encodes the information of a 3D scene in an end-to-end neural network. The camera pose result of APR methods can be observed as the linear combination of the base poses. Previous APR methods’ base poses are learned from training data. However, the training data can limit the performance of the methods, which cannot be generalized to cover the entire scene. To solve this issue, we use handcrafted base poses instead of learning-based base poses, which prevents overfitting the camera poses of the training data. Moreover, we use a dual-stream network architecture to process color and depth images separately to get more accurate localization. On the 7 Scenes dataset, the proposed method is among the best in median rotation error, and in median translation error, it outperforms previous APR methods. On a more difficult dataset—Oxford RobotCar dataset, the proposed method achieves notable improvements in median translation and rotation errors compared to the state-of-the-art APR methods.

23 July 2023
Verified
Conference Paper
Open access
TCTimothy Chen
Timothy Chen
MTMiguel Ying Jie Then
Miguel Ying Jie Then
JHJing-Yuan Huang
Jing-Yuan Huang
YCYang-Sheng Chen
Yang-Sheng Chen
PHPing-Hsuan Han
Ping-Hsuan Han
YHYi-Ping Hung
Yi-Ping Hung

20 September 2025
Verified
Conference Paper
Closed access
HSHung-Ming Sung
Hung-Ming Sung
TCTimothy Chen
Timothy Chen
JLJin-Yao Lin
Jin-Yao Lin
YHYi-Ping Hung
Yi-Ping Hung
Voting, an important process of modern democracy, is naturally subject to coercion and corruption. With the rise of blockchain technology, conducting such campaign on blockchain has drawn attention with its potential to provide a secure, transparent and decentralized voting system. However, with the nature of blockchain being a public ledger, concerns about the privacy arise. In this work, we present a receipt free voting protocol utilizing blockchain as public tally. By separating operating authority into identity authority which is responsible for verifying the voter's identity and voting authority which is responsible for generating encrypted ballots and tallying, we ensure that the privacy of voters is protected while allowing any third party to verify the integrity of the vote and the tally. The protocol makes use of homomorphic encryption for the tally state and blind signature for ballot verification. The protocol achieves receiptfreeness assuming that both authorities are honest.