Surgical tooltip localization via concentric nested square markers and depth-RGB multi-coordinate fusion

Area of Science:

• Computer Vision
• Robotics
• Surgical Navigation

Background:

• Accurate tooltip localization is essential for surgical navigation and precision tasks.
• Traditional ArUco marker systems face challenges with detection stability and accuracy under varied tool poses.

Purpose of the Study:

• Propose a novel real-time localization method using concentric nested square markers.
• Enhance robustness and spatial accuracy through geometric marker enhancement and multi-coordinate frame fusion.

Main Methods:

• Developed a marker integrating an ArUco code within a nested square structure for multi-frame pose estimation.
• Fused poses from both structures, with optional depth data, for tooltip localization.
• Utilized a cubic calibration object for ground-truth establishment and conducted experiments under varied conditions.

Main Results:

• Achieved up to 40.1% improvement in average localization accuracy compared to standard ArUco markers.
• Depth fusion reduced average error to 1.55 mm and improved stability.
• Demonstrated superior performance against AprilTag, QR Code, and calibration patterns.

Conclusions:

• The proposed method provides a robust, compact, and accurate localization solution for common camera systems.
• Enhanced performance in diverse tool poses makes it suitable for real-world surgical applications.
• Source code is publicly available for further research and development.