Detection and Classification of Vehicles in Ultra-High Resolution Images Using Neural Networks

被引：0

作者：

Chen, Ch ^{[1
,2
]}

Minald, A. A. ^{[3
]}

Bohush, R. P. ^{[4
]}

Ma, G. ^{[5
]}

Weichen, Y. ^{[5
]}

Ablameyko, S., V ^{[3
,6
]}

机构：

[1] Zhejiang Shuren Univ, Sch Informat Sci & Technol, Hangzhou, Peoples R China

[2] Int Sci & Technol Cooperat Base Zhejiang Prov Rem, Hangzhou, Peoples R China

[3] Belarusian State Univ, Minsk, BELARUS

[4] Polotsk State Univ, Novopolotsk, BELARUS

[5] EarthView Image Inc, Huzhou, Peoples R China

[6] Natl Acad Sci Belarus, United Inst Informat Problems, Minsk, BELARUS

来源：

JOURNAL OF APPLIED SPECTROSCOPY | 2022年 / 89卷 / 02期

关键词：

detection and classification of objects; images of the earth's surface; ultrahigh resolution images; neural network;

D O I：

10.1007/s10812-022-01361-1

中图分类号：

O433 [光谱学];

学科分类号：

0703 ; 070302 ;

摘要：

A deep neural network architecture is proposed based on integrating the convolutional neural network Faster R-CNN with the Feature Pyramid Network module. Based on this approach, an algorithm is developed for detecting and classifying transport media in images along with a corresponding model. The cross-platform medium ML.NET is used to teach the proposed model. Results of comparing the effectiveness of the application of the proposed approach and the convolutional neural networks YOLO v4 and Faster R-CNN are presented. An improved accuracy of detection and localization of different types of vehicles in ultra-high resolution images is demonstrated. Examples of the processing of images of the earth's surface in ultra-high resolution are given, along with corresponding recommendations.

引用

页码：322 / 329

页数：8

共 50 条

[1] Detection and Classification of Vehicles in Ultra-High Resolution Images Using Neural Networks
Ch. Chen
А. А. Мinald
R. P. Bohush
G. Ma
Y. Weichen
S. V. Аblameyko
Journal of Applied Spectroscopy, 2022, 89 : 322 - 329
[2] Ultra-high resolution images NANOTECHNOLOGY
Donaldson, Laurie
MATERIALS TODAY, 2012, 15 (10) : 429 - 429
[3] SCENE CLASSIFICATION OF HIGH RESOLUTION REMOTE SENSING IMAGES USING CONVOLUTIONAL NEURAL NETWORKS
Cheng, Gong
Ma, Chengcheng
Zhou, Peicheng
Yao, Xiwen
Han, Junwei
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 767 - 770
[4] Plant drought impact detection using ultra-high spatial resolution hyperspectral images and machine learning
Dao, Phuong D.
He, Yuhong
Proctor, Cameron
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2021, 102
[5] Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks
Lim, Kyungsun
Jin, Dongkwon
Kim, Chang-Su
2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 509 - 515
[6] Classification of Low Resolution Astronomical Images using Convolutional Neural Networks
Patil, Jyoti S.
Pawase, Ravindra S.
Dandawate, Y. H.
2017 2ND IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), 2017, : 1168 - 1172
[7] Use of neural networks for automatic classification from high-resolution images
Del Frate, Fabio
Pacifici, Fabio
Schiavon, Giovanni
Solimini, Chiara
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (04): : 800 - 809
[8] Very High Resolution Images Classification by Fusing Deep Convolutional Neural Networks
Iftene, Meziane
Liu, Qingjie
Wang, Yunhong
5TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE APPLICATIONS AND TECHNOLOGIES (ACSAT 2017), 2017, : 172 - 176
[9] Road detection from high-resolution satellite images using artificial neural networks
Mokhtarzade, M.
Zoej, M. J. Valadan
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2007, 9 (01): : 32 - 40
[10] Spectral invariants in ultra-high spatial resolution hyperspectral images
Ihalainen, Olli
Mõttus, Matti
Journal of Quantitative Spectroscopy and Radiative Transfer, 2022, 288

← 1 2 3 4 5 →