3802 Analysis of Pilot Landing Control using Neural Network by Video Data

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.

Download Full-text

Semi-Supervised Faster RCNN-Based Person Detection and Load Classification for Far Field Video Surveillance

Machine Learning and Knowledge Extraction ◽

10.3390/make1030044 ◽

2019 ◽

Vol 1 (3) ◽

pp. 756-767 ◽

Cited By ~ 5

Author(s):

Haoran Wei ◽

Nasser Kehtarnavaz

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Video Data ◽

Far Field ◽

Neural Network Classifier ◽

Computationally Efficient ◽

Person Detection ◽

Video Cameras ◽

Processing Steps

This paper presents a semi-supervised faster region-based convolutional neural network (SF-RCNN) approach to detect persons and to classify the load carried by them in video data captured from distances several miles away via high-power lens video cameras. For detection, a set of computationally efficient image processing steps are considered to identify moving areas that may contain a person. These areas are then passed onto a faster RCNN classifier whose convolutional layers consist of ResNet50 transfer learning. Frame labels are obtained in a semi-supervised manner for the training of the faster RCNN classifier. For load classification, another convolutional neural network classifier whose convolutional layers consist of GoogleNet transfer learning is used to distinguish a person carrying a bundle from a person carrying a long arm. Despite the challenges associated with the video dataset examined in terms of the low resolution of persons, the presence of heat haze, and the shaking of the camera, it is shown that the developed approach outperforms the faster RCNN approach.

Download Full-text

Neural Network Analysis of Pilot Landing Control in Real Flight

Journal of Mechanical Systems for Transportation and Logistics ◽

10.1299/jmtl.1.14 ◽

2008 ◽

Vol 1 (1) ◽

pp. 14-21 ◽

Cited By ~ 2

Author(s):

Ryota MORI ◽

Shinji SUZUKI ◽

Kazuya MASUI ◽

Hiroshi TOMITA

Keyword(s):

Neural Network ◽

Network Analysis ◽

Neural Network Analysis ◽

Landing Control

Download Full-text

Analysis of Pilot Landing Control Using Neural Network

AIAA Atmospheric Flight Mechanics Conference and Exhibit ◽

10.2514/6.2006-6498 ◽

2006 ◽

Cited By ~ 1

Author(s):

Yuki Sakamoto ◽

Ryota Mori ◽

Shinji Suzuki ◽

Hiroshi Takahara

Keyword(s):

Neural Network ◽

Landing Control

Download Full-text

Neural Network Analysis of Pilot Landing Control under Real Flight Condition

46th AIAA Aerospace Sciences Meeting and Exhibit ◽

10.2514/6.2008-880 ◽

2008 ◽

Author(s):

Ryota Mori ◽

Shinji Suzuki

Keyword(s):

Neural Network ◽

Network Analysis ◽

Neural Network Analysis ◽

Flight Condition ◽

Landing Control

Download Full-text

The data conundrum: compression of automotive imaging data and deep neural network based perception

London Imaging Meeting ◽

10.2352/issn.2694-118x.2021.lim-78 ◽

2021 ◽

Vol 2021 (1) ◽

pp. 78-82

Author(s):

Pak Hung Chan ◽

Georgina Souvalioti ◽

Anthony Huggett ◽

Graham Kirsch ◽

Valentina Donzella

Keyword(s):

Neural Network ◽

Video Compression ◽

Situational Awareness ◽

Video Camera ◽

Video Data ◽

Compressed Video ◽

Imaging Data ◽

The Neural Network ◽

Perception System ◽

Driving Assistance

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.

Download Full-text

Lightweight Neural Network-Based Viewport Prediction for Live VR Streaming in Wireless Video Sensor Network

Mobile Information Systems ◽

10.1155/2021/8501990 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Xiaolei Chen ◽

Baoning Cao ◽

Ishfaq Ahmad

Keyword(s):

Neural Network ◽

Sensor Network ◽

Prediction Accuracy ◽

Prediction Method ◽

Video Data ◽

Wireless Video ◽

Resource Saving ◽

Movement Data ◽

Unit Module ◽

Video Sensor

Live virtual reality (VR) streaming (a.k.a., 360-degree video streaming) has become increasingly popular because of the rapid growth of head‐mounted displays and 5G networking deployment. However, the huge bandwidth and the energy required to deliver live VR frames in the wireless video sensor network (WVSN) become bottlenecks, making it impossible for the application to be deployed more widely. To solve the bandwidth and energy challenges, VR video viewport prediction has been proposed as a feasible solution. However, the existing works mainly focuses on the bandwidth usage and prediction accuracy and ignores the resource consumption of the server. In this study, we propose a lightweight neural network-based viewport prediction method for live VR streaming in WVSN to overcome these problems. In particular, we (1) use a compressed channel lightweight network (C-GhostNet) to reduce the parameters of the whole model and (2) use an improved gate recurrent unit module (GRU-ECA) and C-GhostNet to process the video data and head movement data separately to improve the prediction accuracy. To evaluate the performance of our method, we conducted extensive experiments using an open VR user dataset. The experiments results demonstrate that our method achieves significant server resource saving, real-time performance, and high prediction accuracy, while achieving low bandwidth usage and low energy consumption in WVSN, which meets the requirement of live VR streaming.

Download Full-text

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

CASPIAN JOURNAL Control and High Technologies ◽

10.21672/2074-1707.2021.55.3.025-032 ◽

2021 ◽

Vol 55 (3) ◽

pp. 25-32

Author(s):

GERASKIN ALEKSEY S. ◽

◽

UKOLOV RODION V. ◽

Keyword(s):

Neural Network ◽

Video Compression ◽

High Accuracy ◽

Video Data ◽

Modern World ◽

Special Role ◽

Compression Algorithms ◽

Video File ◽

Software Product ◽

Research On Application

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.

Download Full-text