Deploying a quantum annealing processor to detect tree cover in aerial imagery of California

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...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	PloS one Jg. 12; H. 2; S. e0172505
Hauptverfasser:	Boyda, Edward, Basu, Saikat, Ganguly, Sangram, Michaelis, Andrew, Mukhopadhyay, Supratik, Nemani, Ramakrishna R.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Public Library of Science 27.02.2017 Public Library of Science (PLoS)
Schlagworte:	Aerial photography Algorithms Analysis Artificial intelligence Biology and Life Sciences California Classification Classifiers Computer and Information Sciences Computer applications Computer science Computer vision Couplings Earth science Earth Sciences Engineering and Technology Environmental Monitoring - instrumentation Environmental Monitoring - methods Feature extraction Forests Hardware Image detection Image Processing, Computer-Assisted International conferences Linear Models Machine Learning Microprocessors Moon Neural networks Objective function Optimization People and places Phase transitions Physical Sciences Qubits (quantum computing) Remote sensing Remote Sensing Technology Reproducibility of Results Rescaling Research and Analysis Methods Scaling Simulated annealing (Mathematics) Software Technology application Texture Training Trees Valleys California
ISSN:	1932-6203, 1932-6203
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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.
Bibliographie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Conceptualization: EB SB SG AM RN.Data curation: SB SG AM.Formal analysis: EB SB SG.Funding acquisition: SG SM RN.Investigation: EB.Methodology: EB SB SG.Project administration: SG RN.Software: EB SB AM.Supervision: SM RN.Visualization: EB.Writing – original draft: EB.Writing – review & editing: EB SB SG AM RN. Competing Interests: The authors have declared that no competing interests exist.
ISSN:	1932-6203 1932-6203
DOI:	10.1371/journal.pone.0172505