Some features of creating a computer vision system

2021 ◽  
pp. 72-74
Author(s):  
Volodymyr Petrivskyi
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Object Recognition ◽  
Vision System ◽  
Computer Vision System ◽  
The Neural Network ◽  
Subsequent Selection ◽  
Selection Of

In the paper some features of models and algorithms of computer vision are presented. An algorithm for training the neural network of object recognition is proposed and described. The peculiarity of the proposed approach is the parallel training of networks with the subsequent selection of the most accurate. The presented results of experiments confirm the effectiveness of the proposed approach.

scholarly journals An Efficient Convolutional Neural Network Computer Vision System to Prevent Sudden Infant Death Syndrome

2020 ◽  
Author(s):  
Vivek S Bharati
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Sudden Infant Death Syndrome ◽  
Infant Death ◽  
Vision System ◽  
Sudden Infant Death ◽  
Activation Function ◽  
Sudden Infant ◽  
Computer Vision System ◽  
Sleeping Position

Sudden Infant Death Syndrome (SIDS) causes infants under one year of age to die inexplicably. One of the most important external factors responsible for the syndrome, called an ‘outside stressor’, is the sleeping position of the baby. When the baby sleeps on the stomach with face down, the risk of SIDS occurring is very high. We propose a Convolutional Neural Network (CNN) based computer vision system that can alert caregivers on their mobile phones within a few seconds of the baby moving to a hazardous face-down sleeping position. The model processes real-time image feeds with a single efficient forward pass. It has a low computational load and a low memory footprint. This would allow it to be embedded in low power edge devices such as crib cameras. Processing at the edge would also alleviate privacy concerns in sending images into the network. The CNN architecture is composed of multiple sets of processing units, each unit containing a 2D convolutional layer with the Rectified Linear Unit activation function followed by a Max Pooling layer. The final layer in the architecture is a fully connected dense layer with the Sigmoid activation function and outputs three classes of sleeping position indicators. The seed corpus for the training dataset was generated from realistic baby dolls with diverse racial mix in three sleeping positions (face-up, turning, face-down). These seed images were used to generate additional images by applying various image transformations. We experimented with various numbers of convolutional processing units and dense layers as well as the number of convolutional kernels to arrive at the optimal production configuration. We observed a consistently high accuracy of detection of sleeping position changes to turning and face-down positions with a trend towards even higher accuracies with caregiver feedback. Therefore, this system is a viable candidate for consideration as a non-intrusive technology to assist in preventing the Sudden Infant Death Syndrome.

scholarly journals Identification of Baikal phytoplankton inferred from computer vision methods and machine learning

2021 ◽  
pp. 1143-1146
Author(s):  
A.V. Lysenko ◽  
◽  
◽  
M.S. Oznobikhin ◽  
E.A. Kireev ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Object Recognition ◽  
Light Microscope ◽  
Optimal Size ◽  
Optimal Parameters ◽  
The Neural Network

Abstract. This study discusses the problem of phytoplankton classification using computer vision methods and convolutional neural networks. We created a system for automatic object recognition consisting of two parts: analysis and primary processing of phytoplankton images and development of the neural network based on the obtained information about the images. We developed software that can detect particular objects in images from a light microscope. We trained a convolutional neural network in transfer learning and determined optimal parameters of this neural network and the optimal size of using dataset. To increase accuracy for these groups of classes, we created three neural networks with the same structure. The obtained accuracy in the classification of Baikal phytoplankton by these neural networks was up to 80%.

scholarly journals Deep neural networks for analysis of fisheries surveillance video and automated monitoring of fish discards

2019 ◽  
Vol 77 (4) ◽  
pp. 1340-1353 ◽  
Author(s):  
Geoff French ◽  
Michal Mackiewicz ◽  
Mark Fisher ◽  
Helen Holah ◽  
Rachel Kilburn ◽  
...  
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Vision System ◽  
Surveillance Video ◽  
Computer Vision System ◽  
Species Classification ◽  
Fish Catch ◽  
Computer Vision Systems

Abstract We report on the development of a computer vision system that analyses video from CCTV systems installed on fishing trawlers for the purpose of monitoring and quantifying discarded fish catch. Our system is designed to operate in spite of the challenging computer vision problem posed by conditions on-board fishing trawlers. We describe the approaches developed for isolating and segmenting individual fish and for species classification. We present an analysis of the variability of manual species identification performed by expert human observers and contrast the performance of our species classifier against this benchmark. We also quantify the effect of the domain gap on the performance of modern deep neural network-based computer vision systems.

Sign in / Sign up

Export Citation Format

Share Document