| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 5.97 MB | Adobe PDF |
Authors
Abstract(s)
Com intuito de auxiliar no manutenção de colmeias na apicultura, esse projeto tem como
objetivo o desenvolvimento de um classificador automático de subespécies de abelhas.
Para isso foi desenvolvido um programa que utiliza das landmarks adaptadas de Nawrocka[
1] para classificação, porém para realizar o processo de forma automática, foi
necessário implementar um detector de objetos capaz de encontrar asas de abelha em
uma imagem e um detector de landmarks capaz de indentificá-las em uma imagem e então
proceder para classificação. O detector de objetos foi capaz de detectar 98% das asas
e o detector de landmarks obteve foi capaz de detectar todos os landmarks em 91% dos
casos, com uma precisão de 94% de semelhança com landmarks marcados a mão. A classificação
por sua vez, apresentou bons resultados com as maiores classes dos datasets(em
quantidade de elementos), tendo 92% de precisão com as duas maiores classes e 87% de
precisão com as três maiores.
The aim of this project is to help bee hive maintenance in beekeeping to develop an automatic bee subspecies classifier. For this, a program was developed that uses the landmarks adapted from Nawrocka [1] for classification, but to perform the process automatically, it was necessary to implement an object detector capable of finding bee wings in an image and a detector of landmarks able to identify them in an image and then proceed to classification. The object detector was able to detect 98 % of the wings and the landmarks detector obtained was able to detect all landmarks in 91 % of cases, with a precision of 94 % resemblance to hand-marked landmarks. The classification, in turn, presented good results with the largest classes of datasets, with 92 % accuracy with the two largest classes and 87 % accuracy with the three largest.
The aim of this project is to help bee hive maintenance in beekeeping to develop an automatic bee subspecies classifier. For this, a program was developed that uses the landmarks adapted from Nawrocka [1] for classification, but to perform the process automatically, it was necessary to implement an object detector capable of finding bee wings in an image and a detector of landmarks able to identify them in an image and then proceed to classification. The object detector was able to detect 98 % of the wings and the landmarks detector obtained was able to detect all landmarks in 91 % of cases, with a precision of 94 % resemblance to hand-marked landmarks. The classification, in turn, presented good results with the largest classes of datasets, with 92 % accuracy with the two largest classes and 87 % accuracy with the three largest.
Description
Mestrado de dupla diplomação com a UTFPR - Universidade Tecnológica Federal do Paraná
Keywords
Visão computacional Detecção de landmarks Detector de objetos Deep learning