Luke Bidulka

Luke Bidulka

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
23 September 2024 in Neurocomputing
Verified
Journal Article
Closed access
LBLuke Bidulka
Luke Bidulka
MGMohsen Gholami
Mohsen Gholami
JZJiannan Zheng
Jiannan Zheng
MMMartin J. McKeown
Martin J. McKeown
ZWZ. Jane Wang
Z. Jane Wang

31 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
TYTianze Yu
Tianze Yu
LBLuke Bidulka
Luke Bidulka
MMMartin James McKeown
Martin James McKeown
ZWZ. Jane Wang
Z. Jane Wang
This paper tackles a novel and challenging problem—3D hand pose estimation (HPE) from a single RGB image using partial annotation. Most HPE methods ignore the fact that the keypoints could be partially visible (e.g., under occlusions). In contrast, we propose a deep-learning framework, PA-Tran, that jointly estimates the keypoints status and 3D hand pose from a single RGB image with two dependent branches. The regression branch consists of a Transformer encoder which is trained to predict a set of target keypoints, given an input set of status, position, and visual features embedding from a convolutional neural network (CNN); the classification branch adopts a CNN for estimating the keypoints status. One key idea of PA-Tran is a selective mask training (SMT) objective that uses a binary encoding scheme to represent the status of the keypoints as observed or unobserved during training. In addition, by explicitly encoding the label status (observed/unobserved), the proposed PA-Tran can efficiently handle the condition when only partial annotation is available. Investigating the annotation percentage ranging from 50–100%, we show that training with partial annotation is more efficient (e.g., achieving the best 6.0 PA-MPJPE when using about 85% annotations). Moreover, we provide two new datasets. APDM-Hand, is for synthetic hands with APDM sensor accessories, which is designed for a specific hand task. PD-APDM-Hand, is a real hand dataset collected from Parkinson’s Disease (PD) patients with partial annotation. The proposed PA-Tran can achieve higher estimation accuracy when evaluated on both proposed datasets and a more general hand dataset.

4 September 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JGJiaxun Gao
Jiaxun Gao
LBLuke Bidulka
Luke Bidulka
MMMartin James McKeown
Martin James McKeown
ZWZ. Jane Wang
Z. Jane Wang
Eye-tracking, as an accessible, non-invasive technology, offers valuable insights into the human motor and cognitive functions, and it is an essential tool in studying neurodegenerative diseases such as Parkinson’s disease (PD). While current eye movement assessment for PD diagnosis mainly relies on high-end, specialized eye-tracker equipment, this work demonstrates that advanced deep learning methods using RGB-video from regular cameras (with 60 fps sampling rate, 1920 × 1080 image resolution) can provide promising performance on PD eye movement assessment. Our contributions are twofold: First, we show the potential and feasibility of using readily accessible, regular RGB camera data for PD eye movement assessment, making it more attractive for wide applicability in practice. Second, we propose a novel PD classification model by exploring temporal eye movement patterns from regular RGB-video data, and it can achieve performance comparable to or even better than current standard methods reliant on commercial, specialized eye-tracking equipment. The results highlight the promise of regular RGB-video-based PD assessment and the potential for more accessible diagnostic tools in PD studies.