RESUMO

This article presents an approach to autonomous flight planning of Unmanned Aerial Vehicles (UAVs)-Drones as data collectors to the Internet of Things (IoT). We have proposed a model for only one aircraft, as well as for multiple ones. A clustering technique that extends the scope of the number of IoT devices (e.g., sensors) visited by UAVs is also addressed. The flight plan generated from the model focuses on preventing breakdowns due to a lack of battery charge to maximize the number of nodes visited. In addition to the drone autonomous flight planning, a data storage limitation aspect is also considered. We have presented the energy consumption of drones based on the aerodynamic characteristics of the type of aircraft. Simulations show the algorithm's behavior in generating routes, and the model is evaluated using a reliability metric.

RESUMO

In this research, we focus on the use of Unmanned Aerial Vehicles (UAVs) for the delivery of payloads and navigation towards safe-landing zones, specifically on the modeling of flight dynamics of lightweight vehicles denoted Precision Aerial Delivery Systems (PADSs). While a wide range of nonlinear models has been developed and tested on high-end applications considering various degrees of freedom (DOF), linear models suitable for low-cost applications have not been explored thoroughly. In this study, we propose and compare two linear models, a linearized version of a 6-DOF model specifically developed for micro-lightweight systems, and an alternative model based on a double integrator. Both linear models are implemented with a sensor fusion algorithm using a Kalman filter to estimate the position and attitude of PADSs, and their performance is compared to a nonlinear 6-DOF model. Simulation results demonstrate that both models, when incorporated into a Kalman filter estimation scheme, can determine the flight dynamics of PADSs during smooth flights. While it is validated that the double integrator model can adequately operate under the proposed estimation scheme for up to small acceleration changes, the linearized model proves to be capable of reproducing the nonlinear model characteristics even during moderately steep turns.

Assuntos

RESUMO

This study proposes and evaluates five deep fully convolutional networks (FCNs) for the semantic segmentation of a single tree species: SegNet, U-Net, FC-DenseNet, and two DeepLabv3+ variants. The performance of the FCN designs is evaluated experimentally in terms of classification accuracy and computational load. We also verify the benefits of fully connected conditional random fields (CRFs) as a post-processing step to improve the segmentation maps. The analysis is conducted on a set of images captured by an RGB camera aboard a UAV flying over an urban area. The dataset also contains a mask that indicates the occurrence of an endangered species called Dipteryx alata Vogel, also known as cumbaru, taken as the species to be identified. The experimental analysis shows the effectiveness of each design and reports average overall accuracy ranging from 88.9% to 96.7%, an F1-score between 87.0% and 96.1%, and IoU from 77.1% to 92.5%. We also realize that CRF consistently improves the performance, but at a high computational cost.

RESUMO

The use of Unmanned Aerial Vehicles (UAV) has been increasing over the last few years in many sorts of applications due mainly to the decreasing cost of this technology. One can see the use of the UAV in several civilian applications such as surveillance and search and rescue. Automatic detection of pedestrians in aerial images is a challenging task. The computing vision system must deal with many sources of variability in the aerial images captured with the UAV, e.g., low-resolution images of pedestrians, images captured at distinct angles due to the degrees of freedom that a UAV can move, the camera platform possibly experiencing some instability while the UAV flies, among others. In this work, we created and evaluated different implementations of Pattern Recognition Systems (PRS) aiming at the automatic detection of pedestrians in aerial images captured with multirotor UAV. The main goal is to assess the feasibility and suitability of distinct PRS implementations running on top of low-cost computing platforms, e.g., single-board computers such as the Raspberry Pi or regular laptops without a GPU. For that, we used four machine learning techniques in the feature extraction and classification steps, namely Haar cascade, LBP cascade, HOG + SVM and Convolutional Neural Networks (CNN). In order to improve the system performance (especially the processing time) and also to decrease the rate of false alarms, we applied the Saliency Map (SM) and Thermal Image Processing (TIP) within the segmentation and detection steps of the PRS. The classification results show the CNN to be the best technique with 99.7% accuracy, followed by HOG + SVM with 92.3%. In situations of partial occlusion, the CNN showed 71.1% sensitivity, which can be considered a good result in comparison with the current state-of-the-art, since part of the original image data is missing. As demonstrated in the experiments, by combining TIP with CNN, the PRS can process more than two frames per second (fps), whereas the PRS that combines TIP with HOG + SVM was able to process 100 fps. It is important to mention that our experiments show that a trade-off analysis must be performed during the design of a pedestrian detection PRS. The faster implementations lead to a decrease in the PRS accuracy. For instance, by using HOG + SVM with TIP, the PRS presented the best performance results, but the obtained accuracy was 35 percentage points lower than the CNN. The obtained results indicate that the best detection technique (i.e., the CNN) requires more computational resources to decrease the PRS computation time. Therefore, this work shows and discusses the pros/cons of each technique and trade-off situations, and hence, one can use such an analysis to improve and tailor the design of a PRS to detect pedestrians in aerial images.