Computer vision as a tool for forestry
Forestry is a large industry in Sweden and methods have been developed to try to optimize the processes in the business. Yet computer vision has not been used to a large extent despite other industries using computer vision with success. Computer vision is a sub area of machine learning and has beco...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM)
2019
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-85214 |
id |
ndltd-UPSALLA1-oai-DiVA.org-lnu-85214 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-lnu-852142019-06-14T04:25:29ZComputer vision as a tool for forestryengDatorseende som ett verktyg för skogsbruketBång, FilipLinnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM)2019object detectioncomputer visionforestryComputer SciencesDatavetenskap (datalogi)Forestry is a large industry in Sweden and methods have been developed to try to optimize the processes in the business. Yet computer vision has not been used to a large extent despite other industries using computer vision with success. Computer vision is a sub area of machine learning and has become popular thanks to advancements in the field of machine learning. This project plans to investigate how some of the architectures used in computer vision perform when applied in the context of forestry. In this project four architectures were selected that have previously proven to perform well on a general dataset. These four architectures were configured to continue to train on trees and other objects in the forest. The trained architectures were tested by measuring frames per second (FPS) when performing object detection on a video and mean average precision (mAP) which is a measure of how well a trained architecture detects objects. The fastest one was an architecture using a Single Shot Detector together with MobileNet v2 as a base network achieving 29 FPS. The one with the best accuracy was using Faster R-CNN and Inception Resnet as a base network achieving 0.119 mAP on the test set. The overall bad mAP for the trained architectures resulted in that none of the architectures were considered to be useful in a real world scenario as is. Suggestions on how to improve the mAP is focused on improvements on the dataset. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-85214application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
object detection computer vision forestry Computer Sciences Datavetenskap (datalogi) |
spellingShingle |
object detection computer vision forestry Computer Sciences Datavetenskap (datalogi) Bång, Filip Computer vision as a tool for forestry |
description |
Forestry is a large industry in Sweden and methods have been developed to try to optimize the processes in the business. Yet computer vision has not been used to a large extent despite other industries using computer vision with success. Computer vision is a sub area of machine learning and has become popular thanks to advancements in the field of machine learning. This project plans to investigate how some of the architectures used in computer vision perform when applied in the context of forestry. In this project four architectures were selected that have previously proven to perform well on a general dataset. These four architectures were configured to continue to train on trees and other objects in the forest. The trained architectures were tested by measuring frames per second (FPS) when performing object detection on a video and mean average precision (mAP) which is a measure of how well a trained architecture detects objects. The fastest one was an architecture using a Single Shot Detector together with MobileNet v2 as a base network achieving 29 FPS. The one with the best accuracy was using Faster R-CNN and Inception Resnet as a base network achieving 0.119 mAP on the test set. The overall bad mAP for the trained architectures resulted in that none of the architectures were considered to be useful in a real world scenario as is. Suggestions on how to improve the mAP is focused on improvements on the dataset. |
author |
Bång, Filip |
author_facet |
Bång, Filip |
author_sort |
Bång, Filip |
title |
Computer vision as a tool for forestry |
title_short |
Computer vision as a tool for forestry |
title_full |
Computer vision as a tool for forestry |
title_fullStr |
Computer vision as a tool for forestry |
title_full_unstemmed |
Computer vision as a tool for forestry |
title_sort |
computer vision as a tool for forestry |
publisher |
Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM) |
publishDate |
2019 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-85214 |
work_keys_str_mv |
AT bangfilip computervisionasatoolforforestry AT bangfilip datorseendesomettverktygforskogsbruket |
_version_ |
1719205509599330304 |