Deploying a quantum annealing processor to detect tree cover in aerial imagery of California.
Deploying a quantum annealing processor to detect tree cover in aerial imagery of California.
复制标题
DOI：
10.1371/journal.pone.0172505
复制
发表时间：
2017
期刊：
影响因子：
3.7
通讯作者：
Nemani RR
中科院分区：
文献类型：
--
作者：
Boyda E;Basu S;Ganguly S;Michaelis A;Mukhopadhyay S;Nemani RR
量子退火是一种实验性的和潜在的突破性计算技术，用于处理困难的优化问题，包括计算机视觉问题。我们提出了一个案例研究，在培训的生产规模分类器的遥感图像中的树木覆盖，使用早期的量子退火硬件建造的D波系统公司。在一个已知的提升框架内开始，我们训练决策树桩纹理特征和植被指数从四波段，一米分辨率的航空影像从加州的状态。然后，我们施加一个调节二次训练目标，从这些树桩中选择一个最佳的投票子集。子集的投票定义分类器。为了优化，目标函数中的逻辑变量映射到硬件设备中的量子比特，而二次耦合编码为量子比特之间的物理相互作用的强度。硬件设计将这些基本物理实体之间的耦合数量限制为五个或六个。为了解决将大型问题映射到硬件架构的限制，我们提出了通过可训练元模型对训练目标进行截断和重新缩放。我们的基本108和508变量的问题，从而构成的提升过程中，返回分类器，结合了各种各样的颜色和纹理为基础的指标和歧视树覆盖的准确性高达92%的验证和90%的测试场景，包括开放空间保护区和密集的郊区建设的米尔谷，加利福尼亚州。
Quantum annealing is an experimental and potentially breakthrough computational technology for handling hard optimization problems, including problems of computer vision. We present a case study in training a production-scale classifier of tree cover in remote sensing imagery, using early-generation quantum annealing hardware built by D-wave Systems, Inc. Beginning within a known boosting framework, we train decision stumps on texture features and vegetation indices extracted from four-band, one-meter-resolution aerial imagery from the state of California. We then impose a regulated quadratic training objective to select an optimal voting subset from among these stumps. The votes of the subset define the classifier. For optimization, the logical variables in the objective function map to quantum bits in the hardware device, while quadratic couplings encode as the strength of physical interactions between the quantum bits. Hardware design limits the number of couplings between these basic physical entities to five or six. To account for this limitation in mapping large problems to the hardware architecture, we propose a truncation and rescaling of the training objective through a trainable metaparameter. The boosting process on our basic 108- and 508-variable problems, thus constituted, returns classifiers that incorporate a diverse range of color- and texture-based metrics and discriminate tree cover with accuracies as high as 92% in validation and 90% on a test scene encompassing the open space preserves and dense suburban build of Mill Valley, CA.