UJRS A 2116566 Published

Computers, Materials & Continua

Recent trends in communication technologies and unmanned aerial vehicles (UAVs) find its application in several areas such as healthcare, surveillance, transportation, etc. Besides, the integration of Internet of things (IoT) with cloud computing environment offers several benefits for the UAV communication. At the same time, aerial scene classification is one of the major research areas in UAV-enabled MEC systems. In UAV aerial imagery, efficient image representation is crucial for the purpose of scene classification. The existing scene classification techniques generate mid-level image features with limited representation capabilities that often end up in producing average results. Therefore, the current research work introduces a new DL-enabled aerial scene classification model for UAV-enabled MEC systems. The presented model enables the UAVs to capture aerial images which are then transmitted to MEC for further processing. Next, Capsule Network (CapsNet)-based feature extraction technique is applied to derive a set of useful feature vectors from the aerial image. It is important to have an appropriate hyperparameter tuning strategy, since manual parameter tuning of DL model tend to produce several configuration errors. In order to achieve this and to determine the hyperparameters of CapsNet model, Shuffled Shepherd Optimization (SSO) algorithm is implemented. Finally, Backpropagation Neural Network (BPNN) classification model is applied to determine the appropriate class labels of aerial images. The performance of SSO-CapsNet model was validated against two openly-accessible datasets namely, UC Merced (UCM) Land Use dataset and WHU-RS dataset. The proposed SSO-CapsNet model outperformed the existing state-of-the-art methods and achieved maximum accuracy of 0.983, precision of 0.985, recall of 0.982, and F-score of 0.983.

2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), 2023

Abstract—Object detection in unmanned aerial vehicle (UAV) images becomes a persistent problem in the domain of computer vision. Particularly, object detection in drone images is a difficult process because of the object of different scales namely, hills, buildings, and water bodies. The study presents an execution of ensemble transfer learning to improve the efficiency of the fundamental model for multi-scale object recognition in drone imagery. This study develops an Optimal Deep Learning Enabled Object Detection and Classification on Drone Imagery (ODLODCDI) technique. The presented ODL-ODCDI technique can recognize and classify the objects present in the images collected by the drones. It follows a two stage process. In the first level, the ODL-ODCDI technique employed YOLO-v5 as object detector with Nadam optimizer. Next, in the latter level, the ODL-ODCDI technique makes use of random forest (RF) classifier to identify objects in the drone images. To establish the enhanced performance of the ODL-ODCDI approach, a series of experiments were performed. The experimental values depicted the improved outcomes of the ODL-ODCDI method over other DL models

The Journal of Supercomputing

This paper compares the classification performance of machine learning classifiers vs. deep learning-based handcrafted models and various pretrained deep networks. The proposed study performs a comprehensive analysis of object classification techniques implemented on low-altitude UAV datasets using various machine and deep learning models. Multiple UAV object classification is performed through widely deployed machine learning-based classifiers such as K nearest neighbor, decision trees, naïve Bayes, random forest, a deep handcrafted model based on convolutional layers, and pretrained deep models. The best result obtained using random forest classifiers on the UAV dataset is 90%. The handcrafted deep model's accuracy score suggests the efficacy of deep models over machine learning-based classifiers in low-altitude aerial images. This model attains 92.48% accuracy, which is a significant improvement over machine learning-based classifiers. Thereafter, we analyze several pretrained deep learning models, such as VGG-D, InceptionV3, DenseNet, Inception-ResNetV4, and Xception. The experimental assessment demonstrates nearly 100% accuracy values using pretrained VGG16-and VGG19-based deep networks. This paper provides a compilation of machine learning-based classifiers and pretrained deep learning models and a comprehensive classification report for the respective performance measures.

Journal of Scientific and Industrial Research (JSIR), 2020

The advent of computer vision and evolution of high-end computing in remote sensing images have embellish various researchers for unprecedented development in remotely sensed aerial images. The requirement to extract essential information stimulated anatomization of aerial images for its usefulness. Deep learning provides state of the art solutions for widely explored visual recognition system and has emerged as an evolutionary area, being applicable to large scale image processing applications. Convolutional Neural Networks (CNNs), an essential component of deep learning algorithms consists of increasing the depth and connections in the processing layers to learn various features of data at different abstract levels. In this paper, we present an outlook for classifying and extracting the features of aerial images using CNN. We propose a CNN architecture based on various parameters and layers for classification. CNN has been evaluated on two publicly available aerial data sets: UC Merced Land Use and RSSCN7. Experimental results show that the proposed CNN architecture is competent and efficient in terms of accuracy as performance evaluation parameter in comparison with conventional classifiers like Bag of Visual Words (BOVW).

IEEE Access

Recently, the increase in inexpensive and compact unmanned aerial vehicles (UAVs) and lightweight 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. INDEX TERMS Unmanned aerial vehicle, particle swarm optimization, deep learning, convolutional neural networks, machine learning, internet of everything, aerial images, smart environment. I. INTRODUCTION Recently 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 .

AIP Conference Proceedings

Unmanned Aerial Vehicles (UAVs) have been found to have many uses in the maintenance and oversight of civil infrastructure assets. They contribute to scheduled bridge checkups, crisis control, electricity transmission cable oversight and traffic analysis. With more and more uses of UAVs being introduced, a greater focus on individuality and freedom regarding governance of these devices is required to ensure security, competency, and precision. The subject of this study outlines the method and policies to be followed for teaching the principals of the (efficient Neural Network) ENet architecture, machine learning, and using OpenCV to implement semantic segmentation on a collection of images obtained through aerial photography for identification of objects. Possible utilizations of UAVs in the area of transportation are mentioned as well along with the precision and efficiency of training for the application of the ENet architecture, machine learning, and OpenCV to implement semantic segmentation, the optimization selection of operational parameters, and the machine learning and ENet architecture teaching methods and policies drafting process. Through analysis of the object identification results, it was proven that by adhering to a specific set of parameters, the ENet architecture and machine learning procedures can successfully identify objects with an accuracy of 99% when there is no distortion. In addition, using a combination of all three technologies mentioned, it is possible to not only classify objects, but the device is also capable of automated tracking and detection of the objects by real-time processing of streamed videos by the UAVs. The novelty, that the ENET was applied for large class members difference distance among the same objects family.

IEEE, 2024

The use of Unmanned Aerial Vehicles (UAVs) equipped with classification systems in Search and Rescue missions has increasingly shown great application potential. There are however pratical concerns regarding limited embedded computing power and adapting the classifier performance to the characteristics of a specific mission. The UAVs may acquire a large number of images during a mission and it is difficult for humans to search throughout this material. For this matter, we study the performance of a leaner Convolutional Neural Network model to select images with salient objects and present a tool that can help in decision making regarding the definition of the classification threshold through the analysis of possible operational impacts and consequences of eventual detection errors. We also show that, in this application, Data Augmentation is important to improve the classifier performance.

Floods are one of the most fatal and devastating disasters, instigating an immense loss of human lives and damage to property, infrastructure, and agricultural lands. To cater to this, there is a need to develop and implement real-time flood management systems that could instantly detect flooded regions to initiate relief activities as early as possible. Current imaging systems, relying on satellites, have demonstrated low accuracy and delayed response, making them unreliable and impractical to be used in emergency responses to natural disasters such as flooding. This research employs Unmanned Aerial Vehicles (UAVs) to develop an automated imaging system that can identify inundated areas from aerial images. The Haar cascade classifier was explored in the case study to detect landmarks such as roads and buildings from the aerial images captured by UAVs and identify flooded areas. The extracted landmarks are added to the training dataset that is used to train a deep learning algorithm. Experimental results show that buildings and roads can be detected from the images with 91% and 94% accuracy, respectively. The overall accuracy of 91% is recorded in classifying flooded and non-flooded regions from the input case study images. The system has shown promising results on test images belonging to both pre- and post-flood classes. The flood relief and rescue workers can quickly locate flooded regions and rescue stranded people using this system. Such real-time flood inundation systems will help transform the disaster management systems in line with modern smart cities initiatives.

Applied Sciences

Environment classification is one of the most critical tasks for Unmanned Aerial Vehicles (UAV). Since water accumulation may destabilize UAV, clouds must be detected and avoided. In a previous work presented by the authors, Superpixel Segmentation (SPS) descriptors with low computational cost are used to classify ground, sky, and clouds. In this paper, an enhanced approach to classify the environment in those three classes is presented. The proposed scheme consists of a Convolutional Neural Network (CNN) trained with a dataset generated by both, an human expert and a Support Vector Machine (SVM) to capture context and precise localization. The advantage of using this approach is that the CNN classifies each pixel, instead of a cluster like in SPS, which improves the resolution of the classification, also, is less tedious for the human expert to generate a few training samples instead of the normal amount that it is required. This proposal is implemented for images obtained from vid...

2021 International Wireless Communications and Mobile Computing (IWCMC), 2021

Unmanned Aerial Vehicles (UAVs) have recently attracted significant attention due to their outstanding ability to be used in different sectors and serve in difficult and dangerous areas. Moreover, the advancements in computer vision and artificial intelligence have increased the use of UAVs in various applications and solutions, such as forest fires detection and borders monitoring. However, using deep neural networks (DNNs) with UAVs introduces several challenges of processing deeper networks and complex models, which restricts their on-board computation. In this work, we present a strategy aiming at distributing inference requests to a swarm of resourceconstrained UAVs that classifies captured images on-board and finds the minimum decision-making latency. We formulate the model as an optimization problem that minimizes the latency between acquiring images and making the final decisions. The formulated optimization solution is an NP-hard problem. Hence it is not adequate for online resource allocation. Therefore, we introduce an online heuristic solution, namely DistInference, to find the layers placement strategy that gives the best latency among the available UAVs. The proposed approach is general enough to be used for different low decision-latency applications as well as for all CNN types organized into pipeline of layers (e.g., VGG) or based on residual blocks (e.g., ResNet).