<scp>3D</scp> reconstruction based on photoelastic fringes

Tao, Bo; Liu, Yao; Huang, Licheng; Chen, Guanjun; Chen, Baojia

doi:10.1002/cpe.6481

Cited by 37 publications

(31 citation statements)

References 49 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show that the detection performance of the improved model is higher than Faster RCNN, YOLOv3, and SSD models. [77][78][79][80][81] This is due to the improved model designing a more efficient basic network, and the use of focal loss to improve the problem of sample imbalance.…”

Section: Model Trainingmentioning

confidence: 99%

Improved single shot multibox detector target detection method based on deep feature fusion

Bai

Sun

Tao

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

The feature layers of different layers in the single shot multibox detector (SSD) are independently used as the input of the classification network, so it is easy to detect the same object. This article proposes an improved SSD model based on deep feature fusion. In the SSD algorithm, the deep feature fusion between the target detection layer and its adjacent feature layer is used, including convolution kernels and pooling kernels of different sizes, down-sampling of low-level features and up-sampling of deconvolution of high-level features. The network is improved by combining the target frame recommendation strategy in the SSD algorithm and the frame regression algorithm. The experimental results show that the improved SSD algorithm improves the detection accuracy and detection rate of the target, and the effect is more obvious for the relatively small-scale target.

show abstract

Section: Model Trainingmentioning

confidence: 99%

Improved single shot multibox detector target detection method based on deep feature fusion

Bai

Sun

Tao

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…The encoderdecoder network structure effectively avoids inefficient learning and sharing in training, and the atrous spatial pyramid pooling significantly enlarges the receptive field while reducing the number of training parameters. These contributions have potential implications for other applications of biological heuristic algorithms, not limited to image processing problem (Tao et al, 2021b), but can even be applied in public opinion dissemination (Chen et al, 2021b;Chen et al, 2021c) and behavior analysis (Xu et al, 2021a;Xiang et al, 2021). Further extended research will provide broader support for future applications in other aspects.…”

Section: Discussionmentioning

confidence: 94%

Retinal Vessel Segmentation Algorithm Based on Residual Convolution Neural Network

Chen

Cao

et al. 2021

Front. Bioeng. Biotechnol.

Self Cite

View full text Add to dashboard Cite

Retinal vessels are the only deep micro vessels that can be observed in human body, the accurate identification of which has great significance on the diagnosis of hypertension, diabetes and other diseases. To this end, a retinal vessel segmentation algorithm based on residual convolution neural network is proposed according to the characteristics of the retinal vessels on fundus images. Improved residual attention module and deep supervision module are utilized, in which the low-level and high-level feature graphs are joined to construct the encoder-decoder network structure, and atrous convolution is introduced to the pyramid pooling. The experiments result on the fundus image data set DRIVE and STARE show that this algorithm can obtain complete retinal vessel segmentation as well as connected vessel stems and terminals. The average accuracy on DRIVE and STARE reaches 95.90 and 96.88%, and the average specificity is 98.85 and 97.85%, which shows superior performance compared to other methods. This algorithm is verified feasible and effective for retinal vessel segmentation of fundus images and has the ability to detect more capillaries.

show abstract

“…In 2011, NASA applied the digital twin concept to the Apollo project to construct virtual bodies of space vehicles in virtual information space, and through the observation and analysis of the virtual bodies, the prediction and maintenance of the flight status of space vehicles were realized, and then the digital twin technology began to attract attention ( Tao et al, 2018 ; Liu Y et al, 2021a ). Many internationally renowned companies have already started to explore the application of digital twin technology in product design, manufacturing and service ( Sun et al, 2020c ; Tao et al, 2021 ). In product design, for the innovative design of complex products, Dassault has established a 3D experience platform based on the digital twin, which uses the information from user interaction to continuously improve the product design model in the information world and to implement it into the physical product improvement ( Sun et al, 2020d ; Fu et al, 2021 ).…”

Section: Related Workmentioning

confidence: 99%

Genetic Algorithm-Based Trajectory Optimization for Digital Twin Robots

Liu

Tao

et al. 2022

Front. Bioeng. Biotechnol.

Self Cite

View full text Add to dashboard Cite

Mobile robots have an important role in material handling in manufacturing and can be used for a variety of automated tasks. The accuracy of the robot’s moving trajectory has become a key issue affecting its work efficiency. This paper presents a method for optimizing the trajectory of the mobile robot based on the digital twin of the robot. The digital twin of the mobile robot is created by Unity, and the trajectory of the mobile robot is trained in the virtual environment and applied to the physical space. The simulation training in the virtual environment provides schemes for the actual movement of the robot. Based on the actual movement data returned by the physical robot, the preset trajectory of the virtual robot is dynamically adjusted, which in turn enables the correction of the movement trajectory of the physical robot. The contribution of this work is the use of genetic algorithms for path planning of robots, which enables trajectory optimization of mobile robots by reducing the error in the movement trajectory of physical robots through the interaction of virtual and real data. It provides a method to map learning in the virtual domain to the physical robot.

show abstract

3D reconstruction based on photoelastic fringes

Cited by 37 publications

References 49 publications

Improved single shot multibox detector target detection method based on deep feature fusion

Improved single shot multibox detector target detection method based on deep feature fusion

Retinal Vessel Segmentation Algorithm Based on Residual Convolution Neural Network

Genetic Algorithm-Based Trajectory Optimization for Digital Twin Robots

Contact Info

Product

Resources

About