Detection and Classification of Objects in Satellite Images using Custom CNN
Deepthi S, Sandeep Kumar, Dr. Suresh L. · Zenodo (CERN European Organization for Nuclear Research) · 2021
Satellite image analysis is being increasingly used for many applications like surveillance, military, geo-spatial surveys and environmental impacts and change monitoring. Automatic detection and classification of objects is an important functionality of satellite image analysis. Due to the nature and size of objects and the varied visual features, it becomes challenging to detect and classify objects in aerial images. Manual detection of objects in these images is very time-consuming due to the nature and that data captured in these images. It is desirable to automate the detection of various features or objects from these satellite images. The conventional methods for object classification involve two stages: (i) identify the regions with object presence in the image and (ii) classify the objects in the regions. Additionally, detection of objects becomes challenging in presence of complexities in background, size, noise, and distance parameters. This work proposes a customized convolutional neural network to detect and classify three different objects such as trees, building and cars in the images. It also aims to understand and outline briefly the performance characteristics of the considered custom CNN.