Object detection has developed rapidly with the help of deep learning technologies recent years. However, object detection on drone view remains challenging due to two main reasons: (1) It is difficult to detect small-scale objects lacking detailed information. (2) The diversity of camera angles of drones brings dramatic differences in object scale. Although feature pyramid network (FPN) alleviates the problem caused by scale difference to some extent, it also retains some worthless features, which wastes resources and slows down the speed. In this work, we propose a novel High-Resolution Feature Pyramid Network (HR-FPN) to improve the detection accuracy of small-scale objects and avoid feature redundancy. The key components of HR-FPN include a high-resolution feature alignment module (HRFA), a high-resolution feature fusion module (HRFF) and a multi-scale decoupled head (MSDH). HRFA feeds multi-scale features from backbone into parallel resampling channels to obtain high-resolution features at the same scale. HRFF establishes a bottom-up path to distribute context-rich low-level semantic information to all layers that are then aggregated into classification feature and localization feature. MSDH cope with the scale difference of objects by predicting the categories and locations corresponding to different scales of objects separately. Moreover, we train model by scale-weighted loss to focus more on small-scale objects. Extensive experiments and comprehensive evaluations demonstrate the effectiveness and advancement of our approach.

With the integrated design and application of radar, communication and electronic reconnaissance, automatic modulation classification (AMC) is becoming increasingly significant in various applications, e.g. spectrum monitoring and cognitive radio, and has entered a stage of remarkable development. Recently, the AMC technology is suffering from complex and diverse signal types, low signal-to-noise ratio, poor algorithm robustness, and so forth. To cope with these flaws, this paper presents a modulation classification scheme based on deep feature fusion. In this work, the ResNeXt network is utilized to extract the distinctive semantic feature of the signal, and the gated recurrent unit (GRU) is employed to extract the time-series representation characteristic, respectively. Considering the complementarity between different features, a feature fusion model using discriminant correlation analysis (DCA) is proposed to fuse the output responses of the ResNeXt and GRU. The simulation results reveal that the proposed method achieves the superior performance, which is conducive to promoting the application of feature fusion in the AMC.

Recent years have witnessed a surge of developments in deep learning (DL) motivated by a variety of contemporary applications. The conventional DL-based automatic modulation classification (AMC) methods are always relying on a great quan- tity of data. In this paper, we propose a DL-based AMC model with short data for spectrum sensing of wireless communication signals. First, a hopping transform unit is proposed to represent the transient variation occurred either by frequency, amplitude or phase modulations. Second, a bidirectional long short-term memory (Bi-LSTM) based hopping feature perception model, namely deep-learning hopping capture model (DHCM), is built for the AMC. A comprehensive comparison of the DHCM with other existing methods is then provided under various signal-to- noise ratios (SNRs). The experimental results demonstrate the superiority of the proposed method under short data.

This paper investigates the problem of specific emitter identification (SEI), i.e. radar emitter fingerprint or individual emitter identification, which first measures the emitter-specific differences caused by radar's nonlinearities, e.g. mixer, power amplifiers, transmitter, and then makes a decision. In this paper, the SEI problem is considered in the single-modal, dual-modal and multi-modal scenarios, respectively. First, a multi-modal subspace interactive mutual unit is proposed to perform information interaction between radar signal and its multiple transformations. Based on this, a data-driven multi-modal subspace interactive mutual network (MSIMN) is then built to solve the SEI problem. Extensive experiment results demonstrate that the proposed algorithm achieves superior identification performance on the airplane measured data.

In signal communication based on a non-cooperative communication system, the receiver is an unlicensed third-party communication terminal, and the modulation parameters of the transmitter signal cannot be predicted in advance. After the RF signal passes through the RF band-pass filter, low noise amplifier, and image rejection filter, the intermediate frequency signal is obtained by down-conversion, and then the IQ signal is obtained in the baseband by using the intermediate frequency band-pass filter and down-conversion. In this process, noise and signal frequency offset are inevitably introduced. As the basis of subsequent analysis and interpretation, modulation recognition has important research value in this environment. The introduction of deep learning also brings new feature mining tools. Based on this, this paper proposes a signal modulation recognition method based on multi-feature fusion and constructs a deep learning network with a double-branch structure to extract the features of IQ signal and multi-channel constellation, respectively. It is found that through the complementary characteristics of different forms of signals, a more complete signal feature representation can be constructed. At the same time, it can better alleviate the influence of noise and frequency offset on recognition performance, and effectively improve the classification accuracy of modulation recognition.