Combining time of flight and photometric stereo imaging for 3D reconstruction of discontinuous scenes

Francois, Emma Le; Griffiths, Alexander D.; McKendry, Jonathan J. D.; Chen, Haochang; Li, David; Henderson, Robert K.; Herrnsdorf, Johannes; Dawson, Martin D.; Strain, Michael J.

doi:10.1364/ol.424000

Cited by 9 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 67 ] However, the traditional method is costly, and the operation is quite complicated. For example, time‐of‐flight depth cameras [ 68 , 69 ] consist of components such as light sources, optical elements, sensors, control circuitry, and processing circuitry. These cameras are known for their high cost and using them for sampling 3D scenes can be easily affected by multiple reflections.…”

Section: Computation Of Multi‐depth Diffraction Fieldmentioning

confidence: 99%

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Yan,

Liu,

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Efficiently generating 3D holograms is one of the most challenging research topics in the field of holography. This work introduces a method for generating multi‐depth phase‐only holograms using a fully convolutional neural network (FCN). The method primarily involves a forward–backward‐diffraction framework to compute multi‐depth diffraction fields, along with a layer‐by‐layer replacement method (L2RM) to handle occlusion relationships. The diffraction fields computed by the former are fed into the carefully designed FCN, which leverages its powerful non‐linear fitting capability to generate multi‐depth holograms of 3D scenes. The latter can smooth the boundaries of different layers in scene reconstruction by complementing information of occluded objects, thus enhancing the reconstruction quality of holograms. The proposed method can generate a multi‐depth 3D hologram with a PSNR of 31.8 dB in just 90 ms for a resolution of 2160 × 3840 on the NVIDIA Tesla A100 40G tensor core GPU. Additionally, numerical and experimental results indicate that the generated holograms accurately reconstruct clear 3D scenes with correct occlusion relationships and provide excellent depth focusing.

show abstract

Section: Computation Of Multi‐depth Diffraction Fieldmentioning

confidence: 99%

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Yan,

Liu,

et al. 2024

Advanced Science

View full text Add to dashboard Cite

show abstract

“…According to Table 2 , compared with other types of detection methods, the designed method has achieved better results, and the number of false detection and missed detection is also at a low level, 140 and 176, respectively [ 29 ]. While AP, precision, and recall reached 90.2%, 95.5%, and 90.3%, respectively, which were significantly higher than the other four methods.…”

Section: Test Verificationmentioning

confidence: 99%

Museum Relic Image Detection and Recognition Based on Deep Learning

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To improve the accuracy of museum cultural relic image recognition, the DenseNet and ResNet are selected as the backbone neural networks for detection and recognition. In view of the small target problem in cultural relics, the feature pyramid is introduced in this paper to improve the DenseNet method. The accuracy of target detection is improved through multiscale feature extraction and fusion. At the same time, aiming the problem of weak robustness and feature extraction of cultural relic images, the attention mechanism is proposed to improve ResNet. Therefore, this network can pay attention to the key of feature areas in the image. Finally, the aforementioned methods are verified by experiments. The results show that compared with the YOLOv3 and other algorithms, the accuracy of the improved ResNet proposed in this experiment is above 90%. Furthermore, the number of missed and erroneous detection is the lowest, which are 171 and 134, respectively. The identified mAP indicator accuracy can reach 86%, which also exceeds SVD-Net and DenseNet. It can be seen that the constructed method can effectively detect and recognize the museum cultural relic images.

show abstract

“…However, since it is difficult to distinguish non-destructive defects from destructive defects, the effect of traditional machine vision detection methods in detecting high reflection objects is not ideal. Some scholars suggested using photometric stereo vision or the three-dimensional point cloud measurement method to detect destructive defects [ 2 , 3 , 4 ]. However, photometric stereo vision is suitable for the surface defect detection of diffuse objects.…”

Section: Introductionmentioning

confidence: 99%

Phase Deflectometry for Defect Detection of High Reflection Objects

Cheng

Wang

Zhu

et al. 2023

Sensors

View full text Add to dashboard Cite

A method for detecting the surface defects of high reflection objects using phase deflection is proposed. The abrupt change in the surface gradient at the defect leads to the change in the fringe phase. Therefore, Gray code combined with a four-step phase-shift method was employed to obtain the surface gradients to characterize the defects. Then, through the double surface illumination model, the relationship between illumination intensity and phase was established. The causes of periodic error interference were analyzed, and the method of adjusting the fringe width to eliminate it was proposed. Finally, experimental results showed the effectiveness of the proposed method.

show abstract

Combining time of flight and photometric stereo imaging for 3D reconstruction of discontinuous scenes

Cited by 9 publications

References 18 publications

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Museum Relic Image Detection and Recognition Based on Deep Learning

Phase Deflectometry for Defect Detection of High Reflection Objects

Contact Info

Product

Resources

About