An Approach for Aircraft Detection using VGG19 and OCSVM

Abstract

Aircraft detection is an essential and noteworthy area of object detection that has received significant interest from scholars, especially with the progress of deep learning techniques. Aircraft detection is now extensively employed in various civil and military domains. Automated aircraft detection systems play a crucial role in preventing crashes, controlling airspace, and improving aviation traffic and safety on a civil scale. In the context of military operations, detection systems play a crucial role in quickly locating aircraft for surveillance purposes, enabling decisive military strategies in real time. This article proposes a system that accurately detects airplanes independent of their type, model, size, and color variations. However, the diversity of aircraft images, including variations in size, illumination, resolution, and other visual factors, poses challenges to detection performance. As a result, an aircraft detection system must be designed to distinguish airplanes clearly without affecting the aircraft’s position, rotation, or visibility. The methodology involves three significant steps: feature extraction, detection, and evaluation. Firstly, deep features will be extracted using a pre-trained VGG19 model and transfer learning principle. Subsequently, the extracted feature vectors are employed in One Class Support Vector Machine (OCSVM) for detection purposes. Finally, the results are assessed using evaluation criteria to ensure the effectiveness and accuracy of the proposed system. The experimental evaluations were conducted across three distinct datasets: Caltech-101, Military dataset, and MTARSI dataset. Furthermore, the study compares its experimental results with those of comparable publications released in the past three years. The findings illustrate the efficacy of the proposed approach, achieving F1-scores of 96% on the Caltech-101 dataset and 99% on both Military and MTARSI datasets.