Progressive Large Scale-Invariant Image Matching in Scale Space

2017 ◽  
Author(s):  
Lei Zhou ◽  
Siyu Zhu ◽  
Tianwei Shen ◽  
Jinglu Wang ◽  
Tian Fang ◽  
...  
Keyword(s):  
Image Matching ◽  
Large Scale ◽  
Scale Space ◽  
Scale Invariant

scholarly journals Scale-Covariant and Scale-Invariant Gaussian Derivative Networks

2021 ◽  
Author(s):  
Tony Lindeberg
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Large Scale ◽  
Hybrid Approach ◽  
Multiple Scale ◽  
Scale Space ◽  
Training Data ◽  
Scale Invariant ◽  
Gaussian Derivative ◽  
Space Operations

AbstractThis paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale channels, and by using the transformation properties of the scale-space primitives under scaling transformations, the resulting network becomes provably scale covariant. By in addition performing max pooling over the multiple scale channels, or other permutation-invariant pooling over scales, a resulting network architecture for image classification also becomes provably scale invariant. We investigate the performance of such networks on the MNIST Large Scale dataset, which contains rescaled images from the original MNIST dataset over a factor of 4 concerning training data and over a factor of 16 concerning testing data. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not spanned by the training data.

Capture Strategy Based on a Distributed Control System for a Large-scale Space End-Effector

ROBOT ◽  
2011 ◽  
Vol 33 (4) ◽  
pp. 434-439 ◽  
Author(s):  
Dangyang JIE ◽  
Fenglei NI ◽  
Yisong TAN ◽  
Hong LIU ◽  
Hegao CAI
Keyword(s):  
Control System ◽  
Distributed Control ◽  
Large Scale ◽  
Scale Space ◽  
Distributed Control System ◽  
End Effector

scholarly journals Real-time FPGA-based implementation of the AKAZE algorithm with nonlinear scale space generation using image partitioning

2021 ◽  
Author(s):  
Parastoo Soleimani ◽  
David W. Capson ◽  
Kin Fun Li
Keyword(s):  
Real Time ◽  
Memory Management ◽  
Scale Space ◽  
Image Resolution ◽  
Hardware Architecture ◽  
Frame Rate ◽  
Time Sharing ◽  
Scale Invariant ◽  
Nonlinear Scale Space ◽  
Nonlinear Scale

AbstractThe first step in a scale invariant image matching system is scale space generation. Nonlinear scale space generation algorithms such as AKAZE, reduce noise and distortion in different scales while retaining the borders and key-points of the image. An FPGA-based hardware architecture for AKAZE nonlinear scale space generation is proposed to speed up this algorithm for real-time applications. The three contributions of this work are (1) mapping the two passes of the AKAZE algorithm onto a hardware architecture that realizes parallel processing of multiple sections, (2) multi-scale line buffers which can be used for different scales, and (3) a time-sharing mechanism in the memory management unit to process multiple sections of the image in parallel. We propose a time-sharing mechanism for memory management to prevent artifacts as a result of separating the process of image partitioning. We also use approximations in the algorithm to make hardware implementation more efficient while maintaining the repeatability of the detection. A frame rate of 304 frames per second for a $$1280 \times 768$$ 1280 × 768 image resolution is achieved which is favorably faster in comparison with other work.

Scaling Analyses for Large-Scale Space-Based Membrane Optics

AIAA Journal ◽  
2011 ◽  
Vol 49 (7) ◽  
pp. 1313-1323 ◽  
Author(s):  
Michael J. Shepherd ◽  
Richard G. Cobb ◽  
Anthony N. Palazotto ◽  
William P. Baker
Keyword(s):  
Large Scale ◽  
Scale Space ◽  
Scaling Analyses

Piezoelectric polymers actuators for precise shape control of large scale space antennas

2007 ◽  
Author(s):  
Qin Chen ◽  
Don Natale ◽  
Bret Neese ◽  
Kailiang Ren ◽  
Minren Lin ◽  
...  
Keyword(s):  
Shape Control ◽  
Large Scale ◽  
Scale Space ◽  
Piezoelectric Polymers ◽  
Space Antennas ◽  
Precise Shape

Technological Imaginaries, Feasibilities, Syndromes, and Catastrophes

Dark Skies ◽  
2020 ◽  
pp. 104-142
Author(s):  
Daniel Deudney
Keyword(s):  
Genetic Engineering ◽  
Science Fiction ◽  
Technology Assessment ◽  
Large Scale ◽  
New Technologies ◽  
Scale Space ◽  
Technology Governance ◽  
Existential Risk ◽  
Space Colonization ◽  
Space Activities

Space expansionism, science fiction, and space developments are intimately linked. SF from Verne, Wells, and others inspires space expansionists, and SF is shaped by space discoveries. SF makes space expansionism seem plausible but is often unbound by scientific possibility. An assessment of building block, life-engineering, and transformative technologies reveals that large-scale space activities are becoming more feasible, but creating enclosed ecologies, geo-engineering and terraforming remain doubtful. Anticipating the consequences of new technologies (technology assessment) remains difficult. Technology governance is plagued by recalcitrant syndromes. Theorists of catastrophic and existential risk view space colonization as necessary to escape a long list of possible major calamities (including hostile artificial superintelligence and misused genetic engineering for improved humans, called transhumanism). Human survival increasingly depends on competent futurism and social capacities to steer technology with reversals, regulations, and relinquishments, but these are difficult to establish and maintain. Can vital arrangements of restraint survive large-scale space expansion?

Sign in / Sign up

Export Citation Format

Share Document