Kaiyang Ding

ORCID: 0000-0003-1827-0597
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Photoacoustic and Ultrasonic Imaging
  • Advanced Fiber Optic Sensors
  • Robotic Path Planning Algorithms
  • Photonic Crystal and Fiber Optics
  • Maritime Navigation and Safety
  • Random lasers and scattering media
  • Ship Hydrodynamics and Maneuverability
  • Advanced Fiber Laser Technologies
  • Underwater Vehicles and Communication Systems
  • Structural Health Monitoring Techniques
  • Ocean Waves and Remote Sensing
  • Optical Polarization and Ellipsometry
  • Optical measurement and interference techniques
  • Underwater Acoustics Research
  • Image Enhancement Techniques
  • Structural Integrity and Reliability Analysis
  • Optimization and Search Problems
  • Optical Imaging and Spectroscopy Techniques
  • Metamaterials and Metasurfaces Applications

Tsinghua University
2021-2025

Peng Cheng Laboratory
2025

University Town of Shenzhen
2021-2024

Tsinghua–Berkeley Shenzhen Institute
2024

With the development of ocean exploration technology, has become a hot research field involving use autonomous underwater vehicles (AUVs). In complex environments, fast, safe, and smooth arrival target points is key for AUVs to conduct missions. Most path-planning algorithms combine deep reinforcement learning (DRL) achieve obstacle avoidance path shortening. this paper, we propose method improve local minimum in artificial potential (APF) make out by constructing traction force. The...

10.3390/s23156680 article EN cc-by Sensors 2023-07-26

Abstract Snapshot spectral imaging is an emerging technology for fast data acquisition in dynamic environments, capturing high‐volume spatial‐spectral information a single snapshot. However, it suffers from bulky cascading optics and cannot be directly used space‐restricted scenarios such as endoscope‐assisted brain microsurgery real‐time cellular tissue imaging. In this work, ultracompact strategy of parallelized metasurface computed tomography empowered by generative deep learning...

10.1002/adma.202419383 article EN Advanced Materials 2025-04-24

Traditional ship identification systems have difficulty in identifying illegal or broken ships, but the wakes generated by ships can be used as a major feature for identification. However, multi-ship and multi-scale wake detection is also big challenge. This paper combines geometric pixel characteristics of their Synthetic Aperture Radar (SAR) images proposes method detection. first detects highlight area image then generates specific windows around centroid, thereby detecting different...

10.3390/rs14010025 article EN cc-by Remote Sensing 2021-12-22

Dual combs are widely recognized for their significant applications in precision measurement, leveraging advantages of high spectral resolution, large spectrum width, and speed. However, the tight locking dual-comb system faces challenges terms complexity, cost, power consumption, limiting its widespread field applications. This paper introduces an approach to address these by proposing a passively thermal management scheme environment-shared fiber lasers free-running system. The presented...

10.2139/ssrn.4698576 preprint EN 2024-01-01

We present a parallelized metasurfaces approach for ultra-compact computed tomography snapshot spectral light-field imaging in place of conventional bulky or time-sensitive systems with single shot to acquire four-dimensional spatial-spectral and depth data.

10.1364/cleo_at.2024.am4a.6 article EN 2024-01-01

As marine activities expand, deploying underwater autonomous vehicles (AUVs) becomes critical. Efficiently navigating these AUVs through intricate terrains is vital. This paper proposes a sophisticated motion-planning algorithm integrating deep reinforcement learning (DRL) with an improved artificial potential field (IAPF). The incorporates remote sensing information to overcome traditional APF challenges and combines the IAPF traveling salesman problem for optimal path cruising. Through...

10.3390/rs15235607 article EN cc-by Remote Sensing 2023-12-02

Complexities of the underwater environment can seriously affect many detection means, especially influence light scattering by water. To solve this problem, a three-dimensional (3D) morphology measurement method is proposed based on photoacoustic effect. In method, object irradiated with pulsed laser to produce ultrasonic waves via A probe collects signal and subsequent data processing yield complete detection. This approach make full use advantages high precision good directivity ranging...

10.1364/ol.446277 article EN Optics Letters 2021-12-15
Coming Soon ...