Paul K. J. Park

Prof. Dr. Paul K. J. Park

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 July 2013 in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Verified
Conference Paper
Closed access
PPPaul K. J. Park
Paul K. J. Park
HRHyunsurk Ryu
Hyunsurk Ryu
JLJun Haeng Lee
Jun Haeng Lee
CSChang-Woo Shin
Chang-Woo Shin
KLKyoo Bin Lee
Kyoo Bin Lee
TDTobi Delbruck
Tobi Delbruck
We report on the neuromorphic sound localization circuit which can enhance the perceptual sensation in a hearing aid system. All elements are simple leaky integrate-and-fire neuron circuits with different parameters optimized to suppress the impacts of synaptic circuit noises. The detection range and resolution of the proposed neuromorphic circuit are 500 us and 5 us, respectively. Our results show that, the proposed technique can localize a sound pulse with extremely narrow duration (~ 1 ms) resulting in real-time response.

1 February 2026 in Sensors
Verified
Journal Article
Open access
PDF file
PPPaul K. J. Park
Paul K. J. Park
JKJunseok Kim
Junseok Kim
JKJuhyun Ko
Juhyun Ko
Yeoungjin ChangYeoungjin Chang
Yeoungjin Chang
Event-based sensors provide sparse, motion-centric measurements that can reduce data bandwidth and enable always-on perception on resource-constrained edge devices. This paper presents an event-based machine vision framework for smart-home AIoT that couples a Dynamic Vision Sensor (DVS) with compute-efficient algorithms for (i) human/object detection, (ii) 2D human pose estimation, (iii) hand posture recognition for human–machine interfaces. The main methodological contributions are timestamp-based, polarity-agnostic recency encoding that preserves moving-edge structure while suppressing static background, and task-specific network optimizations (architectural reduction and mixed-bit quantization) tailored to sparse event images. With a fixed downstream network, the recency encoding improves action recognition accuracy over temporal accumulation (0.908 vs. 0.896). In a 24 h indoor monitoring experiment (640 × 480), the raw DVS stream is about 30× smaller than conventional CMOS video and remains about 5× smaller after standard compression. For human detection, the optimized event processing reduces computation from 5.8 G to 81 M FLOPs and runtime from 172 ms to 15 ms (more than 11× speed-up). For pose estimation, a pruned HRNet reduces model size from 127 MB to 19 MB and inference time from 70 ms to 6 ms on an NVIDIA Titan X while maintaining a comparable accuracy (mAP from 0.95 to 0.94) on MS COCO 2017 using synthetic event streams generated by an event simulator. For hand posture recognition, a compact CNN achieves 99.19% recall and 0.0926% FAR with 14.31 ms latency on a single i5-4590 CPU core using 10-frame sequence voting. These results indicate that event-based sensing combined with lightweight inference is a practical approach to privacy-friendly, real-time perception under strict edge constraints.

9 December 2025 in Sensors
Verified
Journal Article
Open access
PDF file
PPPaul K. J. Park
Paul K. J. Park
JKJunseok Kim
Junseok Kim
JKJuhyun Ko
Juhyun Ko
We propose and demonstrate a novel motion blur-free hybrid image sensing technique. Unlike the previous hybrid image sensors, we developed a homogeneous hybrid image sensing technique including 60 fps CMOS Image Sensor (CIS) and 1440 fps pseudo Dynamic Vision Sensor (DVS) image frames without any performance degradation caused by static bad pixels. To achieve the fast readout, we implemented two one-side ADCs on two photodiodes (PDs) and the pixel output settling time can be reduced significantly by using the column switch control. The high-speed pseudo DVS frame can be obtained by differentiating fast-readout CIS frames, by which, in turn, the world’s smallest pseudo DVS pixel (1.8 μm) can be achieved. In addition, we confirmed that CIS (50 Mp resolution) and DVS (0.78 Mp resolution) data obtained from the hybrid image sensor can be transmitted over the MIPI (4.5 Gb/s four-lane D-PHY) interface without signal loss. The results showed that the motion blur of a 60 fps CIS frame image can be compensated dramatically by using the proposed pseudo DVS frames together with a deblur algorithm. Finally, using the event simulation, we verified that a 1440 fps pseudo DVS frame can compensate the motion blur of the CIS image captured in the situation of jogging at a 3 m distance.

27 June 2026 in Electronics
Verified
Journal Article
Open access
PDF file
PPPaul K. J. Park
Paul K. J. Park
JKJunseok Kim
Junseok Kim
JKJuhyun Ko
Juhyun Ko
Yeoungjin ChangYeoungjin Chang
Yeoungjin Chang
Low-latency visual perception is essential for interactive machine vision on edge AI devices, but conventional frame-based image sensors impose frame period delays and generate dense image data that increase memory bandwidth and processing latency. Although Dynamic Vision Sensors (DVSs) are known to provide low latency, sparse output, and high dynamic range, these sensor-level properties do not automatically translate into practical application-level latency reduction on resource-constrained edge platforms. This paper presents a latency-driven sensing algorithm co-design approach for DVS-based low-latency machine vision. The main objective is to connect DVS sensor-level characteristics, event representations, task-dependent processing flows, and measured response times on mobile application processors. We first analyze latency requirements for three representative edge AI applications (i.e., person detection, gesture recognition, and Simultaneous Localization and Mapping (SLAM)), which correspond to different latency regimes and processing structures. We then describe the DVS operating principle, pixel-level event latency, and readout latency, showing how asynchronous event generation reduces sensing delay and suppresses redundant static background information before algorithmic processing. In contrast to prior event camera studies that mainly optimize a single task or a specific event representation, this work evaluates three task-specific event processing systems on mobile processors. Person detection achieves 92 ms processing latency on Exynos 7570, gesture recognition based on event-driven 4-DoF motion estimation achieves 20 ms latency on Exynos 5422, and SLAM achieves 15.9 ms latency on Snapdragon 845. These results satisfy the practical latency targets of the corresponding applications and demonstrate that DVS-based sensing can provide not only sensor-level speed advantages but also system-level latency benefits for AIoT, mobile, robotics, and AR/VR machine vision systems.

23 January 2026 in Sensors
Verified
Journal Article
Open access
PDF file
PPPaul K. J. Park
Paul K. J. Park
JKJunseok Kim
Junseok Kim
JKJuhyun Ko
Juhyun Ko
Yeoungjin ChangYeoungjin Chang
Yeoungjin Chang
We report on the post-capture, on-demand deblurring technique based on a Dynamic Vision Sensor (DVS). Motion blur causes photographic defects inherently in most use cases of mobile cameras. To compensate for motion blur in mobile photography, we use a fast event-based vision sensor. However, in this paper, we found severe artifacts resulting in image quality degradation caused by color ghosts, event noises, and discrepancies between conventional image sensors and event-based sensors. To overcome these inevitable artifacts, we propose and demonstrate event-based compensation techniques such as cross-correlation optimization, contrast maximization, resolution mismatch compensation (event upsampling for alignment), and disparity matching. The results show that the deblur performance can be improved dramatically in terms of metrics such as the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Spatial Frequency Response (SFR). Thus, we expect that the proposed event-based image restoration technique can be widely deployed in mobile cameras.

19 January 2026 in Electronics Letters
Verified
Journal Article
Open access
PPPaul K. J. Park
Paul K. J. Park
This paper proposes a quantisation‐driven data‐compression framework for machine vision sensors by combining nonlinear quantisation and bit‐shift masking. The proposed approach compresses pixel data to an effective 1–4 bits per pixel while preserving edge‐salient information required for object detection and feature tracking. Experimental results show that the compressed/quantised images maintain detection and tracking performance without degradation, indicating the proposed framework can reduce sensor‐to‐processor bandwidth and optimise required bit resolution.