Comparing Commercial Depth Sensor Accuracy for Medical Applications

2026-06-11

AI Summary

This study addresses the optical challenges inherent in medical environments—such as homogeneous surfaces, specular reflections, and subsurface scattering—by presenting the first unified and reproducible accuracy benchmark of four leading commercial depth sensors (Intel RealSense D405, PMD Flexx2, ZED 2i, and Zivid 2M+ 60) on real biological tissues (porcine bone and abdominal wall) and a medical phantom (silicone kidney model). Using high-precision probe measurements as ground truth, depth estimation performance was systematically evaluated at an approximate working distance of 50 cm. Results demonstrate that the Zivid 2M+ 60 consistently achieves the highest accuracy across all test specimens and evaluation metrics, while the ZED 2i ranks second on real tissues but performs worst on the phantom. This work provides empirical guidance for depth sensor selection in medical robotics and intraoperative navigation systems.

Abstract

Depth estimation has numerous medical and surgical applications. We benchmark four depth sensors on a porcine bone specimen, a porcine belly specimen, and a silicone kidney phantom using stylus-sampled references. These objects contain several real-world challenges, including homogeneous surfaces, specular surfaces, and subsurface scattering. The comparison includes stereo, structured-light, and time-of-flight sensors at a distance of approximately 50 cm. Specifically, the Intel RealSense D405 (Intel RealSense, United States), PMD Flexx2 (pmdtechnologies, Germany), Stereolabs ZED 2i (Stereolabs, France), and Zivid 2M+ 60 (Zivid, Norway) are compared. The Zivid 2M+ 60 performed best across all objects and metrics considered in this work. The ZED ranked second for real tissue, but last on the phantom.

Problem

• depth sensor
• medical applications
• accuracy comparison
• specular surfaces
• subsurface scattering

Innovation

• depth sensing
• medical imaging
• sensor benchmarking
• structured light
• time-of-flight