Homography Estimation with Convolutional Neural Networks Under Conditions of Variance

by   David Niblick, et al.

Planar homography estimation is foundational to many computer vision problems, such as Simultaneous Localization and Mapping (SLAM) and Augmented Reality (AR). However, conditions of high variance confound even the state-of-the-art algorithms. In this report, we analyze the performance of two recently published methods using Convolutional Neural Networks (CNNs) that are meant to replace the more traditional feature-matching based approaches to the estimation of homography. Our evaluation of the CNN based methods focuses particularly on measuring the performance under conditions of significant noise, illumination shift, and occlusion. We also measure the benefits of training CNNs to varying degrees of noise. Additionally, we compare the effect of using color images instead of grayscale images for inputs to CNNs. Finally, we compare the results against baseline feature-matching based homography estimation methods using SIFT, SURF, and ORB. We find that CNNs can be trained to be more robust against noise, but at a small cost to accuracy in the noiseless case. Additionally, CNNs perform significantly better in conditions of extreme variance than their feature-matching based counterparts. With regard to color inputs, we conclude that with no change in the CNN architecture to take advantage of the additional information in the color planes, the difference in performance using color inputs or grayscale inputs is negligible. About the CNNs trained with noise-corrupted inputs, we show that training a CNN to a specific magnitude of noise leads to a "Goldilocks Zone" with regard to the noise levels where that CNN performs best.



page 1

page 2

page 3

page 4


Analyzing the Performance of Multilayer Neural Networks for Object Recognition

In the last two years, convolutional neural networks (CNNs) have achieve...

SPP-Net: Deep Absolute Pose Regression with Synthetic Views

Image based localization is one of the important problems in computer vi...

On the Limitation of Convolutional Neural Networks in Recognizing Negative Images

Convolutional Neural Networks (CNNs) have achieved state-of-the-art perf...

Color Channel Perturbation Attacks for Fooling Convolutional Neural Networks and A Defense Against Such Attacks

The Convolutional Neural Networks (CNNs) have emerged as a very powerful...

Dense Color Constancy with Effective Edge Augmentation

Recently, computational color constancy via convolutional neural network...

Interactive Deep Colorization With Simultaneous Global and Local Inputs

Colorization methods using deep neural networks have become a recent tre...

Multimodal registration of FISH and nanoSIMS images using convolutional neural network models

Nanoscale secondary ion mass spectrometry (nanoSIMS) and fluorescence in...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.