UAV-Based Real-Time Survivor Detection System in Post-Disaster Search and Rescue Operations

When a natural disaster occurs, the most critical task is to search and rescue trapped people as soon as possible. In recent years, unmanned aerial vehicles (UAVs) have been widely employed because of their high durability, low cost, ease of implementation, and flexibility. In this article, we collected a new thermal image dataset captured by drones. After that, we used several different deep convolutional neural networks to train survivor detection models on our dataset, including YOLOV3, YOLOV3-MobileNetV1, and YOLOV3- MobileNetV3. Due to the limited computing power and memory of the onboard microcomputer, to balance the inference time and accuracy, we found the optimal points to prune and fine-tune the survivor detection network based on the sensitivity of the convolutional layer. We verified it on NVIDIA’s Jetson TX2 and achieved a real-time performance of 26.60 frames/s (FPS). Moreover, we designed a real-time survivor detection system based on DJI Matrice 210 and Manifold 2-G to provide search and rescue services after the disaster.

For more about this article see link below.

Design of Magnetorquer-Based Attitude Control Subsystem for FORESAIL-1 Satellite

The magnetorquer-based attitude control system capable of attaining high spin rates and precise pointing control is required for a 3U CubeSat satellite FORESAIL-1. The satellite, developed by the Finnish Centre of Excellence, needs to maintain a spin rate of 24°/s and precise pointing of the spin axis toward the Sun for the particle telescope instrument, as well as to reach 130°/s spin rate for the deployment of the plasma brake. Mission requirements analysis and attitude system requirements derivation are presented, followed by actuator tradeoff and selection, with a detailed design of the complete attitude control system, including the air-cored type of magnetorquer actuators and their drivers, made of H-bridge and filtering components. The design is based on several theoretical and practical considerations with emphasis on the high-power efficiency, such as effects of parallel and serial magnetorquer connections, modeling the magnetorquers with equivalent circuit models for finding a suitable driving frequency and extrapolation methods for efficient dipole moment usage. The in-house manufacturing process of magnetorquers, using a custom 3-D-printer setup, is described. Finally, the testing and verification are performed, by measuring the performance of the manufactured hardware, circuit simulations, and attitude control simulations. It is shown that the manufactured attitude control system fulfills all system requirements. Simulations also confirm the capability to satisfy mission requirements.

For more about this transaction see link below.

A Review of Spatiotemporal Super-Resolution Mapping for Remote Sensing Data Fusion

Presently, due to the limitations of satellite launch cost and existing technology, it is scarcely possible to obtain single remotely sensed images with both fine-spatial resolution and high temporal resolution at the same time freely. For solving this kind of predicament, an effective method is to fuse multisource remote sensing data by using spatial–temporal super-resolution mapping (STSRM) algorithms. STSRM is developed on the foundation of super-resolution mapping (SRM), which is used for generating land-cover map with a finer spatial resolution by allocating subpixels position in the mixed pixels of coarse remotely sensed images. This review summarizes the existing mainstream models of spatiotemporal SRM and concludes the advantages and limitations of these methods. At the same time, this article analyzes methods of classification accuracy assessment, expounds the existing problems and challenges, and makes a forward-looking prospect for the future development direction of spatiotemporal SRM.

For more about this article see link below.

Object Detection for Unmanned Aerial Vehicle Camera via Convolutional Neural Networks

The object tracking alongside the image segmentation have recently become a particular significance in satellite and aerial imagery. The latest achievements in this field are closely related to the application of the deep-learning algorithms and, particularly, convolutional neural networks (CNNs). Supplemented by the sufficient amount of the training data, CNNs provide the advantageous performance in comparison to the classical methods based on Viola-Jones or support vector machines. However, the application of CNNs for the object detection on the aerial images faces several general issues that cause classification error. The first one is related to the limited camera shooting angle and spatial resolution. The second one arises from the restricted dataset for specific classes of objects that rarely appear in the captured data. This article represents a comparative study on the effectiveness of different deep neural networks for detection of the objects with similar patterns on the images within a limited amount of the pretrained datasets. It has been revealed that YOLO ver. 3 network enables better accuracy and faster analysis than region convolution neural network (R-CNN), Fast R-CNN, Faster R-CNN, and SSD architectures. This has been demonstrated on the example of “Stanford dataset,” “DOTA v-1.5,” and “xView 2018 Detection” datasets. The following metrics on the accuracy have been obtained for the YOLO ver. 3 network: 89.12 mAP (Stanford dataset), 80.20 mAP (DOTA v-1.5), and 78.29 (xView 2018) for testing; and 85.51 mAP (Stanford dataset), 79.28 (DOTA v-1.5), and 79.92 (xView 2018) on validation with the analysis speed of 26.82 frames/s.

For more about this article see link below.

Software-Defined Radios for CubeSat Applications: A Brief Review and Methodology

CubeSats have revolutionized the way scientists and students perceive space. The majority of CubeSat communication is greatly limited by the AX.25 standards, the small communication window, the available transmission power, and the available bandwidth at VHF/UHF band. As a result, CubeSat radios could only establish low data rate links which restrict the communication capabilities of a CubeSat mission. In this article, a brief review of current software-defined radios (SDRs) used in space missions is given. In addition, two different design methodologies for SDRs for CubeSats are proposed that can be used as a guideline for CubeSat developers. Finally, a high data rate SDR for the UOW CubeSat project is presented that address all the above limitations. The radio operates at S-band, employs quadrature amplitude modulation with a maximum data rate of 60 Mb/s consuming 2.6 Watts in transmit mode and 0.4 Watts in receive mode. The digital signal processing functions and the mode control of the radio are orchestrated by a field programmable gate array system-on-chip. The analog radio frequency domain is accommodated by a 4-layer printed circuit board with dimensions of 92 mm × 88 mm. The goal of the UOW CubeSat radio is an adaptive, on-flight reconfigurable communication platform that will revolutionize the current communication capabilities of the CubeSats and expand nanosatellites mission perspectives.

For more about this article see link below.