Automatic Object Detection on Aerial Images Using Convolutional Neural Networks
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2021, Vol 9, Issue 6
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
- EP ID EP747143
- DOI 10.55524/ijircst.2021.9.6.63
- Views 53
- Downloads 0
Application of Artificial Intelligence in Educational Contexts for Teaching and Learning
Innovative educational technology have transformed teaching and learning techniques. Higher education has recently begun to incorporate new technology as artificial intelligence advances. The purpose of this conceptual r...
A Study on Ergonomics for Employee Wellness
The nature of work in modern society is changing rapidly, and competition in the job market is getting more intense. This requires competence from workers and demands them to update their knowledge, skills, and attitudes...
Stabilization of Black Cotton Soil Using Red Mud and Hydrated Lime
This research paper is an effort to use those materials which are disposed as wastes for stabilizing the soil and making the process cost effective. In this research work, two waste materials such as Red Mud and Hydrated...
Development of a Data Type Upgraded BIGINT to “INTCAL†Data Type in a RDBMS
Traditional Database Management System which only provide for primitive data types such as INTEGER and CHARACTER. The data types offered in commercial database systems, CHAR INTEGER NUMBER, VARCHAR, VARCHAR2(),are suffic...
Vehicle Number Plate Identification Using a Bi-Step Region Segmentation and Classification Technique
Vehicle number plate identification (VNPI) is an imperative task for resolving the increasing traffic issues around the world. Although many studies were conducted in the past, there are still many challenges to be answe...