FIELD: information technology.
SUBSTANCE: invention relates to means of optical identification of objects. Method includes obtaining a digital image containing data representing a weed at an early stage of development in a natural environment among the cultivated crop, together with associated metadata, outlining the leaf areas, and determining whether the weed is a single-nucleated plant or a double-seed plant. Besides, method includes detection of weed development stage, detection of weed type identified by weed name and probability of detection accuracy, using at least one of a plurality of obtained metadata and a plurality of metadata detected during contouring, during detection, whether the weed is a single-nucleus plant or a double-seed plant, and during detection of stage of development of weeds, as input parameters for a set of classifiers having access to data storage system, containing names of types of weeds together with multiple sets of metadata for each type of weed.
EFFECT: technical result consists in improvement of accuracy of determination of weeds in natural environment.
15 cl, 9 dwg
Title | Year | Author | Number |
---|---|---|---|
WEED DETECTION IN NATURAL ENVIRONMENT | 2017 |
|
RU2764872C2 |
GRAIN FIELD YIELD PREDICTION | 2017 |
|
RU2769288C2 |
DETECTION OF PLANTS DISEASES BY CLASSIFICATION OF PLANTS PHOTOGRAPHY | 2019 |
|
RU2805670C2 |
METHOD, MEDIUM AND SYSTEM FOR DETECTING POTATO VIRUS IN AGRICULTURAL CROP IMAGE | 2017 |
|
RU2749033C2 |
METHOD, CARRIER AND SYSTEM FOR DETECTING POTATO VIRUS IN AN IMAGE OF AN AGRICULTURAL CROP | 2017 |
|
RU2770465C2 |
METHOD OF APPLYING A SPRAYING AGENT ON A FIELD | 2018 |
|
RU2767347C2 |
SYSTEM AND METHOD FOR SUPPORTING PLANT DISEASE DETECTION | 2020 |
|
RU2815542C2 |
METHOD TO IDENTIFY FOREIGN OBJECTS ON SURFACE OF FIBROUS MATERIALS USING COMPUTER IMAGE | 2009 |
|
RU2411501C1 |
LASER SURGICAL SYSTEM AND METHOD FOR USE THEREOF FOR EVAPORATION OF LIVING TISSUE | 2015 |
|
RU2582213C1 |
VEHICLE SECURITY AND MONITORING SYSTEM | 2004 |
|
RU2250844C1 |
Authors
Dates
2020-10-28—Published
2017-05-05—Filed