Convolutions have long been regarded as fundamental to applied mathematics, physics and engineering. Their mathematical elegance allows for common tasks such as numerical differentiation to be computed efficiently on large data sets. Efficient computation of convolutions is critical to artificial intelligence in real-time applications, like machine vision, where convolutions must be continuously and efficiently computed on tens to hundreds of kilobytes per second. In this paper, we explore how convolutions are used in fundamental machine vision applications. We present an accelerated n-dimensional convolution package in the high performance computing language, Julia, and demonstrate its efficacy in solving the time to contact problem for machine vision. Results are measured against synthetically generated videos and quantitatively assessed according to their mean squared error from the ground truth. We achieve over an order of magnitude decrease in compute time and allocated memory for comparable machine vision applications. All code is packaged and integrated into the official Julia Package Manager to be used in various other scenarios.
[1]
Xin Zhang,et al.
End to End Learning for Self-Driving Cars
,
2016,
ArXiv.
[2]
M. Zwaan.
A handbook of fourier theorems
,
1990
.
[3]
Izhar Wallach,et al.
AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
,
2015,
ArXiv.
[4]
Eve A. Riskin,et al.
Signals, Systems, and Transforms
,
1994
.
[5]
G. T. Shrivakshan,et al.
A Comparison of various Edge Detection Techniques used in Image Processing
,
2012
.
[6]
B.K.P. Horn,et al.
Time to Contact Relative to a Planar Surface
,
2007,
2007 IEEE Intelligent Vehicles Symposium.
[7]
Lawrence D. Jackel,et al.
Backpropagation Applied to Handwritten Zip Code Recognition
,
1989,
Neural Computation.
[8]
Berthold K. P. Horn,et al.
Determining Optical Flow
,
1981,
Other Conferences.
[9]
C. Chandrasekar,et al.
A Comparison of various Edge Detection Techniques used in Image Processing
,
2012
.
[10]
Sean Hayes,et al.
View synthesis by trinocular edge matching and transfer
,
2000,
Image Vis. Comput..