Ji-won Choi

Mr. Ji-won Choi

New Jersey Institute of Technology, Newark, California, USA
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 April 2022 in Sensors
Verified
Journal Article
Open access
PDF file
CICraig Iaboni
Craig Iaboni
DLDeepan Lobo
Deepan Lobo
JCJi-won Choi
Ji-won Choi
PAPramod Abichandani
Pramod Abichandani
Motion capture systems are crucial in developing multi-quadrotor systems due to their ability to provide fast and accurate ground truth measurements for tracking and control. This paper presents the implementation details and experimental validation of a relatively low-cost motion-capture system for multi-quadrotor motion planning using an event camera. The real-time, multi-quadrotor detection and tracking tasks are performed using a deep learning network You-Only-Look-Once (YOLOv5) and a k-dimensional (k-d) tree, respectively. An optimization-based decentralized motion planning algorithm is implemented to demonstrate the effectiveness of this motion capture system. Extensive experimental evaluations were performed to (1) compare the performance of four deep-learning algorithms for high-speed multi-quadrotor detection on event-based data, (2) study precision, recall, and F1 scores as functions of lighting conditions and camera motion, and (3) investigate the scalability of this system as a function of the number of quadrotors flying in the arena. Comparative analysis of the deep learning algorithms on a consumer-grade GPU demonstrates a 4.8× to 12× sampling/inference rate advantage that YOLOv5 provides over representative one- and two-stage detectors and a 1.14× advantage over YOLOv4. In terms of precision and recall, YOLOv5 performed 15% to 18% and 27% to 41% better than representative state-of-the-art deep learning networks. Graceful detection and tracking performance degradation was observed in the face of progressively darker ambient light conditions. Despite severe camera motion, YOLOv5 precision and recall values of 94% and 98% were achieved, respectively. Finally, experiments involving up to six indoor quadrotors demonstrated the scalability of this approach. This paper also presents the first open-source event camera dataset in the literature, featuring over 10,000 fully annotated images of multiple quadrotors operating in indoor and outdoor environments.

17 December 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Ludvik AlkhouryLudvik Alkhoury
Ludvik Alkhoury
JCJi-won Choi
Ji-won Choi
VCVishnu D. Chandran
Vishnu D. Chandran
GCGabriela B. De Carvalho
Gabriela B. De Carvalho
SPSaikat Pal
Saikat Pal
MKMoshe Kam
Moshe Kam
The quality of heart rate (HR) measurements extracted from human photoplethysmography (PPG) signals are known to deteriorate under appreciable human motion. Auxiliary signals, such as accelerometer readings, are usually employed to detect and suppress motion artifacts. A 2019 study by Yifan Zhang and his coinvestigatorsused the noise components extracted from an infrared PPG signal to denoise a green PPG signal from which HR was extracted. Until now, this approach was only tested on “micro-motion” such as finger tapping. In this study, we extend this technique to allow accurate calculation of HR under high-intensity full-body repetitive “macro-motion”. Our Dual Wavelength (DWL) framework was tested on PPG data collected from 14 human participants while running on a treadmill. The DWL method showed the following attributes: (1) it performed well under high-intensity full-body repetitive “macro-motion”, exhibiting high accuracy in the presence of motion artifacts (as compared to the leading accelerometer-dependent HR calculation techniques TROIKA and JOSS); (2) it used only PPG signals; auxiliary signals such as accelerometer signals were not needed; and (3) it was computationally efficient, hence implementable in wearable devices. DWL yielded a Mean Absolute Error (MAE) of 1.22|0.57 BPM, Mean Absolute Error Percentage (MAEP) of 0.95|0.38%, and performance index (PI) (which is the frequency, in percent, of obtaining an HR estimate that is within ±5 BPM of the HR ground truth) of 95.88|4.9%. Moreover, DWL yielded a short computation period of 3.0|0.3 s to process a 360-second-long run.

6 June 2022 in Computer
Verified
Journal Article
Closed access
CICraig Iaboni
Craig Iaboni
HPHimanshu Patel
Himanshu Patel
DLDeepan Lobo
Deepan Lobo
JCJi-won Choi
Ji-won Choi
PAPramod Abichandani
Pramod Abichandani
This tutorial introduces readers to the use of event cameras with frame-based computer vision algorithms. By the end of the article, readers will be proficient in applying off-the-shelf clustering and tracking algorithms to event camera data.

7 March 2022 in Research Square
Verified
Preprint
Open access
PDF file
JCJi-won Choi
Ji-won Choi
LALudvik Alkhoury
Ludvik Alkhoury
LULeonardo F. Urbano
Leonardo F. Urbano
PMPuneet Masson
Puneet Masson
MKMoshe Kam
Moshe Kam
MVMatthew VerMilyea
Matthew VerMilyea
Background: Computer-Assisted Semen Analysis (CASA) enables reliable analysis of semen images, and is designed to process large number of images with high consistency, accuracy, and repeatability. Design and testing of CASA algorithms can be accelerated greatly if reliable simulations of semen images under a variety of conditions and sample quality modes are available. Using lifelike simulation of semen images can quantify the performance of existing and proposed CASA algorithms, since the parameters of the simulated image are known and controllable. Methods: We present simulation models for sperm cell image and swimming modes observed in real 2D (top-down) images of sperm cells in laboratory specimen. The models simulate human sperm using four (4) types of swimming, namely linear mean, circular, hyperactive, and immotile (or dead). Results: The simulation models are used in studying algorithms for segmentation, localization, and tracking of sperm cells. Several segmentation and localization algorithms were tested under varying levels of noise, and then compared using precision, recall, and the optimal subpattern assignment (OSPA) metric. Images of real human semen sample were used to validate the segmentation and localization observations obtained from simulations. An example is given of sperm cell tracking on simulated semen images of cells using the different tracking algorithms (nearest neighbor (NN), global nearest neighbor (GNN), probabilistic data association filter (PDAF), and joint probabilistic data association filter (JPDAF)). Tracking performance was evaluated through multi-object tracking precision (MOTP) and multi-object tracking accuracy (MOTA). Conclusion: Simulation models enable objective assessments of semen image processing algorithms. We demonstrate the use of a new simulation tool to assess and compare segmentation, localization, and tracking methods. The simulation software allows testing along a large spectrum of parameter values that control the appearance and behavior of simulated semen images. Users can generate scenarios of different characteristics and assess the effectiveness of different CASA algorithms in these environments. The simulation was used to assess and compare algorithms for segmentation and tracking of sperm cells in semen images.