Scene Understanding

Scene understanding is a fundamental task in computer vision which requires understanding the scene’s geometry and semantic structure. Initially, I worked on a semantic segmentation algorithm called SegNet. More recently, I’ve been interested in learning depth, instance and semantic segmentation from a unified deep learning architecture.

image-center


Bayesian Deep Learning

Deep learning is great for achieving state-of-the-art results, however these models can’t understand what they don’t know. Bayesian deep learning (BDL) is a very exciting framework for understanding our model’s uncertainty. This paper is an introduction to Bayesian deep learning for computer vision. I’ve also found BDL useful for localisation and scene understanding.

Input Image Semantic Segmentation Uncertainty
Bayesian deep learning for semantic segmentation. From left to right: input image, semantic segmentaion and model uncertainty.

Localisation

PoseNet is an algorithm for relocalisation - estimating the position and orientation of the camera from an image within a previously explored area. It works over large outdoor urban environments or inside buildings. It takes only 5ms to do this from a single colour image, here is a demo.

Check out some 3D reconstructions of King’s College and central Cambridge in your web browser.

image-center


Other Projects

Some more details of other projects, including an autonomous drone and augmented reality, can be found here.