Object detection at the edge

• Main Author: Mathiassen, Truls
• Format: Master Thesis
• Language: English
• Published: UiT Norges arktiske universitet 2020
• Subjects: VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550::Datateknologi: 551; VDP::Technology: 500::Information and communication technology: 550::Computer technology: 551; VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550::Annen informasjonsteknologi: 559; VDP::Technology: 500::Information and communication technology: 550::Other information technology: 559; INF-3981; Arctic; Tundra
• Online Access: https://hdl.handle.net/10037/20516

While monitoring rodents in the Arctic Tundra to evaluate if climate changes affect the ecosystem. The camera-traps of the coat project generates image data in large scale each year. To manually examine the data in regards to label- ing is a tedious and time-consuming job, and a more efficient and automated tool for the task is required. In this thesis we presents the architecture, design and implementation of a object classification model deployed on a small embedded computer, to be used on the gathered image data in order to classify and label the animals at the edge. We conduct transfer-learning on the state-of-the-art pre-trained YOLOv4-tiny model by introducing a labeled COAT image set. We utilize the Convolutional Neural Network of the model to do predictions on a test image set in order to evaluate the model. The result is an application with an embedded model able to predict labels with an accuracy of 96.07% and inference time that classifies it to do so in real-time.