Semantic segmentation for real time system

What is it about?

Convolutional Neural Networks (CNN) contributed considerable improvements for image segmentation tasks in the field of computer vision. Despite their success, an inherent challenge is the trade-off between accuracy and computational cost. The high computational efforts for large networks operating on the image’s pixel grid makes them ineligible for many real time applications such as various Advanced Driver Assistance Systems (ADAS). In this work, we propose a novel CNN approach, based on the combination of super-pixels and high dimensional feature channels applied for road segmentation. The core idea is to reduce the computational complexity by segmenting the image into homogeneous regions (superpixels) and feed image descriptors extracted from these regions into a CNN rather than working on the pixel grid directly. To enable the necessary convolutional operations on the irregular arranged superpixels, we introduce a lattice projection scheme as part of the superpixel creation method, which composes neighbourhood relations and forces the topology to stay fixed during the segmentation process. Reducing the input to the superpixel domain allows the CNN’s structure to stay small and efficient to compute while keeping the advantage of convolutional layers. The method is generic and can be easily generalized for segmentation tasks other than road segmentation.

Featured Image

Photo by Gabe Pierce on Unsplash

Photo by Gabe Pierce on Unsplash

Why is it important?

The high computational efforts for large networks operating on the image’s pixel grid makes them ineligible for many real time applications such as various Advanced Driver Assistance Systems (ADAS). In this work, we propose a novel CNN approach that greatly reduces the computational burden, while retaining high accuracy.