View in EDS

Combining spatially adaptive statistical modelling methods and computer vision approaches for the automatic detection of animals from high resolution images

Saved in:
Bibliographic Details
Title: Combining spatially adaptive statistical modelling methods and computer vision approaches for the automatic detection of animals from high resolution images
Authors: Fell, Christina Mary
Committee Members: MacKenzie, Monique Lea; Harris-Birtill, David Cameron Christopher
Summary: This study aimed to automate detecting animals in aerial images and improve detection by combining computer vision techniques with statistical modelling of the surveyed area. Knowing the number of animals in an area is important for wildlife management and existing methods require trained observers in larger planes or photography from smaller aircraft requiring manual counting. Automating detection would allow large areas to be surveyed more frequently with lower human input. This thesis shows that animals can be automatically detected from aerial images using the YOLO object detection network. Studies ruled out classical computer vision techniques due to excess false positives. The YOLO method detects 61% of the animals compared to 79% detection by humans, however it also detects 11.6 False Positives Per Image (FPPI). Modelling the distribution of multiple species required a multinomial model. CReSS based GAMs were extended to the multinomial case and simulation studies were carried out to compare CReSS to other multinomial approaches, showing CReSS was preferred for: high noise, low sample sizes or animal densities close to exclusion zones. Confidence intervals from the statistical model were concatenated with the YOLO model. This reduced the FPPI from 11.6 to 6.6, showing that combining prior knowledge from a statistical model improves performance of animal detection. Manual checking time per image was reduced by 97%, from 5 minutes to 11 seconds. Using the automated detections to guide manual checks spotted additional animals increasing the recall to 0.81, greater than the recall estimated for human performance of 0.79. The methods described have reduced the estimated manual checking time for the 40,000 photographs covering the 7,500km2 survey area in Namibia from 9 months to 3 weeks, meaning this method could be used frequently to give timely and reliable results.
URL: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.887575
Database: OpenDissertations
FullText Text:
  Availability: 0
Header DbId: ddu
DbLabel: OpenDissertations
An: ddu.oai.ethos.bl.uk.887575
AccessLevel: 6
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Combining spatially adaptive statistical modelling methods and computer vision approaches for the automatic detection of animals from high resolution images
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Fell%2C+Christina+Mary%22">Fell, Christina Mary</searchLink>
– Name: Author
  Label: Committee Members
  Group: Au
  Data: <searchLink fieldCode="CO" term="%22MacKenzie%2C+Monique+Lea%22">MacKenzie, Monique Lea</searchLink>; <searchLink fieldCode="CO" term="%22Harris-Birtill%2C+David+Cameron+Christopher%22">Harris-Birtill, David Cameron Christopher</searchLink>
– Name: Abstract
  Label: Summary
  Group: Ab
  Data: This study aimed to automate detecting animals in aerial images and improve detection by combining computer vision techniques with statistical modelling of the surveyed area. Knowing the number of animals in an area is important for wildlife management and existing methods require trained observers in larger planes or photography from smaller aircraft requiring manual counting. Automating detection would allow large areas to be surveyed more frequently with lower human input. This thesis shows that animals can be automatically detected from aerial images using the YOLO object detection network. Studies ruled out classical computer vision techniques due to excess false positives. The YOLO method detects 61% of the animals compared to 79% detection by humans, however it also detects 11.6 False Positives Per Image (FPPI). Modelling the distribution of multiple species required a multinomial model. CReSS based GAMs were extended to the multinomial case and simulation studies were carried out to compare CReSS to other multinomial approaches, showing CReSS was preferred for: high noise, low sample sizes or animal densities close to exclusion zones. Confidence intervals from the statistical model were concatenated with the YOLO model. This reduced the FPPI from 11.6 to 6.6, showing that combining prior knowledge from a statistical model improves performance of animal detection. Manual checking time per image was reduced by 97%, from 5 minutes to 11 seconds. Using the automated detections to guide manual checks spotted additional animals increasing the recall to 0.81, greater than the recall estimated for human performance of 0.79. The methods described have reduced the estimated manual checking time for the 40,000 photographs covering the 7,500km2 survey area in Namibia from 9 months to 3 weeks, meaning this method could be used frequently to give timely and reliable results.
– Name: URL
  Label: URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.887575" linkWindow="_blank">https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.887575</link>
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ddu&AN=ddu.oai.ethos.bl.uk.887575
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Computer vision ; Aerial survey ; Convolutional Neural Network ; Wildlife survey ; Object detection ; Species distribution modelling ; TA1634.F4 ; Computer vision--Mathematics ; Aerial surveys in wildlife management
        Type: general
    Titles:
      – TitleFull: Combining spatially adaptive statistical modelling methods and computer vision approaches for the automatic detection of animals from high resolution images
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Fell, Christina Mary
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2022
ResultId 1