Parallel K Nearest Neighbor Matching for 3D Reconstruction

Abstract

In recent years, a 3D reconstruction based on structure from motion (SFM) has attracted much attention from the communities of computer vision and graphics. It is well known that the speed and quality of SFM systems largely depend on the technique of feature tracking. If a big volume of image data is inputted for SFM, the speed of this SFM system would become very slow. And, this problem becomes severer for largescale scenes, which typically needs to capture several thousands of images to recover the point-cloud model of the scene. However, none of the existing methods fully addresses the problem of fast feature tracking. Brute force matching is capable of producing correspondences for small-scale scenes but often getting stuck in repeated features. Hashing matching can only deal with middle-scale scenes and is not capable of largescale scenes. In this paper, we propose a new feature tacking method working in a parallel manner rather than in a single thread scheme. Our method consists of steps of keypoint detection, descriptor computing, descriptor matching by parallel k-nearest neighbor (Parallel-KNN) search, and outlier rejecting. This method is able to rapidly match a big volume of keypoints and avoids to consume high computation time, then yielding a set of correct correspondences. We demonstrate and evaluate the proposed method on several challenging benchmark datasets, including those with highly repeated features, and compare to the state-ofthe-art methods. The experimental results indicate that our method outperforms the compared methods in both efficiency and effectiveness.

State-of-the-Art Development of Complex Systems and Their Simulation Methods

“…Our research group at the Hefei University of Technology has performed considerable work on visualization [80][81][82] . For more than 20 years, relying on visual environments, our research group has systematically and deeply studied template theory, intelligent design, motion simulation, and visualization methods, which are guided by the modeling methodology, based on collaborative computing, and rely on visual environments [83][84][85] .…”

The Influence of Western Urban Planning Theory and Practice on Urban Planning and Construction of Hefei Discussion based on “Urban Planning Theory since 1945”

“…He pointed out that, unlike the reverse urbanization and urban decline in the West, China is still in the transition from the initial stage of urbanization to the acceleration period. The physical environment planning is a realistic need and cannot be denied blindly [2]. In the initial stage of Hefei's urban construction, physical planning played a major role, especially the planning and layout of the three main industrial areas in the eastern, northern and southwestern suburbs, which laid the foundation for the industrial development of Hefei.…”

Real-Time 2D Orthomosaic Mapping from Drone-Captured Images Using Feature-Based Sequential Image Registration

“…The KNN matcher determines feature points based on the nearest neighbors, providing robust matching. However, it has a high computational cost [36,37]. Recently, deep learning methods, such as the learned invariant feature transform, super point, super glue, and LoFTR, have been employed in image matching [38][39][40].…”