GSR-PointNet++ with Dynamic Suppression for Point Cloud Semantic Segmentation in Multi-Tier Caged-Pigeon Houses

Abstract

Accurate 3D semantic perception is essential for robotic operations in multi-tier caged-pigeon houses, where dense cage-mounted facilities, repetitive layouts, local geometric similarity, and dynamic objects make static-facility segmentation difficult. To address these issues, this study proposes GSR-PointNet++, a point cloud semantic segmentation method with dynamic suppression. A Hierarchical Dynamic Suppression Front-End (HDS-Front) is introduced before static map construction to reduce dynamic interference caused by pigeon activity and human movement. Based on the processed static point clouds, a semantic segmentation dataset for multi-tier caged-pigeon houses is constructed. GSR-PointNet++ is developed on the PointNet++ backbone and incorporates a Geometric Structure-Relationship Module (GSRM), which models local normal consistency and spatial relationships to enhance feature representation in structurally repetitive scenes. Geometry-aware Prototype Consistency Learning (GPCL) is further introduced during training to improve class separability and prediction stability. Independent testing on the annotated dataset collected from the second pigeon house showed that the proposed method achieved a mean intersection over union (mIoU) of 96.29% ± 0.25% and an overall accuracy (OA) of 98.62% ± 0.13% for the four target facility classes, outperforming PointNet++ by 5.92 and 2.54 percentage points, respectively. These results indicate that the proposed method improves point cloud semantic segmentation for static facilities and has potential to support robotic perception in structured livestock environments.