Real-Time Topology-Aware Branch Segmentation for UAV Perception in Natural Environments

Area of Science:

• Robotics
• Computer Vision
• Artificial Intelligence

Background:

• Autonomous UAVs require precise branch perception for forest navigation and inspection.
• Existing semantic segmentation methods struggle with branch topology and real-time performance on resource-constrained platforms.

Purpose of the Study:

• To develop a topology-aware branch perception framework for autonomous UAVs.
• To improve the accuracy, robustness, and real-time performance of branch segmentation and structural analysis in forest environments.

Main Methods:

• Introduced a Strip-Swift Pyramid Pooling Module (SSPPM) for enhanced elongated structure representation.
• Incorporated a reparameterized Golden Cudgel Block (GCBlock) and Boundary Optimization Module (BOM) for efficiency and boundary quality.
• Developed a topology-aware structural analysis module using skeleton-based connectivity analysis for junction and multi-branch removal.

Main Results:

• Achieved 89.94% mIoU on the Drone-Branch dataset.
• Demonstrated a stable inference latency of 13.7 ms on an NVIDIA Jetson Orin Nano with TensorRT acceleration.
• Post-processing structural analysis improved the reliability of extracted branch structures.

Conclusions:

• The proposed framework effectively enhances branch perception for UAVs in cluttered forest environments.
• The integration of semantic segmentation and structural topology analysis offers robust and consistent branch representation.
• The method is suitable for deployment on resource-constrained UAV platforms for critical environmental understanding tasks.