As space technology advances, an increasing number of spacecrafts are being launched into space, making it essential to monitor and maintain satellites to ensure safe and stable operations. Acquiring 3D information of space targets enables the accurate assessment of their shape, size, and surface damage, providing critical support for on-orbit service activities. Existing 3D reconstruction techniques for space targets, which mainly rely on laser point cloud measurements or image sequences, cannot adapt to scenarios with limited observation data and viewpoints. We propose a novel method to achieve a high-quality 3D reconstruction of space targets. The proposed approach begins with a preliminary 3D reconstruction using the neural radiance field (NeRF) model, guided by observed optical images of the space target and depth priors extracted from a customized monocular depth estimation network (MDE). A NeRF is then employed to synthesize optical images from unobserved viewpoints. The corresponding depth information for these viewpoints, derived from the same depth estimation network, is integrated as a supervisory signal to iteratively refine the 3D reconstruction. By exploiting MDE and the NeRF, the proposed scheme iteratively optimizes the 3D reconstruction of spatial objects from seen viewpoints to unseen viewpoints. To minimize excessive noise from unseen viewpoints, we also incorporate a confident modeling mechanism with relative depth ranking loss functions. Experimental results demonstrate that the proposed method achieves superior 3D reconstruction quality under sparse input, outperforming traditional NeRF and DS-NeRF models in terms of perceptual quality and geometric accuracy.
Recently, Unmanned Aerial Vehicles have been widely used in the fields of water traffic supervision and maritime sovereignty inspection, becoming an important means of data acquisition. It is crucial to apply deep learning-based target detection technology to UAV edge devices. Traditional detectors are often underperformed when deployed directly to UAVs. One reason is that the amount of UAV imagery data is often limited and insufficient to support the training of deep learning algorithms. The second is that deep learning-based detectors often have huge models and huge amounts of parameters with high computational complexity, making it difficult to deploy them to work effectively on edge mobile devices with extremely limited computational resources and memory. To solve these problems, we proposed a new detection model for UAV view ship target based on YOLOv4. To this end, first, we constructed a satellite remote sensing ship image dataset and used transfer learning to reduce the reliance on model training data. Second, we lightened the model by sparsity training, channel and layer pruning, and then used knowledge distillation techniques to rebound the accuracy. In the end, the model size is reduced by 97.19% and the detection time of a single image is reduced by 39.73% while maintaining high detection accuracy, achieving high precision real-time detection suitable for deployment on edge devices such as UAVs.
Oblique photogrammetry imagery often suffers from uneven resolution and blurred details, leading to poor surface texture quality in 3D reconstructions, particularly for building facades. To address these challenges, we propose a novel Attention-Frequency Edge-Enhanced 3D Texture Enhancement Network (TENet) and introduce a comprehensive 3D texture enhancement pipeline. This pipeline applies 2D texture super-resolution techniques to 3D models for fine-grained texture restoration, enhancing the surface texture quality. TENet leverages attention mechanisms and frequency-domain techniques to improve texture sharpness and edge accuracy. Our approach includes a Region-Resolution Adaptive Enhancement Module (RAEM) and a Frequency-Domain Edge Enhancement Mechanism (FDEEM) to enhance local details and restore critical edge features. The experimental results demonstrate that TENet outperforms existing methods, significantly improving texture quality and 3D reconstruction performance. Ablation studies confirmed the effectiveness of each component in enhancing 3D texture reconstruction. The network is validated for real-world applications, showing its ability to significantly reduce edge artifacts and restore clear, accurate textures in real-world 3D surface models.