Segmenting objects with Bayesian fusion of active contour models and convnet priors

TL;DR

This paper introduces a Bayesian active contour segmentation method tailored for natural resource monitoring imagery, integrating CNN-derived priors and novel deep shape models to improve contour accuracy of irregular objects like tree crowns.

Contribution

It presents a new Bayesian segmentation framework combining CNN priors with active contours and introduces Deep Shape Models based on GANs for shape prior, tailored for complex natural imagery.

Findings

Outperforms Mask R-CNN and K-net in tree crown segmentation accuracy.

GAN-based shape priors significantly improve contour reconstruction.

Method effectively handles irregular, overlapping natural objects.

Abstract

Instance segmentation is a core computer vision task with great practical significance. Recent advances, driven by large-scale benchmark datasets, have yielded good general-purpose Convolutional Neural Network (CNN)-based methods. Natural Resource Monitoring (NRM) utilizes remote sensing imagery with generally known scale and containing multiple overlapping instances of the same class, wherein the object contours are jagged and highly irregular. This is in stark contrast with the regular man-made objects found in classic benchmark datasets. We address this problem and propose a novel instance segmentation method geared towards NRM imagery. We formulate the problem as Bayesian maximum a posteriori inference which, in learning the individual object contours, incorporates shape, location, and position priors from state-of-the-art CNN architectures, driving a simultaneous level-set evolution of multiple object contours. We employ loose coupling between the CNNs that supply the priors and the active contour process, allowing a drop-in replacement of new network architectures. Moreover, we introduce a novel prior for contour shape, namely, a class of Deep Shape Models based on architectures from Generative Adversarial Networks (GANs). These Deep Shape Models are in essence a non-linear generalization of the classic Eigenshape formulation. In experiments, we tackle the challenging, real-world problem of segmenting individual dead tree crowns and delineating precise contours. We compare our method to two leading general-purpose instance segmentation methods - Mask R-CNN and K-net - on color infrared aerial imagery. Results show our approach to significantly outperform both methods in terms of reconstruction quality of tree crown contours. Furthermore, use of the GAN-based deep shape model prior yields significant improvement of all results over the vanilla Eigenshape prior.