SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning
We propose a concurrent single-pixel imaging, object location, and classification scheme based on deep learning (SP-ILC). We used multitask learning, developed a new loss function, and created a dataset suitable for this project. The dataset consists of scenes that contain different numbers of possi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/8/9/400 |
| _version_ | 1797517549689110528 |
|---|---|
| author | Zhe Yang Yu-Ming Bai Li-Da Sun Ke-Xin Huang Jun Liu Dong Ruan Jun-Lin Li |
| author_facet | Zhe Yang Yu-Ming Bai Li-Da Sun Ke-Xin Huang Jun Liu Dong Ruan Jun-Lin Li |
| author_sort | Zhe Yang |
| collection | DOAJ |
| description | We propose a concurrent single-pixel imaging, object location, and classification scheme based on deep learning (SP-ILC). We used multitask learning, developed a new loss function, and created a dataset suitable for this project. The dataset consists of scenes that contain different numbers of possibly overlapping objects of various sizes. The results we obtained show that SP-ILC runs concurrent processes to locate objects in a scene with a high degree of precision in order to produce high quality single-pixel images of the objects, and to accurately classify objects, all with a low sampling rate. SP-ILC has potential for effective use in remote sensing, medical diagnosis and treatment, security, and autonomous vehicle control. |
| first_indexed | 2024-03-10T07:17:08Z |
| format | Article |
| id | doaj.art-26fc0838f61243bfad4b7bbe172cf7d7 |
| institution | Directory Open Access Journal |
| issn | 2304-6732 |
| language | English |
| last_indexed | 2024-03-10T07:17:08Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj.art-26fc0838f61243bfad4b7bbe172cf7d72023-11-22T14:50:52ZengMDPI AGPhotonics2304-67322021-09-018940010.3390/photonics8090400SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep LearningZhe Yang0Yu-Ming Bai1Li-Da Sun2Ke-Xin Huang3Jun Liu4Dong Ruan5Jun-Lin Li6State Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing 100084, ChinaWuhan Digital Engineering Institute, Wuhan 430074, ChinaState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing 100084, ChinaWe propose a concurrent single-pixel imaging, object location, and classification scheme based on deep learning (SP-ILC). We used multitask learning, developed a new loss function, and created a dataset suitable for this project. The dataset consists of scenes that contain different numbers of possibly overlapping objects of various sizes. The results we obtained show that SP-ILC runs concurrent processes to locate objects in a scene with a high degree of precision in order to produce high quality single-pixel images of the objects, and to accurately classify objects, all with a low sampling rate. SP-ILC has potential for effective use in remote sensing, medical diagnosis and treatment, security, and autonomous vehicle control.https://www.mdpi.com/2304-6732/8/9/400single-pixel imagingobject locationobject classificationmultitask learningdeep learning |
| spellingShingle | Zhe Yang Yu-Ming Bai Li-Da Sun Ke-Xin Huang Jun Liu Dong Ruan Jun-Lin Li SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning Photonics single-pixel imaging object location object classification multitask learning deep learning |
| title | SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning |
| title_full | SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning |
| title_fullStr | SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning |
| title_full_unstemmed | SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning |
| title_short | SP-ILC: Concurrent Single-Pixel Imaging, Object Location, and Classification by Deep Learning |
| title_sort | sp ilc concurrent single pixel imaging object location and classification by deep learning |
| topic | single-pixel imaging object location object classification multitask learning deep learning |
| url | https://www.mdpi.com/2304-6732/8/9/400 |
| work_keys_str_mv | AT zheyang spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning AT yumingbai spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning AT lidasun spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning AT kexinhuang spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning AT junliu spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning AT dongruan spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning AT junlinli spilcconcurrentsinglepixelimagingobjectlocationandclassificationbydeeplearning |