Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling
The method of physically recording acoustic holograms is time-consuming and inefficient, hindering the ability to reconstruct acoustic holograms rapidly. This text aims to propose a deep learning strategy based on an improved IU-Net to rapidly reconstruct acoustic holograms with phase information. T...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10752505/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533440258736128 |
|---|---|
| author | Mingzhe Cui Yang Li Xuewei Wang Jia Wang Haoxuan Rong |
| author_facet | Mingzhe Cui Yang Li Xuewei Wang Jia Wang Haoxuan Rong |
| author_sort | Mingzhe Cui |
| collection | DOAJ |
| description | The method of physically recording acoustic holograms is time-consuming and inefficient, hindering the ability to reconstruct acoustic holograms rapidly. This text aims to propose a deep learning strategy based on an improved IU-Net to rapidly reconstruct acoustic holograms with phase information. The angular spectrum method is used to simulate the phase information distribution of different sound sources, positions, and initial angles, thereby quickly generating the required data samples, especially for complex or dynamic image scenarios. The framework employs a custom learning rate adjustment mechanism to dynamically adjust the learning rate in real-time, adapt to the training process, and support a stepwise learning strategy. Experimental results show that the proposed method achieves an accuracy of 90.9% in acoustic hologram reconstruction, with a Dice coefficient of 0.928, improving reconstruction speed by over 30% compared to traditional methods, ensuring high-quality and rapid reconstruction of acoustic holograms. |
| format | Article |
| id | doaj-art-cbffd00c6e0347d19e0ec4cd26c631fa |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-cbffd00c6e0347d19e0ec4cd26c631fa2025-01-16T00:01:36ZengIEEEIEEE Access2169-35362024-01-011217819917820810.1109/ACCESS.2024.349692310752505Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate SchedulingMingzhe Cui0https://orcid.org/0009-0009-6254-9545Yang Li1https://orcid.org/0009-0002-6360-6520Xuewei Wang2https://orcid.org/0009-0002-1022-1141Jia Wang3Haoxuan Rong4School of Information Engineering, Beijing Institute of Graphic Communication, Beijing, ChinaSchool of Information Engineering, Beijing Institute of Graphic Communication, Beijing, ChinaSchool of Information Engineering, Beijing Institute of Graphic Communication, Beijing, ChinaSchool of Information Engineering, Beijing Institute of Graphic Communication, Beijing, ChinaSchool of Information Engineering, Beijing Institute of Graphic Communication, Beijing, ChinaThe method of physically recording acoustic holograms is time-consuming and inefficient, hindering the ability to reconstruct acoustic holograms rapidly. This text aims to propose a deep learning strategy based on an improved IU-Net to rapidly reconstruct acoustic holograms with phase information. The angular spectrum method is used to simulate the phase information distribution of different sound sources, positions, and initial angles, thereby quickly generating the required data samples, especially for complex or dynamic image scenarios. The framework employs a custom learning rate adjustment mechanism to dynamically adjust the learning rate in real-time, adapt to the training process, and support a stepwise learning strategy. Experimental results show that the proposed method achieves an accuracy of 90.9% in acoustic hologram reconstruction, with a Dice coefficient of 0.928, improving reconstruction speed by over 30% compared to traditional methods, ensuring high-quality and rapid reconstruction of acoustic holograms.https://ieeexplore.ieee.org/document/10752505/Acoustic hologramdeep learningacoustic field reconstructionwave propagationlearning rate scheduler |
| spellingShingle | Mingzhe Cui Yang Li Xuewei Wang Jia Wang Haoxuan Rong Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling IEEE Access Acoustic hologram deep learning acoustic field reconstruction wave propagation learning rate scheduler |
| title | Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling |
| title_full | Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling |
| title_fullStr | Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling |
| title_full_unstemmed | Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling |
| title_short | Rapid Reconstruction of Acoustic Holograms Using Improved IU-Net With Adaptive Learning Rate Scheduling |
| title_sort | rapid reconstruction of acoustic holograms using improved iu net with adaptive learning rate scheduling |
| topic | Acoustic hologram deep learning acoustic field reconstruction wave propagation learning rate scheduler |
| url | https://ieeexplore.ieee.org/document/10752505/ |
| work_keys_str_mv | AT mingzhecui rapidreconstructionofacoustichologramsusingimprovediunetwithadaptivelearningratescheduling AT yangli rapidreconstructionofacoustichologramsusingimprovediunetwithadaptivelearningratescheduling AT xueweiwang rapidreconstructionofacoustichologramsusingimprovediunetwithadaptivelearningratescheduling AT jiawang rapidreconstructionofacoustichologramsusingimprovediunetwithadaptivelearningratescheduling AT haoxuanrong rapidreconstructionofacoustichologramsusingimprovediunetwithadaptivelearningratescheduling |