Indoor Localization and Navigation based on Deep Learning using a Monocular Visual System

被引：0

作者：

Ancona R.E.A. ^{[1
]}

Ramírez L.G.C. ^{[1
]}

Frías O.O.G. ^{[1
]}

机构：

[1] UPIITA-IPN SEPI Section, Instituto Politécnico Nacional, Mexico City

来源：

International Journal of Advanced Computer Science and Applications | 2021年 / 12卷 / 06期

关键词：

autonomous navigation; feature extractor; object detection; Visual localization; visual navigation;

D O I：

10.14569/IJACSA.2021.0120611

中图分类号：

学科分类号：

摘要：

Now-a-days, computer systems are important for artificial vision systems to analyze the acquired data to realize crucial tasks, such as localization and navigation. For successful navigation, the robot must interpret the acquired data and determine its position to decide how to move through the environment. This paper proposes an indoor mobile robot visual-localization and navigation approach for autonomous navigation. A convolutional neural network and background modeling are used to locate the system in the environment. Object detection is based on copy-move detection, an image forensic technique, extracting features from the image to identify similar regions. An adaptive threshold is proposed due to the illumination changes. The detected object is classified to evade it using a control deep neural network. A U-Net model is implemented to track the path trajectory. The experiment results were obtained from real data, proving the efficiency of the proposed algorithm. The adaptive threshold solves illumination variation issues for object detection. © 2021

引用

页码：79 / 86

页数：7

共 47 条

[31]

Alanis A., Arana N., Lopez C., Guevara Reyes E., Integration of an inverse Optimal Neural Controller with Reinforced SLAM for Path Planning and Mapping in Dynamic Environments, Computación y Sistemas, 19, 3, pp. 445-456, (2015)

[32]

Kermani, Asemani, A Robust Adaptive Algorithm of Movibng Object Detection for Video Surveillance, Journal on Image and Video Processing, 1, 127, pp. 2-9, (2014)

[33]

Mushtaq, Mir, Copy-Move Detection Using Gray Level Run Length Matrix Features, Optical and Wireless Technologies, 472, pp. 411-420, (2018)

[34]

Kuznetsov, Myasnikov, A Copy-Move Detection Algorithm Using Binary Gradient Contours, International Conference on Image Analysis and Recognition, 9730, pp. 349-357, (2016)

[35]

Ghorbani Firouzmand, Faraahi, DWT-DCT (QCD) Based Copy-move Image Forgery, 2011 18th International Conference on Systems, Signals and Image Processing, (2011)

[36]

Yuan Rao J. N., A Deep Learning Approach to Detection of Splicing and Copy move Forgeries in Images, IEEE International Workshop on Information Forensics and Security, (2016)

[37]

Wu Y., Abd-Almageed W., Natarajan P., Deep Matching and Validation Network An end to end to constrained Image Splicing Localization and Detection, IEEE Computer Vision and Pattern Recognition, pp. 1480-1489, (2017)

[38]

Ashwini Malviya S. L., Pixel based Image Forensic Technique for copy-move forgery, 7th International Conference on Communication Computing and Virtualization 2016, 79, pp. 383-390, (2016)

[39]

Wang X., Zhang X., Li Z., Wang S., A DWT-DCT Based Passive Forensics Method for Copy-move Attacks, Third Conference on Multimedia Information Networking and Security, (2011)

[40]

Harris, Pike, 3D Positional integration from image sequences, Image and Vision Computing, 6, 2, pp. 97-90, (1988)

← 1 2 3 4 5 →