US 12,597,161 B2Granted

Systems and methods for object tracking and location prediction

AssigneeCarbon Autonomous Robotic Systems Inc.

InventorsRaven Pillmann, Simon Cochrane, Brian Phillip Stark, Alexander Igorevich Sergeev

Life of this patent

Estimating the term…

Loading patent…

Abstract

Disclosed herein are methods, devices, modules, and systems which may be employed to accurately track, and subsequently target, objects of interest relative to a moving body, such as a vehicle. An object tracking method may be implemented by a detection system with a sensor coupled to the moving body. A targeting system may be used to target objects tracked by the detection system, such as for automated crop cultivation or maintenance. Devices disclosed herein may be configured to locate, identify, and autonomously target a weed with a beam, such as a laser beam, which may burn or irradiate the weed. The methods, devices, modules, and systems may be used for agricultural crop management or for at-home weed control.

Claims32

Dependent claims

A method of tracking objects relative to a moving vehicle, the method comprising:

receiving, from an imaging sensor, a first image capturing a first region at a first time;
determining, in the first image, a first set of actual locations for a first set of objects relative to a moving vehicle;
receiving, from the imaging sensor, a second image capturing a second region at a second time, wherein the second region includes at least a portion of the first region;
determining, in the second image, a second set of actual locations for a second set of objects relative to the moving vehicle, wherein the second set of objects includes one or more of the same objects as the first set of objects;
identifying a tracked object included in the first set of objects;
applying a predicted shift to a first actual location of the tracked object in the first image at the first time to produce a shifted location of the tracked object at the second time;
designating a search area;
selecting a second actual location of the tracked object in the second image from the second set of objects in the second image at the second time from the second set of actual locations, wherein the second actual location of the tracked object in the second image at the second time is within the search area;
determining a vector displacement of the tracked object between the first time and the second time from the first actual location of the tracked object in the first image at the first time and the second actual location of the tracked object in the second image at the second time;
predicting a location of the tracked object based at least in part on the vector displacement, and
manipulating the tracked object at the predicted location.

8 more elements

A method of tracking objects relative to a moving vehicle, the method comprising:

receiving, from an imaging sensor, a first image capturing a first region at a first time,
determining, in the first image, a first set of actual locations for a first set of objects relative to the moving vehicle;
receiving, from the imaging sensor, a second image capturing a second region at a second time, wherein the second region includes at least a portion of the first region,
determining, in the second image, a second set of actual locations for a second set of objects relative to the moving vehicle, wherein the second set of objects includes one or more of the same objects as the first set of objects;
applying a plurality of test shifts to the first set of actual locations for the first set of objects to obtain a set of test locations for the first set of objects at the second time, wherein each test shift of the plurality of test shifts is determined based on a distance between a first actual location of a first object at the first time and a second actual location of a second object at the second time;
determining a plurality of offsets between each of the test locations of the set of test locations for the first set of objects at the second time and each of the second set of actual locations for the second set of objects at the second time, wherein each offset of the plurality of offsets corresponds to a test shift of the plurality of test shifts;
selecting a refined shift from the plurality of test shifts based on the plurality of offsets;
identifying the tracked object included in both the first set of objects and the second set of objects;
predicting a loco cation of the tracked object;
and
manipulating the tracked object at the predicted location.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 18/098,540Filed 18 Jan 2023 · us provisional application
Priority: 19 Jan 2022
Published: US 2023/0237697 A127 Jul 2023
Granted: 7 Apr 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification15 codes

G06T 7/246
Analysis of motion: using feature-based methods, e.g. the tracking of corners or segments
G06T 7/74
Using feature-based methods: involving reference images or patches
A01G 2/00
Vegetative propagation
G06V 10/82
Using pattern recognition or machine learning: using neural networks