Detection of grapes in natural environment using HOG features in low resolution images

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25530%2F17%3A39910985" target="_blank" >RIV/00216275:25530/17:39910985 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1088/1742-6596/870/1/012004" target="_blank" >http://dx.doi.org/10.1088/1742-6596/870/1/012004</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1742-6596/870/1/012004" target="_blank" >10.1088/1742-6596/870/1/012004</a>

Result language

angličtina

Original language name

Detection of grapes in natural environment using HOG features in low resolution images

Original language description

Detection of grapes in real-life images has importance in various viticulture applications. A grape detector based on an SVM classifier, in combination with a HOG descriptor, has proven to be very efficient in detection of white varieties in high-resolution images. Nevertheless, the high time complexity of such utilization was not suitable for its real-time applications, even when a detector of a simplified structure was used. Thus, we examined possibilities of the simplified version application on images of lower resolutions. For this purpose, we designed a method aimed at search for a detector’s setting which gives the best time complexity vs. performance ratio. In order to provide precise evaluation results, we formed new extended datasets. We discovered that even applied on low-resolution images, the simplified detector, with an appropriate setting of all tuneable parameters, was competitive with other state of the art solutions. We concluded that the detector is qualified for real-time detection of grapes in real-life images.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Journal of Physics: Conference Series

ISBN

—

ISSN

1742-6588

e-ISSN

neuvedeno

Number of pages

8

Pages from-to

1-8

Publisher name

Institute of Physics Publishing Ltd

Place of publication

Bristol

Event location

Praha

Event date

Jun 9, 2017

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

000412552100004