Deep convolutional neural networks (CNNs) have been widely used to obtain high-level representation in various computer vision tasks. However, in the field of remote sensing, there are not sufficient images to train a useful deep CNN. Instead, we tend to transfer successful pre-trained deep CNNs to remote sensing tasks. In the transferring process, generalization power of features in pre-trained deep CNNs plays the key role. In this paper, we propose two promising architectures to extract general features from pre-trained deep CNNs for remote scene classification. These two architectures suggest two directions for improvement. First, before the pre-trained deep CNNs, we design a linear PCA network (LPCANet) to synthesize spatial information of remote sensing images in each spectral channel. This design shortens the spatial “distance” of target and source datasets for pre-trained deep CNNs. Second, we introduce quaternion algebra to LPCANet, which further shortens the spectral “distance” between remote sensing images and images used to pre-train deep CNNs. With five well-known pre-trained deep CNNs, experimental results on three independent remote sensing datasets demonstrate that our proposed framework obtains state-of-the-art results without fine-tuning and feature fusing. This paper also provides baseline for transferring fresh pretrained deep CNNs to other remote sensing tasks.

An approach of air-to-air autonomous attack occupation for Unmanned Combat Aerial Vehicles (UCAVs) is proposed to improve attack precision and combat effectiveness. According to the shortage of UCAV in the task of attack occupation, kinematic and dynamic models of UCAV and missile loaded on it are formed. Then, attack zone and no-escape zone are calculated by pattern search algorithm, and the optimum attack position is indicated. To arrive at the optimum attack position accurately with restriction of gesture, a novel adaptive sliding mode control method is suggested to design the integrated guidance and control system of UCAV in the process of autonomous attack occupation. Key parameters of the control system are adaptively regulated, which further economize control energy at the same time. The simulation results show that compared with traditional methods our approach can guide the UCAV to the optimum attack position with stable gesture and economize nearly 25% control energy.

Deep convolutional neural networks (CNNs) have been widely used to obtain high-level representation in various computer vision tasks. However, for the task of remote scene classification, there are no sufficient images to train a very deep CNN from scratch. Instead, transferring successful pre-trained deep CNNs to remote sensing tasks provides an effective solution. Firstly, from the viewpoint of generalization power, we try to find whether deep CNNs need to be deep when applied for remote scene classification. Then, the pre-trained deep CNNs with fixed parameters are transferred for remote scene classification, which solve the problem of time-consuming and parameters over-fitting at the same time. With five well-known pre-trained deep CNNs, experimental results on three independent remote sensing datasets demonstrate that transferred deep CNNs can achieve state-of-the-art results in unsupervised setting. This chapter also provides baseline for applying deep CNNs to other remote sensing tasks.

Concerned with the problems that the extracted features are the absence of objectivity for radar emitter signal intrapulse data because of relying on priori knowledge, a novel method is proposed. First, this method gets the sparse autoencoder by adding certain restrain to the autoencoder. Second, by optimizing the sparse autoencoder and confirming the training scheme, intrapulse deep features are autoextracted with encoder layer parameters. The method extracts the eigenvectors of six typical radar emitter signals and uses them as inputs to a support vector machine classifier. The experimental results show that the method has higher accuracy in the case of large signal-to-noise ratio. The simulation verifies that the extracted features are feasible.