A brief review on 2D and 3D image reconstruction using single-pixel imaging

Li, Mengdi; Mathai, Anumol; Li, Yandi; Chen, Qi; Wang, Xin; Xu, Xiping

doi:10.1088/1555-6611/ab9d78

Cited by 7 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e 3D image reconstruction theory plays a typical role in di erent professional elds. Related elds mainly include medical surgery [1], model reconstruction [2], ultrasound propagation [3], three-dimensional pixels [4], etc. In the eld of medical donor image reconstruction, the existing medical donor image reconstruction needs a large amount of data, and the data cannot better re ect the original shape of the medical donor, there were some problems such as poor accuracy.…”

Section: Introductionmentioning

confidence: 99%

Application of Three-Dimensional Image Reconstruction Technology in Neurogenic Intestinal Nursing Tasks

Shen

Huang

Zhang

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

Neurogenic intestinal care is currently a major research topic in the medical field. In order to improve the accuracy of neurogenic intestinal care and simplify the process of neurogenic intestinal care, this paper adopts a three-dimensional analysis theory to extract the key indicators in neurogenic intestinal care. Through the analysis and calculation of the test data, the calculation results of neurogenic intestinal care under the effect of three-dimensional reconstruction technology were obtained. Through the analysis of the results, the calculation law under the action of the optimization model can be obtained. Based on the three-dimensional reconstruction theory, the contents of neurogenic intestinal care were analyzed by the three-dimensional reconstruction de-highlighting algorithm. The three-dimensional curve was used to screen the key indicators of neurogenic intestinal care, so as to obtain the optimized heavy weight model, and the three-dimensional reconstruction model can analyze the indicators of neurogenic intestinal care. It can be seen from relevant studies that different indicators have different trends in their range of change in the curve projection diagram of the 3D curve screening method. Among them, the curve shadow and curve point have obvious downward changes, while the curve deviation has U-shaped changes. The range of curve weights is relatively large. The variation rule between different data in the 3D curve segment can be obtained through the cost function. Among them, the cost function index and the cost model parameter have the same change trend, and the overall fluctuation range is relatively small through the space index. In the calculation results of neurogenic intestinal care, different factors will have a great influence on the calculation results. Neurons and intestinal peristalsis have the same change trend, while the linear characteristics of nerve endings are relatively obvious, and the fluctuation characteristics of gastrointestinal digestion are good. The health standard decreases linearly with the increase of the sample, and the dynamic reconstruction has a positive effect on the data. This study can provide research ideas for the analysis of neurogenic gut.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Three-Dimensional Image Reconstruction Technology in Neurogenic Intestinal Nursing Tasks

Shen

Huang

Zhang

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…The SPI is a powerful imaging method for obtaining spatial object information in low-light situations. [71,72]. To get LR components, raw data was iteratively processed using Total Variation (TV) regularization [73], as illustrated in Figure 26.…”

Section: Super-resolutionmentioning

confidence: 99%

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Er¹,

Chen²

2023

Preprint

View full text Add to dashboard Cite

Underwater marine object detection, as one of the most fundamental techniques in marine engineering, has been shown to exhibit significant potential for exploring underwater environment in recent years. It has been applied widely in the monitoring of underwater ecosystems, exploration of natural resources, management of commercial fishery management, and other areas. However, due to the complexity of underwater environment, characteristics of marine object, and limitation from exploration equipment, the detection performance revolving around speed, accuracy and robustness could be degraded dramatically. In this context, we present a survey of deep-learning-based underwater marine object detection. To facilitate comprehensive understanding of the subject matter, we categorize the existing research challenges of underwater object detection into image quality degradation, small object detection, poor generalization and real-time detection. Corresponding to each category of the existing challenges, we review recent advances and highlight the pros and cons of existing techniques. Furthermore, we give a detailed and critical review of the most widely used benchmark datasets for underwater marine object detection. Comparisons with existing reviews and future trends of the subject matter, particularly AI-based techniques, are also presented.

show abstract

“…In the case of applications such as time of flight imaging, resolution subsampling, or active multispectral imaging, SPI methods bring advantages over the use of FPA sensors. [18][19][20] Furthermore, the SPI techniques profit strongly from recent technology advancements. Dozens of thousands high resolution scene sampling patterns can be acquired in only one second using digital micromirror arrays.…”

Section: Single Pixel Imaging As An Alternative For Focal Plane Arraysmentioning

confidence: 99%

Modular, multispectral infrared imaging system for reflection and transmission measurements

Stojek

Labaj

2023

Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XXI

View full text Add to dashboard Cite

In this study we propose a new approach to active illumination multispectral imaging with only one detector per spectral channel. Our setup is characterized by a high signal-to-noise ratio, relatively simple design and high spatial resolution. It can be integrated with multiple continuous or pulse light lasers operating at different wavelengths in the near-and mid-infrared spectral regions. We present a demonstrator which works in two spectral ranges (1550 nm and 2992 nm) with scattered and transmitted light. We provide examples of acquired multispectral images. Finally, we put forward proposals for further development which will allow for the simultaneous acquisition of dozens of spectral channels, with additional improvements of the image resolution and quality.

show abstract

A brief review on 2D and 3D image reconstruction using single-pixel imaging

Cited by 7 publications

References 46 publications

Application of Three-Dimensional Image Reconstruction Technology in Neurogenic Intestinal Nursing Tasks

Application of Three-Dimensional Image Reconstruction Technology in Neurogenic Intestinal Nursing Tasks

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Modular, multispectral infrared imaging system for reflection and transmission measurements

Contact Info

Product

Resources

About