Titulo Estágio
AI-Powered Visual Monitoring of Biodiversity
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
CISUC
Enquadramento
Artificial Intelligence (AI), and particularly Computer Vision (CV), is transforming how we address complex classification tasks by enabling machines to interpret and analyze visual data at scale. In biodiversity research and other scientific domains, the automation of image based classification through Deep Learning (DL) has opened up possibilities for faster, more accurate, and more scalable analysis.
This internship focuses on designing and evaluating an AI based framework for species recognition using image data, employing state of the art machine learning models. While Convolutional Neural Networks (CNNs) have long been the standard for image classification, newer architectures such as Vision Transformers (ViT) are gaining traction due to their strong performance on large scale image datasets and their ability to capture long range dependencies in image features.
The primary dataset used in this work will be the “200 Bird Species with 11,788 Images” dataset available on Kaggle (https://www.kaggle.com/datasets/veeralakrishna/200-bird-species-with-11788-images) This dataset provides a diverse collection of labeled bird images across 200 species. However, improvements such as data cleaning, augmentation, and balancing may be necessary to enhance model performance and ensure robust learning across all classes.
Objetivo
To achieve the above defined goal, the following objectives will be pursued:
Study the state of the art
Study the available machine learning architectures, such as CNNs and ViT
Define, implement, and test the framework using available data
Plano de Trabalhos - Semestre 1
Literature review
Identification and study of available technological approaches
Define the architecture of the framework
Start implementing the proposed framework
Write intermediate report
Plano de Trabalhos - Semestre 2
Implement the proposed solution
Test and evaluate performance
Write final report
Condições
This work should take place in the context of a research project in CISUC. There is the possibility of a 6-month scholarship.
Orientador
Catarina Silva, Bernardete Ribeiro, Dinis Costa
catarina@dei.uc.pt 📩