Abstract
Recently, the increase in inexpensive and compact unmanned aerial vehicles (UAVs) and light-weight imaging sensors has led to an interest in using them in various remote sensing applications. The processes of collecting, calibrating, registering, and processing data from miniature UAVs and interpreting the data semantically are time-consuming. In UAV aerial imagery, learning effective image representations is central to the scene classification process. Earlier approaches to the scene classification process depended on feature coding methods with low-level hand-engineered features or unsupervised feature learning. These methods could produce mid-level image features with restricted representational abilities, which generally yielded mediocre results. The development of convolutional neural networks (CNNs) has made image classification more efficient. Due to the limited resources in UAVs, it is hard to fine-tune the hyperparameters and the trade-offs between classifier results and computation complexity. This paper introduces a new multi-objective optimization model for evolving state-of-the-art deep CNNs for scene classification, which generates the non-dominant solutions in an automated way at the Pareto front. We use a set of two benchmark datasets to test the performance of the scene classification model and make a detailed comparative study. The proposed method attains a very low computational time of 80 sec and maximum accuracy of 97.88% compared to all other methods. The proposed method is found to be appropriate for the effective scene classification of images captured by UAVs.
Highlights
There has been a lot of interest in autonomous unmanned aerial vehicles (UAVs) and their applications, which include search-and-rescue, surveillance and reconnaissance, and examination of infrastructure [1], [2].The associate editor coordinating the review of this manuscript and approving it for publication was Moayad Aloqaily .Landcover classification is a significant element of UAV applications, and it is difficult to build entirely autonomous systems
This work introduces a new multi-objective particle swarm optimization (MOPSO) model for evolving state-of-the-art deep convolutional neural networks (CNNs) in scene classification that generates the non-dominant solutions in an automated way at the Pareto front
THE PROPOSED METHOD This paper proposes a technique of the MOPSO algorithm to manage a trade-off between the inference latency and classification accuracy that is known as multiobjective CNN (MOCNN)
Summary
There has been a lot of interest in autonomous unmanned aerial vehicles (UAVs) and their applications, which include search-and-rescue, surveillance and reconnaissance, and examination of infrastructure [1], [2]. Deep learning (DL) techniques [13], [14] have been very useful for solving conventional problems like object detection and recognition, natural language processing, and speech recognition, and in numerous real-time applications. This work introduces a new multi-objective particle swarm optimization (MOPSO) model for evolving state-of-the-art deep CNNs in scene classification that generates the non-dominant solutions in an automated way at the Pareto front. This method helps to achieve a trade-off between the inference latency and classification accuracy, known as multiobjective CNN (MOCNN).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.