دانلود رایگان مقاله گراف چند فریم مطابق با الگوریتم برای پهنای باند کم SLAM RGB-D

Abstract

This paper presents a novel multi-frame graph matching algorithm for reliable partial alignments among point clouds. We use this algorithm to stitch frames for 3D environment reconstruction. The idea is to utilize both descriptor similarity and mutual spatial coherency of features existed in multiple frames to match these frames. The proposed multi-frame matching algorithm can extract coarse correspondence among multiple point clouds more reliably than pairwise matching algorithms, especially when the data are noisy and the overlap is relatively small. When there are insufficient consistent features that appeared in all these frames, our algorithm reduces the number of frames to match to deal with it adaptively. Hence, it is particularly suitable for cost-efficient robotic Simultaneous Localization and Mapping (SLAM). We design a prototype system integrating our matching and reconstruction algorithm on a remotely controlled navigation iRobot, equipped with a Kinect and a Raspberry Pi. Our reconstruction experiments demonstrate the effectiveness of our algorithm and design.

5. Conclusions

We presented a novel N-frame graph matching algorithm to handle partial matching for 3D reconstruction. The algorithm is effective for aligning data sets with relatively small overlap and is robust in handling noisy data obtained by low-cost scanner scanners such as Kinect and PrimeSense. We also develop an iRobot SLAM system to navigate and reconstruct a 3D indoor environment. The proposed N-frame graph matching model first extracts a set of N-corresponding tuples. Then the mutual spatial consistency of these features (among multiple frames), together with their descriptor similarity, is used to find an optimal correspondence among these features. Feature correspondences are then used to align and stitch frames together. Experiments show that our algorithm has better reliability than existing algorithms in the reconstruction of noisy and low-frame-rate 3D scans. Despite better accuracy and robustness, a limitation of multiframe matching is efficiency, especially when simultaneously matching many frames. Now that in 3D reconstruction, frames only differ by rigid transformations, the correct rate of the correspondence is more important than the number of corresponding pairs that are identified. Hence, increasing the similarity threshold of descriptors will suppress the size of initial correspondence set, and will greatly reduce the dimension of the affinity matrix. We also plan to explore better optimization strategies [50] and parallel implementation to improve the speed of matching computation.