A Simulated Dataset in Aerial Images using Simulink for Object Detection and Recognition

Abstract

The understanding and implementation of object detection and classification algorithms help in deploying diverse applications of UAVs. There is a need for a simulated UAV dataset to incorporate a pipeline for various algorithms. To reduce human efforts, multiple simulators have been utilized to mimic the real-time behavior of drones. Our work inspired simulators and can be considered by engineering students to create a dataset in a simulated environment. In this paper, we focused on the study of MATLAB-based Simulink through multiple environment settings. The core objective of the paper is to create a simulated dataset from the utilized quadcopter-based flight control model in MATLAB-based Simulink. In this customized model, few modifications have been made to obtain drone videos to detect object categories such as pedestrians, other drones and obstacles while navigating in a simulated environment. Additionally, these simulated images are annotated for aerial image interpretation with multiple object categories. The dataset is annotated and is freely downloadable from: https://bit.ly/38jlAsh. In this research study, we mainly focus on the process of drone simulation in the MATLAB-based Simulink model. Further, the captured dataset is verified on state-of-the-art object detectors such as YoloV3, TinyYolov3 etc. by evaluating the authenticity of the dataset.

Keywords

• UAV Simulator
• Object detection
• Simulated dataset
• Computer vision
• Deep learning