DIVESPOT: Depth Integrated Volume Estimation of Pile of Things Based on Point Cloud

TL;DR

DIVESPOT is a novel point cloud-based method for non-contact volume estimation of pile objects, addressing challenges like unstable poses, light interference, and computational load with innovative algorithms, achieving high accuracy without training data.

Contribution

The paper introduces DIVESPOT, a new approach combining pose correction, RGB-independent ground feature extraction, and voxel compression for efficient volume estimation.

Findings

Volume estimation error within 2% without training data

Achieves under 3% error with 90% voxel compression

Effective in unstable measurement and light interference conditions

Abstract

Non-contact volume estimation of pile-type objects has considerable potential in industrial scenarios, including grain, coal, mining, and stone materials. However, using existing method for these scenarios is challenged by unstable measurement poses, significant light interference, the difficulty of training data collection, and the computational burden brought by large piles. To address the above issues, we propose the Depth Integrated Volume EStimation of Pile Of Things (DIVESPOT) based on point cloud technology in this study. For the challenges of unstable measurement poses, the point cloud pose correction and filtering algorithm is designed based on the Random Sample Consensus (RANSAC) and the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). To cope with light interference and to avoid the relying on training data, the height-distribution-based ground feature extraction algorithm is proposed to achieve RGB-independent. To reduce the computational burden, the storage space optimizing strategy is developed, such that accurate estimation can be acquired by using compressed voxels. Experimental results demonstrate that the DIVESPOT method enables non-data-driven, RGB-independent segmentation of pile point clouds, maintaining a volume calculation relative error within 2%. Even with 90% compression of the voxel mesh, the average error of the results can be under 3%.