Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection

TL;DR

This paper introduces a deep learning model that combines semantic segmentation with boundary detection to improve the accuracy of remote sensing image analysis, especially around object edges.

Contribution

It proposes a novel approach integrating boundary detection into existing CNN architectures to enhance segmentation quality, particularly at object boundaries.

Findings

Boundary detection improves segmentation accuracy.

The ensemble achieves over 90% accuracy on a benchmark.

The method effectively preserves high-frequency boundary details.

Abstract

We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to accumulate contextual information over very large windows (receptive fields). However, this success comes at a cost, since the associated loss of effecive spatial resolution washes out high-frequency details and leads to blurry object boundaries. Here, we propose to counter this effect by combining semantic segmentation with semantically informed edge detection, thus making class-boundaries explicit in the model, First, we construct a comparatively simple, memory-efficient model by adding boundary detection to the Segnet encoder-decoder architecture. Second, we also include boundary detection in FCN-type models and set up a high-end classifier ensemble. We show that boundary detection significantly improves semantic segmentation with CNNs. Our high-end ensemble achieves > 90% overall accuracy on the ISPRS Vaihingen benchmark.