Aghila Rajagopal

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.

Summary Due to the significant utilization of terrestrial communication, Low Earth Orbit (LEO) satellite network is a critical part of satellite communication networks owing to its several benefits. But the efficient and trustworthy routing for LEO satellite networks (LSNs) is a difficult process because of dynamic topology, adequate link changes, and imbalanced communication load. This study devises a new hybridization of extreme learning machine (ELM) with multitask beetle antennae search (MBAS) algorithm‐based distributed routing called the MBAS‐ELM model. The proposed model determines the routes based on traffic forecasting with respect to the level of traffic circulation on the earth. The proposed method is employed for traffic forecasting at the satellite nodes (SNs). To identify the optimal routes, mobile agents (MAs) are applied to concurrently and autonomously determine for LSNs and make a decision on routing data. The experimental outcome has showcased the effective performance of the proposed model over the compared models in terms of different measures, namely, average delay, packet loss ratio (PLR), and queuing delay. The results are validated under varying simulation time and data sensing rates. The obtained outcome pointed out the superior performance of the proposed MBAS‐ELM model compared with other methods.

In recent days, unmanned aerial vehicles (UAVs) becomes more familiar because of its versatility, automation abilities, and low cost. Dynamic scene classification gained significant interest among the UAV-based surveillance systems, e.g., high-voltage power line and forest fire monitoring, which facilitate the object detection, tracking process and drastically enhances the outcome of visual surveillance. This paper proposes a new optimal deep learning-based scene classification model captured by UAVs. The proposed model involves a residual network-based features extraction (RNBFE) which extracts features from the diverse convolution layers of a deep residual network. In addition, the several parameters in RNBFE lead to many configuration errors due to manual parameter tuning. So, self-adaptive global best harmony search (SGHS) algorithm is employed for tuning the parameters of the RNBFE. The resultant feature vectors undergo classification by the use of latent variable support vector machine (LVSVM) model. The presented optimal RNBFE (ORNBFE) model has been tested using two open access datasets namely UC Merced (UCM) Land Use Dataset and WHU-RS Dataset. The presented technique attains maximum scene classification accuracy over the other recently proposed methods.

Object classification based on shape features for video surveillance has been a research problem for number of years. The object classification accuracy depends on the type of classifier and the extracted object features used for classification. Excellent classification accuracy can be obtained with an appropriate combination of the extracted features with a particular classifier. In this paper, we propose to use an online feature selection method which gives a good subset of features while the machine learns the classification task and use these selected features for object classification. This paper also explores the impact of different kinds of shape features on the object classification accuracy and the performance of different classifiers in a typical automated video surveillance application.