Search

The overlap between edge computing and unmanned aerial systems enables Unmanned Aerial Vehicles (UAV) to quickly offload image processing tasks onto edge devices, avoiding the transmission of images over long distances. To improve the speed and efficiency of UAV image stitching in an edge computing environment, this paper proposes an adaptive UAV image parallel stitching algorithm in an edge computing environment. The algorithm incorporates both route-based parallel processing and inverted binary tree-based parallel processing, dividing the image stitching task into multiple processes and allocating them to different cores based on the CPU core count, number of flight routes, and number of images, thereby enhancing computational efficiency in edge scenarios. The experimental results indicate that, when the number of flight routes is greater than or equal to the number of CPUs, the adaptive algorithm will employ the more efficient route parallelism. Conversely, when the number of flight routes is less than the number of CPUs, the efficiency of inverted binary tree parallelism is higher. In the same experimental environment and dataset, the adaptive image stitching algorithm demonstrates an efficiency improvement of approximately 2–10 times compared to other algorithms, with no significant degradation in image quality. This demonstrates that in edge environments, the utilization of multi-threaded adaptive route and inverted binary tree-based parallel approaches can effectively harness the computing resources of edge devices, significantly improving the stitching speed of UAV images and providing technical support for rapid real-time monitoring by UAV. [ABSTRACT FROM AUTHOR]

Automatic target recognition and detection in synthetic aperture radar (SAR) images is playing a significant role in military and civilian fields. Traditional methods are weak in migration capabilities and cumbersome in manual design. Existing deep learning-based methods can achieve high recognition and detection accuracy, but most of them have a very large number of parameters and slow recognition and computational efficiency, which makes it difficult for them to migrate to edge computing equipments, and computational efficiency is crucial in rapid maritime rescue and emergency military deployment. Therefore, we propose a lightweight feature extraction block, lightweight split concat block (LSCB), for SAR automatic target recognition and detection. Specifically, LSCB consists of several operators, such as split, depthwise convolution (DC), multiple kernel sizes block (MKSB), and channel-shuffle (CS). MKSB is a novel channel attention mechanism designed by us, which can make feature maps have target features of different scales and adjust their receptive field sizes adaptively. In addition, to assess the performance of LSCB, we use LSCB to build LSCNet-R and LSCNet-D for SAR target recognition and detection, respectively, and conduct extensive experiments on MSTAR, SSDD, and SAR-Ship-Dataset. The experimental results show that our LSCNet-R and LSCNet-D built with LSCB achieve higher recognition and detection accuracy and computational efficiency with few parameters compared with existing excellent methods. This further illustrates that the proposed LSCB can extract fine and stable features with few parameters. [ABSTRACT FROM AUTHOR]

Designing a lightweight and robust real-time land cover segmentation algorithm is an important task for land resource applications. In recent years, with the development of edge computing and the increasing resolution of remote sensing images, the huge amount of calculations and parameters have restricted the efficiency of real-time semantic segmentation. Therefore, the emergence of lightweight CNN (convolutional neural network) has accelerated the development of real-time semantic segmentation of land cover. However, nowadays, the time and space span of aerial images is getting larger and larger, resulting in the loss of details and blurred edges of lightweight CNN. Therefore, the existing lightweight CNN model has low segmentation accuracy and poor generalization ability in real-time land cover segmentation tasks. In order to solve the problem of lightweight network in this respect, this paper proposes a Semantics Guided Bottleneck Network (SGBNet) to balance accuracy and reasoning speed. First, a basic unit and the overall network structure are redesigned to increase the overall reasoning efficiency of the model. The model can efficiently extract spatial details and contextual semantic information. Then, the model optimizes the lightweight network and realizes the extraction of details and contextual semantic information. Finally, a lightweight attention mechanism is used to restore high-resolution pixel-level features. The results of comparative experiments show that the method in this paper has a higher segmentation accuracy than existing models while achieving lightweight. [ABSTRACT FROM AUTHOR]

Wildfire, also known as forest fire, is a common natural or man-made disaster that has caused devastation to both man-made structures and natural ecosystems throughout the world. Unmanned Aerial Systems (UAS)-based remote sensing (RS) provides valuable support for wildfire management efforts, enhancing both spatial and temporal resolution. The aim of this paper is to summarize the current applications of UAS operations for combating the wildfire worldwide. RS applications of UAS has been explored during the three stages of wildfire, including Pre-fire, Active-fire, and Post-fire, with a particular emphasis on the types of information collected and data processing methods. The pre-fire section assesses fire potentials, the active-fire stage focuses on fire surveillance and propagation, while the post-fire stage focuses on studies assessing wildfire impact using UAS. In addition, the review provides a comprehensive overview of UAS navigation techniques adapted to fire surveillance. The literature review was conducted using three bibliographic databases, including Science Direct, IEEE Explore, and Scopus, and 186 articles relevant to UAS applications in wildfires were manually gathered. This literature review encompasses 119 articles focused on RS, 40 articles related to navigation, and the remaining articles covering reviews, concept proposals, UAS designs, and solutions addressing technical limitations of UASs in the context of wildfire management. This review offers a comprehensive overview of recent UAS operations for future researchers aiming to utilize UAS technologies for efficient wildfire management. The findings highlight the need for further investigation into the onboard computational capacities of Artificial Intelligence (AI) algorithms, precise fuel load estimation, considering individual vegetation, and field experiments to evaluate and validate navigation algorithms. [ABSTRACT FROM AUTHOR]

Rice is the most important food crop in the world, which is meaningful to ensure the quality and quantity of rice production. During the plantation process, weeds are the key factor to influence the rice yields. In recent years, the chemical control becomes the most widely used means to control the weed infestation because of its advantage in pesticide effects and efficiency. However, excessive use of herbicides has caused negative effects on the rice quality as well as the environment. An accurate weed cover map can provide support information for specific site weed management (SSWM) applications, which may well address the problem of traditional chemical controls. In this work, the unmanned aerial vehicle (UAV) imagery was captured on four different dates over two different rice fields. Object-based image analysis (OBIA) and deep learning approaches were applied to the weed mapping task of the UAV imagery. For the OBIA methods, the multiresolution segmentation and an improved k-means method were applied to segment the imagery into different objects; the colour and texture features were extracted and concatenated into a feature vector; back propagation (BP) neural network, support vector machine (SVM) and random forest were used for classification. After careful hyperparameter optimization and model selection, it was proven that the OBIA method achieved the accuracy of 66.6% mean intersection over union (MIU) on the testing set, and the inference speed is 2343.5 ms for an image sample. For the deep learning approach, the fully convolutional network (FCN) was applied for the pixel-wise classification task; transfer learning was used, and four pretrained convolutional neural networks (AlexNet, VGGNet, GoogLeNet, and ResNet) were transferred to our dataset via fine-tuning technique. Traditional skip architecture and fully connected conditional random fields (CRF) were used to improve the spatial details of FCN; after that, this work proposed to use a partially connected CRF as post processing, which may significantly accelerate the inference speed of fully connected CRF. Besides one single improvement method, hybrid improvement methods were applied and tested. Experimental results showed that the VGGNet-based FCN achieved the highest accuracy; for the improvement methods, the skip architecture and newly proposed partially connected CRF effectively improved the accuracy, and the hybrid improvement method (skip architecture and partially connected CRF) further improved the performance. The hybrid improvement method achieved 80.2% MIU on the testing set, and the inference speed for an image sample is 326.8 ms. The experimental results of this work demonstrated that the UAV remote-sensing utilizing deep learning method can provide reliable support information for SSWM applications in rice fields. [ABSTRACT FROM AUTHOR]