Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods.

Single-shot fringe projection profilometry (FPP) is crucial for real-time or dynamic 3D measurement scenarios. In this regard, we propose a spatial composite fringe pattern projection profilometry (SCFPP), which creatively fuses the spatial feature in different frequency fringe patterns. Inspired by image inpainting techniques in computer vision, SCFPP employs a novel adaptive space-division encoding strategy (ASES) to divide fringe patterns into several basic blocks and re-aggregate partial basic blocks in the spatial domain to form a spatial composite fringe pattern. In the demodulation stage, we develop a deep learning network model, the phase inpainting network (PIN), to restore the spatial composite fringe pattern to complete phase information. The absolute phase map is then obtained with high accuracy by applying the conventional three-frequency heterodyne phase unwrapping (CTHPU) algorithm with three known wrapped phase maps. To our knowledge, SCFPP is the first successful use of spatial multiplexing strategy in FPP. Additionally, SCFPP can be seen as an application of image inpainting techniques in the fringe projection field, introducing new ideas for applying computer vision methods in fringe analysis.

Head pose estimation has been considered an important and challenging task in computer vision. In this paper we propose a novel method to estimate head pos

As artificial intelligence (AI) technology advances rapidly, its increasing involvement in military defense fosters intelligent air combat domain development. The Intelligent Flight Controller (IFC) is a crucial technology and foundation for intelligent air combat decision-making systems. Controlling 6 Degree-of-freedom (DOF) aircraft in close-to-real-world environments requires an adaptable and dynamic decision-making controller. Most IFC researches focus on simplistic flight trajectory design and validation, while air combat requires aircraft that can perform complex tactical maneuvers. Deep reinforcement learning (DRL) provides a suitable technical paradigm. However, DRL suffers from sparse rewards, insufficient supervisory signals, low sampling efficiency, and slow convergence. In contrast, Large Language Model (LLM) possesses abundant knowledge about the real world, contextual understanding, and reasoning capabilities. By leveraging this, LLM can serve as prior knowledge for DRL, thereby reducing DRL training time. This paper proposes an LLM-guided deep reinforcement learning framework for IFC, which utilizes LLM-guided deep reinforcement learning to achieve intelligent flight control under limited computational resources. LLM provides direct guidance during training based on local knowledge, which improves the quality of data generated in agent-environment interaction within DRL, expedites training, and offers timely feedback to agents, thereby partially mitigating sparse reward issues. Additionally, we present an effective reward function to comprehensively balance the aircraft coupling control to ensure stable, flexible control. Finally, simulations and experiments show that the proposed techniques have good performance, robustness, and adaptability across various flight tasks, laying a foundation for future research in the intelligent air combat decision-making domain.

The pose estimation of the aircraft in the airport plays an important role in preventing collisions and constructing the real‐time scene of the airport. However, current airport target surveillance methods regard the aircraft as a point, neglecting the importance of pose estimation. Inspired by human pose estimation, this paper presents an aircraft pose estimation method based on a convolutional neural network through reconstructing the two‐dimensional skeleton of an aircraft. Firstly, the key points of an aircraft and the matching relationship are defined to design a 2D skeleton of an aircraft. Secondly, a convolutional neural network is designed to predict all key points and components of the aircraft kept in the confidence maps and the Correlation Fields, respectively. Thirdly, all key points are coarsely matched based on the matching relationship and then refined through the Correlation Fields. Finally, the 2D skeleton of an aircraft is reconstructed. To overcome the lack of benchmark dataset, the airport surveillance video and Autodesk 3ds Max are utilized to build two datasets. Experiment results show that the proposed method get better performance in terms of accuracy and efficiency compared with other related methods.

Many state-of-the-art stereo matching algorithms based on deep learning have been proposed in recent years, which usually construct a cost volume and adopt cost filtering by a series of 3D convolutions. In essence, the possibility of all the disparities is exhaustively represented in the cost volume, and the estimated disparity holds the maximal possibility. The cost filtering could learn contextual information and reduce mismatches in ill-posed regions. However, this kind of methods has two main disadvantages: 1) cost filtering is very time-consuming, and it is thus difficult to simultaneously satisfy the requirements for both speed and accuracy; 2) thickness of the cost volume determines the disparity range which can be estimated, and the pre-defined disparity range may not meet the demand of practical application. This paper proposes a novel real-time stereo matching method called RLStereo, which is based on reinforcement learning and abandons the cost volume or the routine of exhaustive search. The trained RLStereo makes only a few actions iteratively to search the value of the disparity for each pair of stereo images. Experimental results show the effectiveness of the proposed method, which achieves comparable performances to state-of-the-art algorithms with real-time speed on the public large-scale testset, i.e., Scene Flow.