Finding interesting images from large quantities of camera trap data

To protect the endangered Saimaa ringed seal population, the ringed seals are monitored with automatic camera traps in order to gather knowledge about them including population size, territory, age, health and breeding data. To achieve this, the monitoring system has to be able to tell apart individ...

Full description

Bibliographic Details
Main Author: Kauppala, Juho
Other Authors: Lappeenrannan-Lahden teknillinen yliopisto LUT, Lappeenranta-Lahti University of Technology LUT
Format: Bachelor Thesis
Language:English
Published: 2020
Subjects:
Online Access:https://lutpub.lut.fi/handle/10024/161252
Description
Summary:To protect the endangered Saimaa ringed seal population, the ringed seals are monitored with automatic camera traps in order to gather knowledge about them including population size, territory, age, health and breeding data. To achieve this, the monitoring system has to be able to tell apart individual ringed seals from the automatically gathered images. For such a system to work efficiently, it has to be able to find the images with animal for further analysis. Methods to re-identify Saimaa ringed seals as well as other animals from images have already been proposed. A review to animal re-identification and automatic image dataset cleaning are made, and the basic principle of convolutional neural network is presented. A dataset which contains images of Saimaa ringed seals as well as empty images is also introduced. A model for cleaning the Saimaa ringed seal dataset, that is removing images that do not contain a ringed seal, is proposed. The model consist of splitting the image into small patches, predicting the probability for each patch to contain a Saimaa ringed seal using a convolutional neural network, and then deciding whether the image contains a Saimaa ringed seal based on an connected-component labeling algorithm. The model performs well, achieving the accuracy of more than 90%. Uhanalaisen saimaannorppapopulaation suojelemiseksi norppia tarkkaillaan automaattisilla riistakameroilla. Tarkoituksena on kerätä tietoa etenkin norppapopulaation koosta, norppien reviiristä, eliniästä, terveydentilasta sekä lisääntymisestä. Jotta tämä onnistuisi, tarkkailujärjestelmän on pystyttävä erottamaan valokuvista eri norppayksilöt. Sitä varten tarkkailujärjestelmän on kyettävä ensin tunnistamaan, onko valokuvassa norppa ylipäänsä. Keinoja saimaannorppien sekä muiden eläinlajien automaattiseen tunnistamiseen kuvista on jo esitetty. Työssä esitellään perusasioita eläinten tunnistamisesta, automatisoidusta kuvajoukon suodattamisesta sekä kerrotaan konvoluutioneuroverkon toimintaperiaate. Esitellään myös kuvajoukko, ...