scholarly journals Spiking neural networks for computer vision

2018 ◽  
Vol 8 (4) ◽  
pp. 20180007 ◽  
Author(s):  
Michael Hopkins ◽  
Garibaldi Pineda-García ◽  
Petruţ A. Bogdan ◽  
Steve B. Furber
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Network Architecture ◽  
Visual Scene ◽  
Vision Systems ◽  
Biological Vision ◽  
Vision Sensors ◽  
Learning Capabilities ◽  
Spatio Temporal ◽  
Event Based

State-of-the-art computer vision systems use frame-based cameras that sample the visual scene as a series of high-resolution images. These are then processed using convolutional neural networks using neurons with continuous outputs. Biological vision systems use a quite different approach, where the eyes (cameras) sample the visual scene continuously, often with a non-uniform resolution, and generate neural spike events in response to changes in the scene. The resulting spatio-temporal patterns of events are then processed through networks of spiking neurons. Such event-based processing offers advantages in terms of focusing constrained resources on the most salient features of the perceived scene, and those advantages should also accrue to engineered vision systems based upon similar principles. Event-based vision sensors, and event-based processing exemplified by the SpiNNaker (Spiking Neural Network Architecture) machine, can be used to model the biological vision pathway at various levels of detail. Here we use this approach to explore structural synaptic plasticity as a possible mechanism whereby biological vision systems may learn the statistics of their inputs without supervision, pointing the way to engineered vision systems with similar online learning capabilities.

The machine training in problems of satellite images’s processing

Metrologiya ◽  
2020 ◽  
pp. 15-37
Author(s):  
L. P. Bass ◽  
Yu. A. Plastinin ◽  
I. Yu. Skryabysheva
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Computer Vision ◽  
Satellite Images ◽  
Vision Systems ◽  
Earth Remote Sensing ◽  
Practical Applications ◽  
Convolution Neural Networks ◽  
Computer Vision Systems ◽  
Trained Neural Network

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

scholarly journals Comparative Performance Analysis of Neural Network Real-Time Object Detections in Different Implementations

2020 ◽  
Vol 226 ◽  
pp. 02020
Author(s):  
Alexey V. Stadnik ◽  
Pavel S. Sazhin ◽  
Slavomir Hnatic
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Performance Analysis ◽  
Object Detection ◽  
Real Time ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Comparative Performance

The performance of neural networks is one of the most important topics in the field of computer vision. In this work, we analyze the speed of object detection using the well-known YOLOv3 neural network architecture in different frameworks under different hardware requirements. We obtain results, which allow us to formulate preliminary qualitative conclusions about the feasibility of various hardware scenarios to solve tasks in real-time environments.

scholarly journals Deep Learning Based Switching Filter for Impulsive Noise Removal in Color Images

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2782
Author(s):  
Krystian Radlak ◽  
Lukasz Malinski ◽  
Bogdan Smolka
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Network Architecture ◽  
Noise Suppression ◽  
Impulsive Noise ◽  
Noise Removal ◽  
Vision Systems ◽  
Mean Filter ◽  
Computer Vision Systems ◽  
Active Research

Noise reduction is one of the most important and still active research topics in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we observed a substantially increased interest in the application of deep learning algorithms. Many computer vision systems use them, due to their impressive capability of feature extraction and classification. While these methods have also been successfully applied in image denoising, significantly improving its performance, most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering technique intended for impulsive noise removal using deep learning. In the proposed method, the distorted pixels are detected using a deep neural network architecture and restored with the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in color digital images.

Neural networks for precise measurement in computer vision systems

1995 ◽  
Vol 27 (3) ◽  
pp. 225-236 ◽  
Author(s):  
Chao-Ton Su ◽  
C.Alec Chang ◽  
Fang-Chih Tien
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Precise Measurement ◽  
Vision Systems ◽  
Computer Vision Systems

Application of convolutional neural networks for monitoring of marine objects

2020 ◽  
pp. 53-61
Author(s):  
Н.А. Полковникова ◽  
Е.В. Тузинкевич ◽  
А.Н. Попов
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Research Process ◽  
Probability Of Detection ◽  
Neural Network Architecture ◽  
Deep Convolutional Neural Networks

В статье рассмотрены технологии компьютерного зрения на основе глубоких свёрточных нейронных сетей. Применение нейронных сетей особенно эффективно для решения трудно формализуемых задач. Разработана архитектура свёрточной нейронной сети применительно к задаче распознавания и классификации морских объектов на изображениях. В ходе исследования выполнен ретроспективный анализ технологий компьютерного зрения и выявлен ряд проблем, связанных с применением нейронных сетей: «исчезающий» градиент, переобучение и вычислительная сложность. При разработке архитектуры нейросети предложено использовать функцию активации RELU, обучение некоторых случайно выбранных нейронов и нормализацию с целью упрощения архитектуры нейросети. Сравнение используемых в нейросети функций активации ReLU, LeakyReLU, Exponential ReLU и SOFTMAX выполнено в среде Matlab R2020a. На основе свёрточной нейронной сети разработана программа на языке программирования Visual C# в среде MS Visual Studio для распознавания морских объектов. Программапредназначена для автоматизированной идентификации морских объектов, производит детектирование (нахождение объектов на изображении) и распознавание объектов с высокой вероятностью обнаружения. The article considers computer vision technologies based on deep convolutional neural networks. Application of neural networks is particularly effective for solving difficult formalized problems. As a result convolutional neural network architecture to the problem of recognition and classification of marine objects on images is implemented. In the research process a retrospective analysis of computer vision technologies was performed and a number of problems associated with the use of neural networks were identified: vanishing gradient, overfitting and computational complexity. To solve these problems in neural network architecture development, it was proposed to use RELU activation function, training some randomly selected neurons and normalization for simplification of neural network architecture. Comparison of ReLU, LeakyReLU, Exponential ReLU, and SOFTMAX activation functions used in the neural network implemented in Matlab R2020a.The computer program based on convolutional neural network for marine objects recognition implemented in Visual C# programming language in MS Visual Studio integrated development environment. The program is designed for automated identification of marine objects, produces detection (i.e., presence of objects on image), and objects recognition with high probability of detection.

scholarly journals Event-Based Gesture Recognition through a Hierarchy of Time-Surfaces for FPGA

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3404 ◽  
Author(s):  
Ricardo Tapiador-Morales ◽  
Jean-Matthieu Maro ◽  
Angel Jimenez-Fernandez ◽  
Gabriel Jimenez-Moreno ◽  
Ryad Benosman ◽  
...  
Keyword(s):  
Gesture Recognition ◽  
Time History ◽  
High Temporal Resolution ◽  
Vision Sensors ◽  
Dynamic Vision ◽  
Mammalian Retina ◽  
Continuous Stream ◽  
Spatio Temporal ◽  
Event Based ◽  
Embedded Applications

Neuromorphic vision sensors detect changes in luminosity taking inspiration from mammalian retina and providing a stream of events with high temporal resolution, also known as Dynamic Vision Sensors (DVS). This continuous stream of events can be used to extract spatio-temporal patterns from a scene. A time-surface represents a spatio-temporal context for a given spatial radius around an incoming event from a sensor at a specific time history. Time-surfaces can be organized in a hierarchical way to extract features from input events using the Hierarchy Of Time-Surfaces algorithm, hereinafter HOTS. HOTS can be organized in consecutive layers to extract combination of features in a similar way as some deep-learning algorithms do. This work introduces a novel FPGA architecture for accelerating HOTS network. This architecture is mainly based on block-RAM memory and the non-restoring square root algorithm, requiring basic components and enabling it for low-power low-latency embedded applications. The presented architecture has been tested on a Zynq 7100 platform at 100 MHz. The results show that the latencies are in the range of 1 μ s to 6.7 μ s, requiring a maximum dynamic power consumption of 77 mW. This system was tested with a gesture recognition dataset, obtaining an accuracy loss for 16-bit precision of only 1.2% with respect to the original software HOTS.

scholarly journals Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision

2019 ◽  
Author(s):  
Courtney J Spoerer ◽  
Tim C Kietzmann ◽  
Johannes Mehrer ◽  
Ian Charest ◽  
Nikolaus Kriegeskorte
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Visual Recognition ◽  
Network Models ◽  
Neural Network Models ◽  
Biological Vision ◽  
Visual Systems ◽  
Confidence Threshold ◽  
Recurrent Processing

AbstractDeep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computational resources over time, and so might boost the performance of a physically finite brain or model. Here we show: (1) Recurrent convolutional neural network models outperform feedforward convolutional models matched in their number of parameters in large-scale visual recognition tasks on natural images. (2) Setting a confidence threshold, at which recurrent computations terminate and a decision is made, enables flexible trading of speed for accuracy. At a given confidence threshold, the model expends more time and energy on images that are harder to recognise, without requiring additional parameters for deeper computations. (3) The recurrent model’s reaction time for an image predicts the human reaction time for the same image better than several parameter-matched and state-of-the-art feedforward models. (4) Across confidence thresholds, the recurrent model emulates the behaviour of feedforward control models in that it achieves the same accuracy at approximately the same computational cost (mean number of floating-point operations). However, the recurrent model can be run longer (higher confidence threshold) and then outperforms parameter-matched feedforward comparison models. These results suggest that recurrent connectivity, a hallmark of biological visual systems, may be essential for understanding the accuracy, flexibility, and dynamics of human visual recognition.Author summaryDeep neural networks provide the best current models of biological vision and achieve the highest performance in computer vision. Inspired by the primate brain, these models transform the image signals through a sequence of stages, leading to recognition. Unlike brains in which outputs of a given computation are fed back into the same computation, these models do not process signals recurrently. The ability to recycle limited neural resources by processing information recurrently could explain the accuracy and flexibility of biological visual systems, which computer vision systems cannot yet match. Here we report that recurrent processing can improve recognition performance compared to similarly complex feedforward networks. Recurrent processing also enabled models to behave more flexibly and trade off speed for accuracy. Like humans, the recurrent network models can compute longer when an object is hard to recognise, which boosts their accuracy. The model’s recognition times predicted human recognition times for the same images. The performance and flexibility of recurrent neural network models illustrates that modeling biological vision can help us improve computer vision.

Sign in / Sign up

Export Citation Format

Share Document