No abstract

Recent progress on remote sensing scene classification is substantial, benefiting mostly from the explosive development of convolutional neural networks (CNNs). However, different from the natural images in which the objects occupy most of the space, objects in remote sensing images are usually small and separated. Therefore, there is still a large room for improvement of the vanilla CNNs that extract global image-level features for remote sensing scene classification, ignoring local object-level features. In this paper, we propose a novel remote sensing scene classification method via enhanced feature pyramid network with deep semantic embedding. Our proposed framework extracts multi-scale multi-level features using an enhanced feature pyramid network (EFPN). Then, to leverage the complementary advantages of the multi-level and multi-scale features, we design a deep semantic embedding (DSE) module to generate discriminative features. Third, a feature fusion module, called two-branch deep feature fusion (TDFF), is introduced to aggregate the features at different levels in an effective way. Our method produces state-of-the-art results on two widely used remote sensing scene classification benchmarks, with better effectiveness and accuracy than the existing algorithms. Beyond that, we conduct an exhaustive analysis on the role of each module in the proposed architecture, and the experimental results further verify the merits of the proposed method.

No abstract

No abstract

Abstract:Aiming for large-scale renewable energy sources (RES) integrated to power systems with power electronic devices, the technology of virtual synchronous generator (VSG) has been developed and studied in recent years. It is necessary to analyze the damping characteristics of the power system with RES generation based on VSG and develop its corresponding damping controller to suppress the possible low frequency oscillation. Firstly, the mathematical model of VSG in a per unit (p.u) system is presented. Based on the single-machine infinite bus system integrated with an RES power plant, the influence of VSG on the damping characteristics of the power system is studied qualitatively by damping torque analysis. Furthermore, the small-signal model of the considered system is established and the damping ratio of the system is studied quantitatively by eigenvalue analysis, which concluded that adjusting the key control parameters has limited impacts on the damping ratio of the system. Consequently, referring to the configuration of traditional power system stabilizer (PSS), an auxiliary damping controller (ADC) for VSG is designed to suppress the low frequency oscillation of the power system. Finally, simulations were performed to verify the validity of theoretical analysis and the effectiveness of designed ADC.

The automatic recognition of multi-class objects with various backgrounds is a big challenge in the field of remote sensing (RS) image analysis. In this paper, we propose a novel recognition framework for multi-class RS objects based on the discriminative sparse representation. In this framework, the recognition problem is implemented in two stages. In the first, or discriminative dictionary learning stage, considering the characterization of remote sensing objects, the scale-invariant feature transform descriptor is first combined with an improved bag-of-words model for multi-class objects feature extraction and representation. Then, information about each class of training samples is fused into the dictionary learning process; by using the K-singular value decomposition algorithm, a discriminative dictionary can be learned for sparse coding. In the second, or recognition, stage, to improve the computational efficiency, the phase spectrum of a quaternion Fourier transform model is applied to the test image to predict a small set of object candidate locations. Then, a multi-scale sliding window mechanism is utilized to scan the image over those candidate locations to obtain the object candidates (or objects of interest). Subsequently, the sparse coding coefficients of these candidates under the discriminative dictionary are mapped to the discriminative vectors that have a good ability to distinguish different classes of objects. Finally, multi-class object recognition can be accomplished by analyzing these vectors. The experimental results show that the proposed work outperforms a number of state-of-the-art methods for multi-class remote sensing object recognition.

No abstract

No abstract