Computer Vision for Camera Trap Footage : Comparing classification with object detection
Monitoring wildlife is of great interest to ecologists and is arguably even more important in the Arctic, the region in focus for the research network INTERACT, where the effects of climate change are greater than on the rest of the planet. This master thesis studies how artificial intelligence (AI)...
Main Author: | |
---|---|
Format: | Bachelor Thesis |
Language: | English |
Published: |
Uppsala universitet, Avdelningen för visuell information och interaktion
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447482 |
id |
ftuppsalauniv:oai:DiVA.org:uu-447482 |
---|---|
record_format |
openpolar |
spelling |
ftuppsalauniv:oai:DiVA.org:uu-447482 2023-05-15T15:11:37+02:00 Computer Vision for Camera Trap Footage : Comparing classification with object detection Örn, Fredrik 2021 application/pdf http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447482 eng eng Uppsala universitet, Avdelningen för visuell information och interaktion UPTEC F, 1401-5757 21037 http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447482 info:eu-repo/semantics/openAccess computer vision camera traps classification object detection neural networks artificial intelligence machine learning datorseende kamerafällor klassificering detektering neurala nätverk artificiell intelligens maskininlärning Computer Vision and Robotics (Autonomous Systems) Datorseende och robotik (autonoma system) Student thesis info:eu-repo/semantics/bachelorThesis text 2021 ftuppsalauniv 2023-02-23T21:56:17Z Monitoring wildlife is of great interest to ecologists and is arguably even more important in the Arctic, the region in focus for the research network INTERACT, where the effects of climate change are greater than on the rest of the planet. This master thesis studies how artificial intelligence (AI) and computer vision can be used together with camera traps to achieve an effective way to monitor populations. The study uses an image data set, containing both humans and animals. The images were taken by camera traps from ECN Cairngorms, a station in the INTERACT network. The goal of the project is to classify these images into one of three categories: "Empty", "Animal" and "Human". Three different methods are compared, a DenseNet201 classifier, a YOLOv3 object detector, and the pre-trained MegaDetector, developed by Microsoft. No sufficient results were achieved with the classifier, but YOLOv3 performed well on human detection, with an average precision (AP) of 0.8 on both training and validation data. The animal detections for YOLOv3 did not reach an as high AP and this was likely because of the smaller amount of training examples. The best results were achieved by MegaDetector in combination with an added method to determine if the detected animals were dogs, reaching an average precision of 0.85 for animals and 0.99 for humans. This is the method that is recommended for future use, but there is potential to improve all the models and reach even more impressive results.Teknisk-naturvetenskapliga Bachelor Thesis Arctic Climate change Uppsala University: Publications (DiVA) Arctic |
institution |
Open Polar |
collection |
Uppsala University: Publications (DiVA) |
op_collection_id |
ftuppsalauniv |
language |
English |
topic |
computer vision camera traps classification object detection neural networks artificial intelligence machine learning datorseende kamerafällor klassificering detektering neurala nätverk artificiell intelligens maskininlärning Computer Vision and Robotics (Autonomous Systems) Datorseende och robotik (autonoma system) |
spellingShingle |
computer vision camera traps classification object detection neural networks artificial intelligence machine learning datorseende kamerafällor klassificering detektering neurala nätverk artificiell intelligens maskininlärning Computer Vision and Robotics (Autonomous Systems) Datorseende och robotik (autonoma system) Örn, Fredrik Computer Vision for Camera Trap Footage : Comparing classification with object detection |
topic_facet |
computer vision camera traps classification object detection neural networks artificial intelligence machine learning datorseende kamerafällor klassificering detektering neurala nätverk artificiell intelligens maskininlärning Computer Vision and Robotics (Autonomous Systems) Datorseende och robotik (autonoma system) |
description |
Monitoring wildlife is of great interest to ecologists and is arguably even more important in the Arctic, the region in focus for the research network INTERACT, where the effects of climate change are greater than on the rest of the planet. This master thesis studies how artificial intelligence (AI) and computer vision can be used together with camera traps to achieve an effective way to monitor populations. The study uses an image data set, containing both humans and animals. The images were taken by camera traps from ECN Cairngorms, a station in the INTERACT network. The goal of the project is to classify these images into one of three categories: "Empty", "Animal" and "Human". Three different methods are compared, a DenseNet201 classifier, a YOLOv3 object detector, and the pre-trained MegaDetector, developed by Microsoft. No sufficient results were achieved with the classifier, but YOLOv3 performed well on human detection, with an average precision (AP) of 0.8 on both training and validation data. The animal detections for YOLOv3 did not reach an as high AP and this was likely because of the smaller amount of training examples. The best results were achieved by MegaDetector in combination with an added method to determine if the detected animals were dogs, reaching an average precision of 0.85 for animals and 0.99 for humans. This is the method that is recommended for future use, but there is potential to improve all the models and reach even more impressive results.Teknisk-naturvetenskapliga |
format |
Bachelor Thesis |
author |
Örn, Fredrik |
author_facet |
Örn, Fredrik |
author_sort |
Örn, Fredrik |
title |
Computer Vision for Camera Trap Footage : Comparing classification with object detection |
title_short |
Computer Vision for Camera Trap Footage : Comparing classification with object detection |
title_full |
Computer Vision for Camera Trap Footage : Comparing classification with object detection |
title_fullStr |
Computer Vision for Camera Trap Footage : Comparing classification with object detection |
title_full_unstemmed |
Computer Vision for Camera Trap Footage : Comparing classification with object detection |
title_sort |
computer vision for camera trap footage : comparing classification with object detection |
publisher |
Uppsala universitet, Avdelningen för visuell information och interaktion |
publishDate |
2021 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447482 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change |
genre_facet |
Arctic Climate change |
op_relation |
UPTEC F, 1401-5757 21037 http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447482 |
op_rights |
info:eu-repo/semantics/openAccess |
_version_ |
1766342448207888384 |