scholarly journals Optical Multi-Imaging-Casting Accelerator for Fully Parallel Universal Convolution Computing

2021 ◽  
Author(s):  
Changhe Zhou ◽  
Guoqing Ma ◽  
Rongwei Zhu ◽  
Junjie Yu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recognition Accuracy ◽  
Optical Computing ◽  
Two Dimensional ◽  
Potential Solution ◽  
New Paradigm ◽  
The Core ◽  
Coding Method ◽  
Computing Accuracy

Abstract Over the last few years, optical computing has become a potential solution to computationally heavy convolution, aimed at accelerating various artificial intelligence applications. However, past schemes have never efficiently realized fully parallel optical convolution. Here, we propose a new paradigm for a universal convolution accelerator with truly massive parallelism and high precision based on optical multi-imaging-casting architecture. Specifically, a two-dimensional Dammann grating is adopted for the generation of multiple displaced images of the kernel, which is the core process for kernel sliding on the convolved matrix. Our experimental results indicate that the computing accuracy is typically close to 8-bit, and this accuracy can be improved further by using hybrid analog–digital coding method. In addition, a convolutional neural network for the standard MNIST dataset is demonstrated, and the recognition accuracy for inference is up to 97.3%. The paradigm reported here will open new opportunities for high-throughput universal convolution accelerators for real-time or quasi-real-time AI applications.

scholarly journals Investigation of optimal configurations of a convolutional neural network for the identification of objects in real-time

2019 ◽  
pp. 417-423
Author(s):  
M A Isayev ◽  
D A Savelyev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Real Time ◽  
State Of The Art ◽  
Average Precision ◽  
The Core ◽  
Particular Solution ◽  
Optimal Configurations

The comparison of different convolutional neural networks which are the core of the most actual solutions in the computer vision area is considers in hhe paper. The study includes benchmarks of this state-of-the-art solutions by some criteria, such as mAP (mean average precision), FPS (frames per seconds), for the possibility of real-time usability. It is concluded on the best convolutional neural network model and deep learning methods that were used at particular solution.

Methods and means for real-time object recognition accuracy increase in video images on ios mobile platform

2021 ◽  
Vol 3 (1) ◽  
pp. 80-88
Author(s):  
D Kushnir ◽  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Frame Rate ◽  
Mobile Platform ◽  
Additional Layer ◽  
The Neural Network ◽  
Analytical Review ◽  
Accuracy Increase

As a result of the analytical review, it was established that the family of Yolo models is a promising area of search and recognition of objects. However, existing implementations do not support the ability to run the model on the iOS platform. To achieve these goals, a comprehensive scalable conversion system has been developed to improve the recognition accuracy of arbitrary models based on the Docker system. The method of improvement is to add a layer with the Mish activation function to the original model. The method of conversion is to quickly convert any Yolo model to CoreML format. As part of the study of these techniques, a model of the neural network Yolov4_TCAR was created. Additionally, a method of accelerating the load on the CPU using an additional layer of neural network with the function of activating Mish in Swift for the iOS mobile platform was added. As a result, the effectiveness of the Mish activation function, the CPU load of the mobile device, the amount of RAM used, and the frame rate when using the improved original Yolov4-TCAR model were studied. The results of the research confirmed the functioning of the algorithm for conversion and accuracy increase of the neural network model in real-time.

scholarly journals Data Augmentation Technology for Improving the Recognition Accuracy of Target Image

2020 ◽  
Vol 2 (3) ◽  
pp. 58
Author(s):  
Feng Ling ◽  
Rajamohan Parthasarathy ◽  
Ye Wang ◽  
Sokchoo Ng
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Recognition Accuracy ◽  
Target Image ◽  
Image Labeling ◽  
Related Data ◽  
The Core ◽  
Lighting Conditions ◽  
Network Algorithm ◽  
Neural Network Algorithm

<p align="justify">Relevant studies have pointed out that public has paid highly attention on the accuracy of neural network algorithm as it is widely applied in recent years. According to the present practice, it is quite difficult to collect related data when applying neural network algorithm. Besides, problems of trifles and complication exists in data image labeling process, which leads to a bad impact on the recognition accuracy of targets. In this article, analyzes are conducted on the relevant data from the perspective of data image processing with neural network algorithm as the core of this work. Besides, corresponding data augmentation technology is also put forward. Generally speaking, this technology has effectively realized the simulation under different shooting and lighting conditions by flipping, transforming and changing the pixel positions of the related original images, which contributes to the expansion of database types and promotes the robustness of detection work.</p>

Real-time fault diagnosis using deep fusion of features extracted by parallel long short-term memory with peephole and convolutional neural network

2020 ◽  
pp. 095965182094829
Author(s):  
Funa Zhou ◽  
Zhiqiang Zhang ◽  
Danmin Chen
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Short Term Memory ◽  
Two Dimensional ◽  
Short Term ◽  
Term Memory ◽  
One Dimensional ◽  
Long Short Term Memory

Analysis of one-dimensional vibration signals is the most common method used for safety analysis and health monitoring of rotary machines. How to effectively extract features involved in one-dimensional sequence data is crucial for the accuracy of real-time fault diagnosis. This article aims to develop more effective means of extracting useful features potentially involved in one-dimensional vibration signals. First, an improved parallel long short-term memory called parallel long short-term memory with peephole is designed by adding a peephole connection before each forget gate to prevent useless information transferring in the cell. It can not only solve the memory bottleneck problem of traditional long short-term memory for long sequence but also can make full use of all possible information helpful for feature extraction. Second, a fusion network with new training mechanism is designed to fuse features extracted from parallel long short-term memory with peephole and convolutional neural network, respectively. The fusion network can incorporate two-dimensional screenshot image into comprehensive feature extraction. It can provide more accurate fault diagnosis result since two-dimensional screenshot image is another form of expression for one-dimensional vibration sequence involving additional trend and locality information. Finally, real-time two-dimensional screenshot image is fed into convolutional neural network to secure a real-time online diagnosis which is the primary requirement of the engineers in health monitoring. Validity of the proposed method is verified by fault diagnosis for rolling bearing and gearbox.

scholarly journals The Aircraft Pose Estimation Based on a Convolutional Neural Network

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Daoyong Fu ◽  
Wei Li ◽  
Songchen Han ◽  
Xinyan Zhang ◽  
Zhaohuan Zhan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Pose Estimation ◽  
Estimation Method ◽  
Human Pose Estimation ◽  
Two Dimensional ◽  
Surveillance Video ◽  
Key Points ◽  
Human Pose

The pose estimation of the aircraft in the airport plays an important role in preventing collisions and constructing the real-time scene of the airport. However, current airport target surveillance methods regard the aircraft as a point, neglecting the importance of pose estimation. Inspired by human pose estimation, this paper presents an aircraft pose estimation method based on a convolutional neural network through reconstructing the two-dimensional skeleton of an aircraft. Firstly, the key points of an aircraft and the matching relationship are defined to design a 2D skeleton of an aircraft. Secondly, a convolutional neural network is designed to predict all key points and components of the aircraft kept in the confidence maps and the Correlation Fields, respectively. Thirdly, all key points are coarsely matched based on the matching relationship and then refined through the Correlation Fields. Finally, the 2D skeleton of an aircraft is reconstructed. To overcome the lack of benchmark dataset, the airport surveillance video and Autodesk 3ds Max are utilized to build two datasets. Experiment results show that the proposed method get better performance in terms of accuracy and efficiency compared with other related methods.

Sign in / Sign up

Export Citation Format

Share Document