Leaf detection and extraction system

US12520772B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-12520772-B2
Application numberUS-202318453908-A
CountryUS
Kind codeB2
Filing dateAug 22, 2023
Priority dateAug 22, 2022
Publication dateJan 13, 2026
Grant dateJan 13, 2026

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Disclosed herein is a system and methods for leaf detection and extraction. The extracted leaf may be used for leaf water potential analysis. In some embodiments, the method comprises identifying the leaf from a point cloud based on an image, determining a pose of the leaf based on the point cloud, and cutting and storing the leaf based on the pose of the leaf.

First claim

Opening claim text (preview).

What is claimed is: 1 . A computer-implemented method for collecting one or more leaves, comprising: receiving, from a camera, an image comprising a leaf; generating, based on the image, a point cloud; identifying a portion of the point cloud associated with the leaf; determining, based on the portion of the point cloud, a pose of the leaf, wherein: the pose comprises a position and an orientation of the leaf, an end-effector is aligned to the leaf based on the pose of the leaf, and a pneumatic subsystem is enabled; enclosing the leaf in a chamber of the end-effector, wherein, after the aligning the end-effector to the leaf, the chamber of the end-effector is moved toward the leaf to enclose the leaf; cutting, via a blade of the end-effector, a stem of the leaf; and storing the leaf in the chamber of the end-effector. 2 . The method of claim 1 , wherein: the end-effector is coupled to an arm; and the arm aligns the end-effector to the leaf and moves the end-effector toward the leaf. 3 . The method of claim 1 , wherein: the end-effector comprises the camera; and the camera takes images of the leaves as it moves toward the leaf. 4 . The method of claim 1 , wherein: the end-effector actuates a slider for occluding the chamber, wherein: the slider is coupled to the blade and a piston; and the piston actuates the slider and the blade. 5 . The method of claim 1 wherein: the end-effector actuates a gate for occluding the chamber, wherein: the gate is coupled to the blade and two four-bar linkages; and the two four-bar linkages actuate the gate and the blade. 6 . The method of claim 1 , wherein: the point cloud comprises a second portion, the second portion comprising points at distances greater than a threshold distance from the camera, and the method further comprises: identifying the second portion; and disregarding the second portion for the identifying the portion of the point cloud associated with the leaf. 7 . The method of claim 1 , wherein the identifying the portion of the point cloud associated with the leaf comprises: downsampling the portion of the point cloud; and clustering the portion of the point cloud. 8 . The method of claim 1 , wherein the determining the pose of the leaf comprises: bounding a clustered portion of the point cloud; and determining a center, dimensions, and orientation of the bounded cluster. 9 . The method of claim 1 , wherein the image comprises a second leaf, the method further comprising: identifying a second portion of the point cloud associated with the second leaf; determining, based on the second portion of the point cloud, a second pose of the second leaf, wherein: the second pose comprises a position and an orientation of the second leaf, and the end-effector is aligned to the second leaf based on the second pose of the second leaf; enclosing the second leaf in the chamber of the end-effector, wherein, after the aligning the end-effector to the second leaf, the chamber of the end-effector is moved toward the second leaf to enclose the second leaf; cutting, via the blade of the end-effector, a stem of the second leaf; and storing the second leaf in the chamber of the end-effector. 10 . The method of claim 9 , wherein the end-effector is aligned to the second leaf, suction is enabled, the end-effector is moved toward the second leaf, the stem of the second leaf is cut, and the second leaf is stored in accordance with a determination that the leaf is damaged. 11 . The method of claim 1 , wherein the pneumatic subsystem actuates suction within the end-effector using a solenoid, an air compressor, and an air tank. 12 . The method of claim 1 , further comprising: receiving, from the camera, a second image different from the image; generating, based on the second image, a second point cloud; and identifying a portion of the second point cloud, wherein the portion of the point cloud is associated with a second leaf. 13 . The method of claim 1 , wherein the determining the pose of the leaf further comprises identifying the stem of the leaf, a tip of the leaf, and a centroid of the leaf. 14 . An end-effector for collecting one or more leaves, comprising: a camera configured to take images of the leaves to send to the processor; a blade configured to cut the leaves; a chamber to encapsulate the leaves for cutting and storage; and one or more processors configured to cause the end-effector to perform the method of claim 1 . 15 . The end-effector of claim 14 , wherein a weight of the end-effector is less than 1.3 kg. 16 . The end-effector of claim 14 , wherein the chamber has a width of 110 mm, a height of 45 mm, and a depth of 185 mm. 17 . The end-effector of claim 14 , wherein a force for cutting the stem is 2.9-20 N, or operates at a pressure no greater than 120 psi. 18 . The end-effector of claim 14 , wherein the camera comprises a depth camera configured to provide images of the leaf to transmit to the processor for leaf detection. 19 . The end-effector of claim 14 , wherein: the end-effector further comprises a slider for occluding the chamber, the slider is coupled to the blade and a piston, and the piston is configured to actuate the slider and the blade. 20 . The end-effector of claim 14 , wherein: the end-effector further comprises a gate for occluding the chamber, the gate is coupled to the blade and two four-bar linkages, and the two four-bar linkages are configured to actuate the gate and the blade. 21 . A system for collecting one or more leaves, comprising: an end-effector comprising: a camera configured to take images of the one or more leaves to send to one or more processors; a blade configured to cut the one or more leaves; a chamber to encapsulate the one or more leaves for cutting and storage; and wherein the one or more processors are configured to cause the end-effector to perform the method of claim 1 ; a pneumatic system configured to use suction to align the one or more leaves; an arm coupled to the end-effector and configured to move the end-effector with six degrees of freedom; and a base coupled to the arm and comprising wheels. 22 . The system of claim 21 , wherein the pneumatic system comprises an air compressor, an air tank, and a solenoid.

Assignees

Inventors

Classifications

  • Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

  • Vegetation; Agriculture · CPC title

  • Range image; Depth image; 3D point clouds · CPC title

  • Vehicle exterior; Vicinity of vehicle · CPC title

  • Biomedical image inspection · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US12520772B2 cover?
Disclosed herein is a system and methods for leaf detection and extraction. The extracted leaf may be used for leaf water potential analysis. In some embodiments, the method comprises identifying the leaf from a point cloud based on an image, determining a pose of the leaf based on the point cloud, and cutting and storing the leaf based on the pose of the leaf.
Who is the assignee on this patent?
Univ California
What technology area does this patent fall under?
Primary CPC classification A01G3/00. Mapped technology areas include Human Necessities.
When was this patent published?
Publication date Tue Jan 13 2026 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 1 related publication on this page (citations in our corpus or others sharing the same primary CPC).