Ginger seed picking system and method based on depth camera and mechanical arm

By combining a depth camera and a robotic arm, high-precision identification and automatic seed collection of ginger seeds were achieved, solving the problem of ginger sprout orientation deviation and improving the intelligence and automation of ginger planting.

CN121264243BActive Publication Date: 2026-06-02BEIJING UNIV OF POSTS & TELECOMM
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING UNIV OF POSTS & TELECOMM
Filing Date
2025-11-04
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

In the current ginger planting process, the orientation of ginger sprouts is prone to deviation, which limits the level of intelligence in mechanized planting, increases labor costs, and makes it difficult to achieve fully automated planting.

Method used

A ginger seed extraction system based on a depth camera and a robotic arm is adopted. The depth camera identifies the three-dimensional centroid coordinates and orientation of the ginger seed, and combined with the inverse kinematics model of the robotic arm, it can achieve accurate identification of the ginger rhizome posture and automatic seed extraction.

Benefits of technology

It has achieved high-precision identification and automatic seed extraction of ginger seeds, improving the intelligence and automation level of ginger cultivation and reducing the need for manual intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121264243B_ABST
    Figure CN121264243B_ABST
Patent Text Reader

Abstract

The application belongs to the field of agricultural automation, and discloses a ginger seed taking system and method based on a depth camera and a mechanical arm. The system comprises a depth camera, a mechanical arm actuator, a terminal adsorption device, a power supply module, a control communication module and a PC host computer. The depth camera is used to collect images of a ginger seed stacking area. The host computer extracts the three-dimensional pose of a target ginger block by using an instance segmentation model and a spatial positioning algorithm, and controls the mechanical arm based on inverse kinematics to achieve precise seed taking. The terminal adsorption device is composed of an air pipe and an elastic sponge, and is matched with an electric air compressor to generate negative pressure adsorption force. The adsorption control is realized by a USB relay module. The method aims to solve the problems of low efficiency, poor recognition accuracy and high labor intensity of the existing manual seed taking. The method realizes accurate identification, seed taking and direction adjustment and placement of the stacked fresh ginger in the box by the mechanical arm, and is suitable for intelligent seeding and agricultural automatic seed taking scenes.
Need to check novelty before this filing date? Find Prior Art