Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything

TL;DR

Measure Anything is a vision-based framework that accurately estimates object dimensions like diameter and length in real-time, using segmentation and skeleton analysis, demonstrated on agricultural and robotic applications.

Contribution

It introduces a novel, integrated approach leveraging SAM for real-time dimensional measurement of objects with complex geometries, enabling automation and scalability.

Findings

Successfully measured Canola stem diameters in the field

Extended framework to robotic grasping applications

Achieved accurate, real-time geometric estimations

Abstract

We present Measure Anything, a comprehensive vision-based framework for dimensional measurement of objects with circular cross-sections, leveraging the Segment Anything Model (SAM). Our approach estimates key geometric features -- including diameter, length, and volume -- for rod-like geometries with varying curvature and general objects with constant skeleton slope. The framework integrates segmentation, mask processing, skeleton construction, and 2D-3D transformation, packaged in a user-friendly interface. We validate our framework by estimating the diameters of Canola stems -- collected from agricultural fields in North Dakota -- which are thin and non-uniform, posing challenges for existing methods. Measuring its diameters is critical, as it is a phenotypic traits that correlates with the health and yield of Canola crops. This application also exemplifies the potential of Measure Anything, where integrating intelligent models -- such as keypoint detection -- extends its scalability to fully automate the measurement process for high-throughput applications. Furthermore, we showcase its versatility in robotic grasping, leveraging extracted geometric features to identify optimal grasp points.