Journal
OPTICS AND LASERS IN ENGINEERING
Volume 153, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.optlaseng.2022.106989
Keywords
Particle field; Deep learning; 3D reconstruction; Depth from defocus
Categories
Funding
- Science and Technology Research Project for the Colleges in Hebei Province [QN2020426]
- Sci-ence and Technology Research and Development Project of Handan City [19422083008-69]
- Natural Science Foundation of Hebei Province [F2018402285]
- National Natural Science Founda-tion of China [62175059]
Ask authors/readers for more resources
Our paper proposes a particle field positioning method based on EfficientNet convolutional neural network and depth-from-defocus method. By classifying the defocus based on characteristics, combined with the lateral positions obtained by traditional methods, the proposed method can determine the 3D position of each particle. Experimental results show that our approach successfully measures the particle field and is suitable for 3D tracking of planktons. Additionally, simulative data generated by a cycle generative adversarial network reduces the workload of training data collection. The high efficiency of the proposed method demonstrates its potential application in various fields.
Our paper presents a particle field positioning method based on a developed convolutional neural network (CNN) architecture named EfficientNet, and the depth-from-defocus method which detects the depth of a particle from the blur images. The input two-dimensional images can be classified by the amount of defocus based on their characteristics. EfficientNet is then applied to estimate the depth positions of the particles. Combined with their lateral positions obtained by the traditional methods, the proposed method can determine each particle's three-dimensional (3D) position in the field. Verifiable experimental results support that our approach successfully measures the identical particle field. It is also proved to be suitable for the 3D tracking of the particles by investi-gating the planktons. In addition, we employed a cycle generative adversarial network to produce simulative data to reduce the workload of training data collection. Finally, the high efficiency of the proposed method shows the application potential in various fields, such as the 3D positioning, fluid investigation, and tracking of the dynamic samples.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available