Unmanned aerial vehicles (UAVs) can capture high-quality aerial photos and have been widely used for large-scale urban 3D reconstruction. However, even with the help of commercial flight control software, it is still a challenging task for non-professional users to capture full-coverage aerial photos in complex urban environments, which normally leads to incomplete 3D reconstruction. In this paper, we propose a novel path planning method for the high-quality aerial 3D reconstruction of urban scenes. The proposed approach first captures aerial photos, following an initial path to generate a coarse 3D model as prior knowledge. Then, 3D viewpoints with constrained location and orientation are generated and evaluated, according to the completeness and accuracy of the corresponding visible regions of the prior model. Finally, an optimized path is produced by smoothly connecting the optimal viewpoints. We perform an extensive evaluation of our method on real and simulated data sets, in comparison with a state-of-the-art method. The experimental results indicate that the optimized trajectory generated by our method can lead to a significant boost in the performance of aerial 3D urban reconstruction.

Visual odometry, which aims to estimate relative camera motion between sequential video frames, has been widely used in the fields of augmented reality, virtual reality, and autonomous driving. However, it is still quite challenging for state-of-the-art approaches to handle low-texture scenes. In this paper, we propose a robust and efficient visual odometry algorithm that directly utilizes edge pixels to track camera pose. In contrast to direct methods, we choose reprojection error to construct the optimization energy, which can effectively cope with illumination changes. The distance transform map built upon edge detection for each frame is used to improve tracking efficiency. A novel weighted edge alignment method together with sliding window optimization is proposed to further improve the accuracy. Experiments on public datasets show that the method is comparable to state-of-the-art methods in terms of tracking accuracy, while being faster and more robust.