A5026576128- Radar Systems and Signal Processing
- Photoacoustic and Ultrasonic Imaging
- Ultrasound Imaging and Elastography
- Electromagnetic Compatibility and Measurements
- Advanced SAR Imaging Techniques
- Ultrasonics and Acoustic Wave Propagation
- Antenna Design and Analysis
- Ultrasound and Hyperthermia Applications
- Flow Measurement and Analysis
- Robotics and Sensor-Based Localization
- Microwave Imaging and Scattering Analysis
- Remote Sensing and LiDAR Applications
- Electrical and Bioimpedance Tomography
- 3D Surveying and Cultural Heritage
NXP (Netherlands)
2024
Technical University of Denmark
2019-2021
Korea University
2015
Delay-and-sum (DAS) beamforming is unable to identify individual scatterers when their density so high that point spread functions overlap. This paper proposes a convolutional neural network (CNN)-based method detect and localize high-density scatterers, some of which are closer than the resolution limit delay-andsum beamforming. A CNN was designed take radio frequency channel data return non-overlapping Gaussian confidence maps. The scatterer positions were estimated from maps by...
In this paper, a realtime pseudo-structure extraction algorithm for 3D indoor point cloud data (PCD) is proposed. This called Convex Cut (CC) because of its two main steps: cutting the PCD with arbitrary planes, and extracting convex parts. CC can be used as preprocessing module other existing algorithms to extract static parts in dynamic environments or represent principal model given PCD. Its calculation time 24 milliseconds 50k on consumer PC, it yields precision value 0.90 recall 0.99...
Ultrasound localization microscopy (ULM) can surpass the resolution limit of conventional ultrasound imaging. However, a trade-off between and data acquisition time is introduced. For microbubble (MB) localization, centroid detection commonly used. Therefore, low-concentrations MBs are required to avoid overlapping point spread functions (PSFs), leading long due limited number detectable in an image frame. Recently, deep learning-based MB methods across high-concentration regimes have been...
Super-resolution imaging (SRI) can achieve sub-wavelength resolution by detecting and tracking intravenously injected microbubbles (MBs) over time. However, current SRI is limited long data acquisition times since the MB detection still relies on diffraction-limited conventional ultrasound images. This limits number of detectable MBs in a fixed time duration. In this work, we propose deep learning-based method for localizing high-density multiple point targets from radio frequency (RF)...
Ultrasound localization microscopy (ULM) can break the diffraction limit of ultrasound imaging. However, a long data acquisition time is often required due to use low concentrations microbubbles (MBs) for high accuracy. Lately, deep learning-based methods that robustly localize have been proposed overcome this constraint. In particular, unfolded ULM has shown promising results with few parameters by using sparsity prior. work, further extended perform beamforming as well MB localization. The...