Automatic Object Detection on Aerial Images Using Convolutional Neural Networks

Abstract

Large quantities of aerial and satellite images are being acquired on a daily basis. Many practical applications may benefit from the analysis of such huge amounts of data. We propose an automated content-based analysis of aerial photography in this letter, which may be used to identify and label arbitrary objects or areas in high-resolution pictures. We developed a convolutional neural network-based approach for automated object identification for this purpose. In the tasks of aerial picture classification and object identification, a new two-stage method for network training is developed and validated. First, we used the UC Merced data set of aerial pictures to evaluate the suggested training method, and we were able to obtain an accuracy of about 98.6%. Second, a technique for automatically detecting objects was developed and tested. For GPGPU implementation, a processing time of approximately 30 seconds was needed for one aerial picture of size 5000 x 5000 pixels.

Authors and Affiliations

Jasdeep Singh

Keywords

Related Articles

A Review on Black Hole Detection on Mobile Ad-hoc Network

MANET is a network with unrestricted mobility in nature and no centralised control. Mobile node can move from one network to another frequently. MANET is infrastructure less so any node can enter and exit the system at a...

Text Extraction from Document Images Using Gabor, Wavelet and Hough Technique: A Novel Approach

Text extraction in document images has been an important research area. Extraction of the information in the form of text involves detection, localization, tracking, extraction, enhancement, and recognition of the text f...

Review of Speech Recognition System

This paper takes a tour of speech recognition system which includes it’s evaluation and accuracy of system and discuss the structure of utterance that uses the vocal tract to make the utterance. Dynamic warping with its...

A New Approach for Task Scheduling of Cloud Computing Using Fuzzy

Cloud Computing is the distributed computing on internet or delivery of computing services over the internet. Cloud computing involves deploying groups of remote servers and software networks that allow centralized data...

Design and Analysis of Composite Propeller Blade for Aircraft

The work in this paper primarily focuses on the modelling and analysis of a plane's propeller blade for strength. The geometry of a propeller blade is a sophisticated 3D model. CATIA V5 R20 is utilised to generate the bl...

Download PDF file
  • EP ID EP747143
  • DOI 10.55524/ijircst.2021.9.6.63
  • Views 54
  • Downloads 0

How To Cite

Jasdeep Singh (2021). Automatic Object Detection on Aerial Images Using Convolutional Neural Networks. International Journal of Innovative Research in Computer Science and Technology, 9(6), -. https://europub.co.uk/articles/-A-747143