[论文解读] Parallel Structure from Motion for UAV Images via Weighted Connected Dominating Set

San Ping Jiang, Qingquan Li+2 more|arXiv (Cornell University)|Jun 23, 2022

Robotics and Sensor-Based Localization被引用 4

一句话总结

该论文提出了一种基于加权连通支配集（WCDS）的并行结构光束法（SfM）框架，用于无人机（UAV）影像，通过提取全局几何模型实现高效聚类合并。通过利用词汇树匹配方法以及一种新型WCDS算法（该算法考虑了特征匹配分布的边权重），该方法在保持相近定向精度的同时，相比串行SfM实现了17.4倍的加速，地理参照误差在水平和垂直方向上约为地面采样距离（GSD）的2.0–3.0倍。

ABSTRACT

Incremental Structure from Motion (ISfM) has been widely used for UAV image orientation. Its efficiency, however, decreases dramatically due to the sequential constraint. Although the divide-and-conquer strategy has been utilized for efficiency improvement, cluster merging becomes difficult or depends on seriously designed overlap structures. This paper proposes an algorithm to extract the global model for cluster merging and designs a parallel SfM solution to achieve efficient and accurate UAV image orientation. First, based on vocabulary tree retrieval, match pairs are selected to construct an undirected weighted match graph, whose edge weights are calculated by considering both the number and distribution of feature matches. Second, an algorithm, termed weighted connected dominating set (WCDS), is designed to achieve the simplification of the match graph and build the global model, which incorporates the edge weight in the graph node selection and enables the successful reconstruction of the global model. Third, the match graph is simultaneously divided into compact and non-overlapped clusters. After the parallel reconstruction, cluster merging is conducted with the aid of common 3D points between the global and cluster models. Finally, by using three UAV datasets that are captured by classical oblique and recent optimized views photogrammetry, the validation of the proposed solution is verified through comprehensive analysis and comparison. The experimental results demonstrate that the proposed parallel SfM can achieve 17.4 times efficiency improvement and comparative orientation accuracy. In absolute BA, the geo-referencing accuracy is approximately 2.0 and 3.0 times the GSD (Ground Sampling Distance) value in the horizontal and vertical directions, respectively. For parallel SfM, the proposed solution is a more reliable alternative.

研究动机与目标

• 为解决由于串行处理限制导致的增量式SfM在无人机影像处理中效率低下的瓶颈问题。
• 通过引入对重叠结构变化具有鲁棒性的全局几何约束，改进分治法SfM中的聚类合并。
• 开发一种可扩展的并行SfM流水线，在显著减少计算时间的同时保持高精度。
• 通过轻量但高效的全局模型提取方法，实现可靠的大规模无人机三维重建。

提出的方法

• 从基于词汇树的图像检索构建无向加权匹配图，其中边权重反映特征匹配的数量及其空间分布。
• 设计一种加权连通支配集（WCDS）算法，基于边权重和冗余性选择关键节点（影像），以形成紧凑且连通的全局模型。
• 利用全局模型作为参考，将匹配图划分为紧凑且非重叠的聚类，以实现并行SfM重建。
• 通过识别全局模型与单个聚类重建之间的公共三维点，完成聚类合并。
• 应用包含地面控制点（GCPs）的绝对束调整以评估地理参照精度，使用残差统计进行对比。
• 通过最小化冗余处理并聚焦于最终束调整中的高价值轨迹，优化整个流水线。

实验结果

研究问题

• RQ1 通过WCDS提取的全局模型是否能提升并行SfM中无人机影像聚类合并的准确性和鲁棒性？
• RQ2 所提出的基于WCDS的全局模型在重建效率和精度方面与现有方法相比如何？
• RQ3 所提出的并行SfM解决方案在多大程度上减少了计算时间，同时保持定向精度？
• RQ4 全局模型如何影响大规模无人机数据集中地理参照残差的分布和质量？

主要发现

• 所提出的并行SfM相比串行SfM实现了17.4倍的加速，显著提升了处理效率。
• 该方法的地理参照精度在水平和垂直方向上分别约为地面采样距离（GSD）的2.0倍和3.0倍。
• 在绝对束调整中，该方法的精度与ColMap和Pix4Dmapper等先进工具相当，X和Y方向的残差标准差分别为0.020 m和0.024 m。
• 基于WCDS的全局模型实现了更均匀分布的残差，并在重叠结构变化的情况下仍能实现鲁棒的合并。
• 约20%的影像被保留用于构建全局模型，这在极大规模数据集上可能限制可扩展性。
• 约一半的总时间用于场景合并和最终束调整，表明在相似性变换和轨迹选择方面仍有优化空间。