CNN BASED REALTIME AIRCRAFT DETECTION

Abstract

Deep learning techniques such as Convolutional Neural Networks (CNN) and Transfer Learning are being used to detect and identify fighter aircraft or jets in a dataset consisting of 21 different aircraft with 20,000 images. The principle of "pooling" in Convolutional Neural Networks (CNN) involves progressively reducing the spatial size of the model to decrease the number of parameters and computations in the network. These techniques have been applied to various aspects of aircraft recognition, including object detection and engine defect detection. Convolutional Neural Networks (CNNs) are widely employed in various domains, including defence, agriculture, business, and face recognition technology, for image detection tasks. Transfer learning is a machine learning method that involves using a pre-trained model as the initial point for a new task, allowing for faster training and improved performance. This technique is particularly useful in deep learning, where large amounts of data are required for training complex models. The dataset is processed using Python libraries such as pandas, seaborn, and sci-kit-learn to find pre-trained patterns and insights. The data is then split into training and testing datasets, with 80% and 20% of the total data, respectively. A model is built using the TensorFlow library for CNN, and the metric used is "accuracy". Additionally, a transfer learning model is built to compare the accuracy results and adopt the best-fitting one. Keywords: Convolutional Neural Network, Deep Learning, Artificial Neural Network, Support Vector Machines.