Seminar: Adapting CNNs for Fisheye Cameras without Retraining, 6th June, 1:00pm

When: Thursday 6th of June, 1:00pm AEST

Where: This seminar will be partially presented at the ACFR seminar area, J04 lvl 2 (Rose St Building) and partially online via Zoom. RSVP

Title: Adapting CNNs for Fisheye Cameras without Retraining

Abstract:

The majority of image processing approaches assume images are in or can be rectified to a perspective projection. However, in many applications it is beneficial to use non-conventional cameras, such as fisheye cameras, that have a larger field of view (FOV). The issue arises that these large-FOV images can’t be rectified to a perspective projection without significant cropping of the original image. To address this issue, we propose Rectified Convolutions (RectConv); a new approach for adapting pre-trained convolutional networks to operate with new non-perspective images, without any retraining. Replacing the convolutional layers of the network with RectConv layers allows the network to see both rectified patches and the entire FOV. Our approach requires no additional data or training, and operates directly on the native image as captured from the camera. We believe this work is a step toward adapting the vast resources available for perspective images to operate across a broad range of camera geometries.

Bio:

Ryan Griffiths is a final year PhD student at the ACFR. He completed his undergraduate degree in Mechatronics at the University of Sydney in 2020, then joined the ACFR to complete a PhD under Donald Dansereau. Ryans research interest includes novel cameras and how we can use machine learning to be able to deploy them in robotic applications.