Search

Image interpretation algorithms based on deep learning are becoming increasingly important in land cover information acquisition. We propose CSSwin-unet, a network designed for the semantic segmentation of remote sensing images. CSSwin-unet is based on Swin-unet, follows the U-shaped codec structure of U-Net, but utilizes Swin transformer blocks with superior global modelling capabilities to constitute the codec. In addition, we design a parallel branch in the encoder with a context aggregation module (CAM) to enhance contextual information extraction and alleviate the semantic ambiguity problem resulting from occlusion. To address the problem of semantic information mismatch between codecs and improve the model's ability to extract spatial information, we constructed a space extraction module (SEM) in the skip connections, which replaces the direct copying of encoder features in Swin-unet. To reduce information loss during the downsampling process and strengthen the segmentation capacity of the network, we designed a feature shrinkage module (FSM) in the downsampling session. We conducted comprehensive ablation experiments on a dataset we produced ourselves and compared the results with other advanced methods. The test results showed significant improvement, with mIoU, mF1, and OA values improving by 2.83%, 2.47%, and 2.05%, respectively, compared to the second best performing model, Swin-unet. The above results prove the excellent performance of CSSwin-unet. [ABSTRACT FROM AUTHOR]

Mangroves are endemic forest communities in tropical and subtropical coastal zones. China's Hainan Island is very rich in mangrove plant species. In recent years, due to climate change and human disturbance, the living environment of many mangrove distribution areas has been seriously threatened. This study used land satellite series remote sensing images from 1990 to 2020 to monitor the coverage and area changes of mangroves on Hainan Island. The spatial distribution pattern and change trend of mangroves were explored using the standard deviation ellipse method, and the CA–Markov model was used to predict the possible changes of mangroves in the study area in 2025 and 2030. The development trend of mangroves in the future and the driving factors affecting the evolution of mangroves were also analyzed. Over the past 30 years, the area of mangroves has witnessed fluctuations. It decreased from 4578 hectares in 1990 to its lowest at 3870 hectares in 2005 and then rebounded to 4474 hectares by 2020, indicating an initial decline followed by a gradual increase. Although conservation and restoration efforts have yielded success, specific areas have witnessed a decline in mangrove coverage. From 1990 to 2020, mangrove areas in Huiwen decreased from 1055 hectares to 904 hectares, areas in Guannan decreased from 227 hectares to 167 hectares, areas in Xinyinggang decreased from 328 hectares to 298 hectares, areas in Yangpugang decreased from 747 hectares to 682 hectares, areas in Huachangwan decreased from 355 hectares to 327 hectares, and areas in Puqian decreased from 170 hectares to 141 hectares. In particular, the growth in the Eastern and Mayao port areas is especially significant. Additionally, data analysis has revealed the spatial distribution characteristics of mangroves in different regions, such as the mangrove area in Dongzhaigang, which remained relatively stable from 1990 to 2020, while in other areas like Huiwen and Guannan, the mangrove area decreased during these 20 years. By calculating the standard deviation ellipse, we observed that the overall change of mangroves on Hainan Island from 1990 to 2020 was relatively slow, mainly distributed along the northern coastal area of Hainan Island. Furthermore, the standard deviation ellipse and SDE center point of each mangrove growth area have visualized the growth trends of the mangroves. The Markov chain simulation results show that future changes in mangroves will mainly be concentrated in the marginal areas of the mangroves. These areas may be affected by rising sea levels, climate change, soil salinity, and human activities. In the future, mangrove areas are expected to display a dynamic equilibrium, experiencing periods of expansion and reduction, ultimately moving towards a more consistent state. To protect and restore mangroves, it is necessary to strengthen the monitoring and management of their ecological environment and socio-economic factors and improve their stability and diversity. [ABSTRACT FROM AUTHOR]

Spot detection has attracted continuous attention for laser sensors with applications in communication, measurement, etc. The existing methods often directly perform binarization processing on the original spot image. They suffer from the interference of the background light. To reduce this kind of interference, we propose a novel method called annular convolution filtering (ACF). In our method, the region of interest (ROI) in the spot image is first searched by using the statistical properties of pixels. Then, the annular convolution strip is constructed based on the energy attenuation property of the laser and the convolution operation is performed in the ROI of the spot image. Finally, a feature similarity index is designed to estimate the parameters of the laser spot. Experiments on three datasets with different kinds of background light show the advantages of our ACF method, with comparison to the theoretical method based on international standard, the practical method used in the market products, and the recent benchmark methods AAMED and ALS. [ABSTRACT FROM AUTHOR]

Video summarization offers a summary version that conveys the primary information of a longer video. The main challenges of video summarization are related to keyframe extraction and saliency mapping. Thus, this work proposes a sparse coding model for keyframe extraction and saliency mapping applications. Specifically, the minimax concave penalty (MCP) is utilized as a sparse regularization scheme and the regularized non‐convex MCP problem is solved by decomposing MCP into two convex functions and the convex function's algorithm difference is relied on to solve the resulting sub‐problems. The experimental results demonstrate higher compressed keyframes and saliency maps than current state‐of‐the‐art algorithms. In particular, the model attains a lower summary length of 34% and 19% compared to sparse modeling representation selection (SMRS) and sparse modeling using the determinant sparsity measure (SC‐det), respectively. In addition, the developed scheme has a shorter computation time, requiring 82% and 33% less time than the ITTI and the dense and sparse reconstruction (DSR) methods. [ABSTRACT FROM AUTHOR]

Compared to the focus of other literature on this topic - for example, Asian perspectives on the international investment regime, the Association of Southeast Asian Nations (ASEAN)'s perspective on the international investment regime, the changing international investment regime in Asia, etc. - this book puts the spotlight on the Asian I turn i in foreign investment, as indicated by its title. In this Chapter, after thoroughly delving into the Asian story, Julien Chaisse and Xu Qian assess the influence of the proactive investment policy of the European Union in Asia, concluding that it only encourages a recalibration of the investment regulation in the Asian regime. [Extracted from the article]

In recent years, the model compression technique is very effective for deep neural network compression. However, many existing model compression methods rely heavily on human experience to explore a compression strategy between network structure, speed, and accuracy, which is usually suboptimal and time-consuming. In this paper, we propose a framework for automatically compressing models through the actor–critic structured deep reinforcement learning (DRL) which interacts with each layer in the neural network, where the actor network determines the compression strategy and the critic network ensures the decision accuracy of the actor network through predicted values, thus improving the compression quality of the network. To enhance the prediction performance of the critic network, we impose the L 1 norm regularizer on the weights of the critic network to obtain a distinct activation output feature on the representation, thus enhancing the prediction accuracy of the critic network. Moreover, to improve the decision performance of the actor network, we impose the L 1 norm regularizer on the weights of the actor network to improve the decision accuracy of the actor network by removing the redundant weights in the actor network. Furthermore, to improve the training efficiency, we use the proximal gradient method to optimize the weights of the actor network and the critic network, which can obtain an effective weight solution and thus improve the compression performance. In the experiment, in MNIST datasets, the proposed method has only a 0.2% loss of accuracy when compressing more than 70% of neurons. Similarly, in CIFAR-10 datasets, the proposed method compresses more than 60% of neurons, with only 7.1% accuracy loss, which is superior to other existing methods. In terms of efficiency, the proposed method also cost the lowest time among the existing methods. [ABSTRACT FROM AUTHOR]

Dynamic off-chain routing in payment channel network (PCN)-based Internet of Things (IoT) is attracting increasing research attention. However, there are two major issues in dynamic routing in PCN-based IoT with resource-limited devices. The first issue is how to achieve high long-term transaction efficiency in PCN with dynamic channel capacities. The second issue is how to achieve a lightweight routing algorithm deployed on IoT devices while achieving high transaction efficiency, i.e., successful payment amount and success ratio. Therefore, in this paper, we propose a compact deep reinforcement learning (DRL) algorithm to learn the joint dynamic and lightweight routing policy for maximizing long-term transaction efficiency. To obtain optimal performance in dynamic routing problems for off-chain systems, a proximal policy optimization algorithm is employed to create an actor–critic learning structure for training the teacher DRL model. To obtain a compact and efficient student DRL model, an adaptive pruning technique is utilized for pruning unnecessary parameters of networks in the teacher model adaptively without affecting its learning ability. Furthermore, knowledge distillation is leveraged to improve the performance of the student network. Thus, a compact and efficient student DRL model can be developed and implemented to maximize the long-term transaction efficiency in off-chain systems on resource-limited IoT devices. The simulation results demonstrate that the proposed DRL algorithm outperforms the other baseline algorithms in PCN transaction efficiency while requiring only 10% of the computation and storage resources compared with that of the original teacher model. [ABSTRACT FROM AUTHOR]

Carrier-phase multipath is the main problem of GNSS deformation monitoring. Traditional methods usually adopt sidereal day filtering to mitigate the multipath. However, the necessity of presetting the session duration of the static baseline solution reduces the timeliness of the methods in real engineering. Moreover, these methods are not suitable for the systems that contain different types of GNSS satellites (e.g., BDS). To address the problems, this paper proposes an Adaptive Fast Independent Component Analysis (AF-ICA) method for mitigating multipath effects in GNSS deformation monitoring, which can effectively process the multi-GNSS data and separate several multipath signals. In the experimental study, compared with Sidereal Filtering in Observation Domain (SF-OD) method, AF-ICA method can improve both the positioning accuracy and peak-to-peak value. In GNSS deformation monitoring positioning accuracy, AF-ICA method can achieve the root-mean-square (RMS) of 1 mm horizon-tally and 2 mm vertically. Compared with the MSF method, the positioning accuracy of the AF-ICA method in the direction of ENU is improved by 44%, 14%, and 31%, respectively, and the corresponding peak-to-peak values increased by 36%, 17%, and 29%, respectively. Our proposed method can automatically get the monitoring information without estimating the orbit period in advance to realize automatic deformation monitoring. Through the automatic monitoring solution, the AF-ICA method in this paper can be applied to the natural disaster monitoring in the Internet of Things and provides real-time data monitoring information for disaster early warning. [ABSTRACT FROM AUTHOR]