Semantic keypoint extraction for scanned animals using multi-depth-camera systems

TL;DR

This paper introduces a novel semantic keypoint extraction method for animal point clouds using multi-depth-camera systems, reformulating the task as a regression problem on the point cloud manifold with data augmentation and deformation techniques.

Contribution

It presents a new approach that models keypoint extraction as a regression problem using RBFs and an encoder-decoder architecture, tailored for multi-camera animal data.

Findings

Effective keypoint annotation on moving cattle

Robustness to calibration noise and camera dropout

Suitable for real-world agricultural robotics applications

Abstract

Keypoint annotation in point clouds is an important task for 3D reconstruction, object tracking and alignment, in particular in deformable or moving scenes. In the context of agriculture robotics, it is a critical task for livestock automation to work toward condition assessment or behaviour recognition. In this work, we propose a novel approach for semantic keypoint annotation in point clouds, by reformulating the keypoint extraction as a regression problem of the distance between the keypoints and the rest of the point cloud. We use the distance on the point cloud manifold mapped into a radial basis function (RBF), which is then learned using an encoder-decoder architecture. Special consideration is given to the data augmentation specific to multi-depth-camera systems by considering noise over the extrinsic calibration and camera frame dropout. Additionally, we investigate computationally efficient non-rigid deformation methods that can be applied to animal point clouds. Our method is tested on data collected in the field, on moving beef cattle, with a calibrated system of multiple hardware-synchronised RGB-D cameras.