thumbnail

Topic

Technologies and technical equipment for agriculture and food industry

Volume

Volume 75 / No. 1 / 2025

Pages : 1193-1206

Metrics

Volume viewed 0 times

Volume downloaded 0 times

POINTNET++LR3D: AN IMPROVED POINTNET++ MODEL FOR INDIVIDUAL IDENTIFICATION OF PIG BACK POINT CLOUD

POINTNET++LR3D:一种改进的POINTNET++模型用于猪背点云个体识别

DOI : https://doi.org/10.35633/inmateh-75-98

Authors

Yongshuai YANG

College of Software, Shanxi Agricultural University

Yaqi YAN

College of Software, Shanxi Agricultural University

Yuhang LI

College of Software, Shanxi Agricultural University

Jiarui ZHANG

College of Software, Shanxi Agricultural University

Xiaochan GAO

College of Software, Shanxi Agricultural University

Jie HU

College of Software, Shanxi Agricultural University

(*) Juan LIU

Department of Basic Sciences, Shanxi Agricultural University, Taigu, Shanxi / China

(*) Corresponding authors:

liujuannk@sxau.edu.cn |

Juan LIU

Abstract

Individual pig identification is a key technology to realize fine farming management, which is of great value in the fields of animal behaviour tracking and health monitoring. Aiming at the limitations of traditional 2D vision methods in stereo feature extraction, this study uses pig back point cloud to effectively capture deep 3D features such as back contour and skin texture and proposes an improved PointNet++ model for pig individual identification, which explicitly captures the local geometric and feature differences through two-stream differential coding, refines the feature distribution by using low-rank bilinear decomposition and residual sharpening strategies, and then establish the two-way dependency between channel and space to generate the global perceptual map, and finally combine with Mish activation function to enhance the nonlinear feature extraction. The experiment takes the hybrid long white pig as the research object and uses the Intel D435i depth camera to collect data and construct the segmentation and identification model. The results show that the improved model PointNet++LR3D achieves an overall accuracy of 97.11% in the individual identification task, which is an improvement of 1.9% compared to the base PointNet++MSG model. In addition, extended tests on the ModelNet40 dataset show an improvement in classification accuracy to 93.1%, validating the generalization ability of the architectural improvements. This study provides an efficient solution for non-contact pig identification based on point cloud, demonstrating the potential for application in fine-tuned farming.

Abstract in Chinese

猪只个体识别是实现精细化养殖管理的关键技术,在动物行为追踪、健康监测等领域具有重要价值。针对传统二维视觉方法在立体特征提取上的局限性,本研究使用猪背点云有效捕捉背部轮廓和皮肤纹理等深度三维特征,提出了一种改进的PointNet++模型用于猪只个体识别,通过双流差分编码显式捕捉局部几何与特征差异,利用低秩双线性分解和残差锐化策略细化特征分布,进而建立通道与空间的双向依赖关系生成全局感知图,最后结合Mish激活函数增强非线性特征提取。实验以杂交长白猪为研究对象,使用Intel D435i深度相机采集数据,构建分割与识别模型。结果表明,改进模型PointNet++LR3D在个体识别任务中整体准确率达97.11%,相比基础PointNet++MSG模型提升1.9%。此外,在ModelNet40数据集上的扩展测试显示分类准确率提升至93.1%,验证了架构改进的泛化能力。本研究为基于点云的非接触式猪只识别提供了高效解决方案,展现了在精细化养殖中的应用潜力。

Indexed in

Clarivate Analytics.
 Emerging Sources Citation Index
Scopus/Elsevier
Google Scholar
Crossref
Road