Evaluating saliency scores in point clouds of natural environments by learning surface anomalies

TL;DR

This paper introduces a learning-based method using deep neural networks to detect salient objects in natural environment point clouds by identifying surface anomalies through reconstruction errors, effectively handling noise and textures.

Contribution

It presents a novel deep learning approach that learns surface models and detects anomalies as salient objects in noisy, textured natural environment point clouds.

Findings

Strong correlation between reconstruction error and salient objects

Effective detection of surface anomalies in diverse natural scenarios

Robustness to noise and textures in point cloud data

Abstract

In recent years, three-dimensional point clouds are used increasingly to document natural environments. Each dataset contains a diverse set of objects, at varying shapes and sizes, distributed throughout the data and intricately intertwined with the topography. Therefore, regions of interest are difficult to find and consequent analyses become a challenge. Inspired from visual perception principles, we propose to differentiate objects of interest from the cluttered environment by evaluating how much they stand out from their surroundings, i.e., their geometric salience. Previous saliency detection approaches suggested mostly handcrafted attributes for the task. However, such methods fail when the data are too noisy or have high levels of texture. Here we propose a learning-based mechanism that accommodates noise and textured surfaces. We assume that within the natural environment any change from the prevalent surface would suggest a salient object. Thus, we first learn the underlying surface and then search for anomalies within it. Initially, a deep neural network is trained to reconstruct the surface. Regions where the reconstructed part deviates significantly from the original point cloud yield a substantial reconstruction error, signifying an anomaly, i.e., saliency. We demonstrate the effectiveness of the proposed approach by searching for salient features in various natural scenarios, which were acquired by different acquisition platforms. We show the strong correlation between the reconstruction error and salient objects.