RESEARCH ON APPLICATION OF NEURAL NETWORKS FOR RESTORING DAMAGED VIDEO FILES OF AVI AND MP4 FORMATS

2021 ◽  
Vol 55 (3) ◽  
pp. 25-32
Author(s):  
GERASKIN ALEKSEY S. ◽  
◽  
UKOLOV RODION V. ◽  

In the modern world, video files play a special role. The development of video compression algorithms and the growth of the Internet’s capabilities make it possible to transfer video files. Damage inevitably occurs when transferring video files. Accordingly, the question arises about restoring a damaged file and obtaining information from it. The article discusses the most commonly used video file extensions AVI, MP4. As a result of the study, it was revealed that the most common damage is in the headers, which leads to errors when opening files by players, data is damaged less often. Data corruption leads to the fact that a certain fragment of the video file is either played with errors, distortions, or is skipped. The article discusses the possibility of recovering damaged video file using the removal of undistorted data and proposes an algorithm for analyzing frames using a neural network. As part of the algorithm, a neural network is used to identify damaged frames in video data. The algorithm was implemented as a software product. For the first stage of checking the efficiency of the algorithm, deliberate distortions of one frame were made for each video file under study. As a result of experimental verification of the developed algorithm, it was revealed that it provides high accuracy in detecting distorted frame sequences.

2021 ◽  
Vol 2021 (1) ◽  
pp. 78-82
Author(s):  
Pak Hung Chan ◽  
Georgina Souvalioti ◽  
Anthony Huggett ◽  
Graham Kirsch ◽  
Valentina Donzella

Video compression in automated vehicles and advanced driving assistance systems is of utmost importance to deal with the challenge of transmitting and processing the vast amount of video data generated per second by the sensor suite which is needed to support robust situational awareness. The objective of this paper is to demonstrate that video compression can be optimised based on the perception system that will utilise the data. We have considered the deployment of deep neural networks to implement object (i.e. vehicle) detection based on compressed video camera data extracted from the KITTI MoSeg dataset. Preliminary results indicate that re-training the neural network with M-JPEG compressed videos can improve the detection performance with compressed and uncompressed transmitted data, improving recalls and precision by up to 4% with respect to re-training with uncompressed data.


Connectivity ◽  
2020 ◽  
Vol 146 (4) ◽  
Author(s):  
G. Ya. Kis ◽  
◽  
V. M. Cherevyk ◽  

The article describes the current state of data transfer protocols and methods of image and video compression through the use of artificial neural networks, namely convolutional multilayer networks and deep structured learning. Based on recent publications, a comparative analysis of the performance of classical compression methods and methods based on neural networks was performed. The most effective are those compression methods which are based on decorrelation transforms, namely discrete cosine (JPEG standard) and wavelet (JPEG-2000 standard) transforms. The transform coefficients have a well-understood physical content of spatial frequencies and can be further quantized for a more optimal representation of components that are less important for human perception. The HEVC standard guarantees a more efficient image compression scheme that further takes advantage of the similarity of adjacent blocks and uses interpolation (intracoding). Based on the HEVC standard, the BPG (better portable graphics) format was developed to be used on the Internet as an alternative to JPEG, which is much more efficient than other standards. An overview of the current state of open standards, provided in the article, gives an explanation of what properties of neural networks can be applied to image compression. There are two approaches towards the compression using neural networks: in case of the first approach neural network is used as a part of an existing algorithm (hybrid coding), and in case of the second approach the neural network gives a concise representation of the data (compression network). The final conclusions were made as regards to the application of these algorithms in H.265 protocol (HEVC) and the possibility of creating a new protocol which is completely based on the neural network. Protocols using neural network show better results during image compression, but are currently hard to be subjected to standardization in order to obtain the expected result in case of different network architects. We may expect and predict an increase in the need for video transmission in the future, which will bump into the imitating nature of classical approaches. At the same time, the development of specialized processors for parallel data processing and implementation of neural networks is currently underway. These two factors indicate that neural networks must be embedded into the industrial data standards.


2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Author(s):  
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.


2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.


2020 ◽  
Vol 68 (4) ◽  
pp. 283-293
Author(s):  
Oleksandr Pogorilyi ◽  
Mohammad Fard ◽  
John Davy ◽  
Mechanical and Automotive Engineering, School ◽  
Mechanical and Automotive Engineering, School ◽  
...  

In this article, an artificial neural network is proposed to classify short audio sequences of squeak and rattle (S&R) noises. The aim of the classification is to see how accurately the trained classifier can recognize different types of S&R sounds. Having a high accuracy model that can recognize audible S&R noises could help to build an automatic tool able to identify unpleasant vehicle interior sounds in a matter of seconds from a short audio recording of the sounds. In this article, the training method of the classifier is proposed, and the results show that the trained model can identify various classes of S&R noises: simple (binary clas- sification) and complex ones (multi class classification).


2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.


2013 ◽  
Vol 385-386 ◽  
pp. 589-592
Author(s):  
Hong Qi Wu ◽  
Xiao Bin Li

In order to improve the diagnosis rates of transformer fault, a research on application of RBF neural network is carried out. The structure and working principle of radial basis function (RBF) neural network are analyzed and a three layer RBF network is also designed for transformer fault diagnosis. It is proved by MATLAB experiment that RBF neural network is a strong classifier which is used to diagnose transformer fault effectively.


Sign in / Sign up

Export Citation Format

Share Document