Convolutional neural networks

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

by

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. 

https://ieeexplore.ieee.org/document/9440534

Object Detection for Unmanned Aerial Vehicle Camera via Convolutional Neural Networks

by

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. 

https://ieeexplore.ieee.org/document/9273062