Detection of Waste Containers Using Computer Vision
This work is a part of an ongoing study to substitute the identification of waste containers via radio-frequency identification. The purpose of this paper is to propose a method of identification based on computer vision that performs detection using images, video, or real-time video capture to iden...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Applied System Innovation |
Subjects: | |
Online Access: | https://www.mdpi.com/2571-5577/2/1/11 |
id |
doaj-1bf3f1a4045c4f9ca6591e2bdb185b7a |
---|---|
record_format |
Article |
spelling |
doaj-1bf3f1a4045c4f9ca6591e2bdb185b7a2020-11-24T21:44:23ZengMDPI AGApplied System Innovation2571-55772019-03-01211110.3390/asi2010011asi2010011Detection of Waste Containers Using Computer VisionMiguel Valente0Hélio Silva1João M. L. P. Caldeira2Vasco N. G. J. Soares3Pedro D. Gaspar4Escola Superior de Tecnologia, Instituto Politécnico de Castelo Branco, 6000-767 Castelo Branco, PortugalEVOX Technologies, 6000-767 Castelo Branco, PortugalEscola Superior de Tecnologia, Instituto Politécnico de Castelo Branco, 6000-767 Castelo Branco, PortugalEscola Superior de Tecnologia, Instituto Politécnico de Castelo Branco, 6000-767 Castelo Branco, PortugalDepartamento de Engenharia Eletromecânica, Universidade da Beira Interior, 6201-001 Covilhã, PortugalThis work is a part of an ongoing study to substitute the identification of waste containers via radio-frequency identification. The purpose of this paper is to propose a method of identification based on computer vision that performs detection using images, video, or real-time video capture to identify different types of waste containers. Compared to the current method of identification, this approach is more agile and does not require as many resources. Two approaches are employed, one using feature detectors/descriptors and other using convolutional neural networks. The former used a vector of locally aggregated descriptors (VLAD); however, it failed to accomplish what was desired. The latter used you only look once (YOLO), a convolutional neural network, and reached an accuracy in the range of 90%, meaning that it correctly identified and classified 90% of the pictures used on the test set.https://www.mdpi.com/2571-5577/2/1/11waste containerobject detectionVLADconvolutional neural networksYOLO |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Miguel Valente Hélio Silva João M. L. P. Caldeira Vasco N. G. J. Soares Pedro D. Gaspar |
spellingShingle |
Miguel Valente Hélio Silva João M. L. P. Caldeira Vasco N. G. J. Soares Pedro D. Gaspar Detection of Waste Containers Using Computer Vision Applied System Innovation waste container object detection VLAD convolutional neural networks YOLO |
author_facet |
Miguel Valente Hélio Silva João M. L. P. Caldeira Vasco N. G. J. Soares Pedro D. Gaspar |
author_sort |
Miguel Valente |
title |
Detection of Waste Containers Using Computer Vision |
title_short |
Detection of Waste Containers Using Computer Vision |
title_full |
Detection of Waste Containers Using Computer Vision |
title_fullStr |
Detection of Waste Containers Using Computer Vision |
title_full_unstemmed |
Detection of Waste Containers Using Computer Vision |
title_sort |
detection of waste containers using computer vision |
publisher |
MDPI AG |
series |
Applied System Innovation |
issn |
2571-5577 |
publishDate |
2019-03-01 |
description |
This work is a part of an ongoing study to substitute the identification of waste containers via radio-frequency identification. The purpose of this paper is to propose a method of identification based on computer vision that performs detection using images, video, or real-time video capture to identify different types of waste containers. Compared to the current method of identification, this approach is more agile and does not require as many resources. Two approaches are employed, one using feature detectors/descriptors and other using convolutional neural networks. The former used a vector of locally aggregated descriptors (VLAD); however, it failed to accomplish what was desired. The latter used you only look once (YOLO), a convolutional neural network, and reached an accuracy in the range of 90%, meaning that it correctly identified and classified 90% of the pictures used on the test set. |
topic |
waste container object detection VLAD convolutional neural networks YOLO |
url |
https://www.mdpi.com/2571-5577/2/1/11 |
work_keys_str_mv |
AT miguelvalente detectionofwastecontainersusingcomputervision AT heliosilva detectionofwastecontainersusingcomputervision AT joaomlpcaldeira detectionofwastecontainersusingcomputervision AT vascongjsoares detectionofwastecontainersusingcomputervision AT pedrodgaspar detectionofwastecontainersusingcomputervision |
_version_ |
1725910694658834432 |