Search

Due to the complex imaging mechanism of SAR images and the lack of multi-angle and multi-parameter real scene SAR target data, the generalization performance of existing deep-learning-based synthetic aperture radar (SAR) image target detection methods are extremely limited. In this paper, we propose an unsupervised domain-adaptive SAR ship detection method based on cross-domain feature interaction and data contribution balance. First, we designed a new cross-domain image generation module called CycleGAN-SCA to narrow the gap between the source domain and the target domain. Second, to alleviate the influence of complex backgrounds on ship detection, a new backbone using a self-attention mechanism to tap the potential of feature representation was designed. Furthermore, aiming at the problems of low resolution, few features and easy information loss of small ships, a new lightweight feature fusion and feature enhancement neck was designed. Finally, to balance the influence of different quality samples on the model, a simple and efficient E 1 2 I o U Loss was constructed. Experimental results based on a self-built large-scale optical-SAR cross-domain target detection dataset show that compared with existing cross-domain methods, our method achieved optimal performance, with the mAP reaching 68.54%. Furthermore, our method achieved a 6.27% improvement compared to the baseline, even with only 5% of the target domain labeled data. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV) is one of the main means of information warfare, such as in battlefield cruises, reconnaissance, and military strikes. Rapid detection and accurate recognition of key targets in UAV images are the basis of subsequent military tasks. The UAV image has characteristics of high resolution and small target size, and in practical application, the detection speed is often required to be fast. Existing algorithms are not able to achieve an effective trade-off between detection accuracy and speed. Therefore, this paper proposes a parallel ensemble deep learning framework for unmanned aerial vehicle video multi-target detection, which is a global and local joint detection strategy. It combines a deep learning target detection algorithm with template matching to make full use of image information. It also integrates multi-process and multi-threading mechanisms to speed up processing. Experiments show that the system has high detection accuracy for targets with focal lengths varying from one to ten times. At the same time, the real-time and stable display of detection results is realized by aiming at the moving UAV video image. [ABSTRACT FROM AUTHOR]

Burned area is a critical input to biomass burning carbon emissions algorithms and for understanding variability in fire activity due to climate change. This study presents the spatial and temporal patterns of wildland fires in the Mongolian Plateau (MP) using Collection 6 NASA MCD64A1 500 m global Burned Area product from 2001 to 2021. Both inter- and intra-annual fire trends and variations in two subregions, Mongolia and China's Inner Mongolia, were analyzed. The results indicated that an average area of 1.3 × 104 km2 was consumed by fire per year in the MP. The fire season has two peaks: spring (March, April, and May) and autumn (September, October, and December). The profiles of the burnt area for each subregion exhibit distinct seasonality. The majority of wildfires occurred in the northeastern and southwestern regions of the MP, on the border between Mongolia and China. There were 2.7 × 104 km2 of land burned by wildfires in the MP from 2001 to 2021, 57% of which occurred in spring. Dornod aimag (province) of Mongolia is the most fire-prone region, accounting for 51% of the total burned area in the MP, followed by Hulunbuir, at 17%, Sukhbaatar, at 9%, and Khentii at 8%. The changing patterns of spatiotemporal patterns of fire in the MP were analyzed by using a spatiotemporal cube analysis tool, ArcGIS Pro 3.0.2. The results suggested that fires showed a decreasing trend overall in the MP from 2001 to 2021. Fires in the southern region of Dornod aimag and eastern parts of Great Xing'an Mountain showed a sporadic increasing trend. Therefore, these areas should be priorities for future fire protection for both Mongolia and China. [ABSTRACT FROM AUTHOR]

Target detection in synthetic aperture radar (SAR) images has a wide range of applications in military and civilian fields. However, for engineering applications involving edge deployment, it is difficult to find a suitable balance of accuracy and speed for anchor-based SAR image target detection algorithms. Thus, an anchor-free detection algorithm for SAR ship targets with deep saliency representation, called SRDet, is proposed in this paper to improve SAR ship detection performance against complex backgrounds. First, we design a data enhancement method considering semantic relationships. Second, the state-of-the-art anchor-free target detection framework CenterNet2 is used as a benchmark, and a new feature-enhancing lightweight backbone, called LWBackbone, is designed to reduce the number of model parameters while effectively extracting the salient features of SAR targets. Additionally, a new mixed-domain attention mechanism, called CNAM, is proposed to effectively suppress interference from complex land backgrounds and highlight the target area. Finally, we construct a receptive-field-enhanced detection head module, called RFEHead, to improve the multiscale perception performance of the detection head. Experimental results based on three large-scale SAR target detection datasets, SSDD, HRSID and SAR-ship-dataset, show that our algorithm achieves a better balance between ship target detection accuracy and speed and exhibits excellent generalization performance. [ABSTRACT FROM AUTHOR]

As an active microwave device, synthetic aperture radar (SAR) uses the backscatter of objects for imaging. SAR image ship targets are characterized by unclear contour information, a complex background and strong scattering. Existing deep learning detection algorithms derived from anchor-based methods mostly rely on expert experience to set a series of hyperparameters, and it is difficult to characterize the unique characteristics of SAR image ship targets, which greatly limits detection accuracy and speed. Therefore, this paper proposes a new lightweight position-enhanced anchor-free SAR ship detection algorithm called LPEDet. First, to resolve unclear SAR target contours and multiscale performance problems, we used YOLOX as the benchmark framework and redesigned the lightweight multiscale backbone, called NLCNet, which balances detection speed and accuracy. Second, for the strong scattering characteristics of the SAR target, we designed a new position-enhanced attention strategy, which suppresses background clutter by adding position information to the channel attention that highlights the target information to more accurately identify and locate the target. The experimental results for two large-scale SAR target detection datasets, SSDD and HRSID, show that our method achieves a higher detection accuracy and a faster detection speed than state-of-the-art SAR target detection methods. [ABSTRACT FROM AUTHOR]

Modeling forest fire spread is a very complex problem, and the existing models usually need some input parameters which are hard to get. How to predict the time series of forest fire spread rate based on passed series may be a key problem to break through the current technical bottleneck. In the process of forest fire spreading, spread rate and wind speed would affect each other. In this paper, three kinds of network models based on Long Short-Term Memory (LSTM) are designed to predict fire spread rate, exploring the interaction between fire and wind. In order to train these LSTM-based models and validate their effectiveness of prediction, several outdoor combustion experiments are designed and carried out. Process data sets of forest fire spreading are collected with an infrared camera mounted on a UAV, and wind data sets are recorded using a anemometer simultaneously. According to the close relationship between wind and fire, three progressive LSTM based models are constructed, which are called CSG-LSTM, MDG-LSTM and FNU-LSTM, respectively. A Cross-Entropy Loss equation is employed to measure the model training quality, and then prediction accuracy is computed and analyzed by comparing with the true fire spread rate and wind speed. According to the performance of training and prediction stage, FNU-LSTM is determined as the best model for the general case. The advantage of FNU-LSTM is further demonstrated by doing comparison experiments with the normal LSTM and other LSTM based models which predict both fire spread rate and wind speed separately. The experiment has also demonstrated the ability of the model to the real fire prediction on the basis of two historical wildland fires. [ABSTRACT FROM AUTHOR]