Semantic Segmentation For Pet Detection Using Convolutional Neural Network

124 Views · 69 Downloads · ★★★★★ 5.0

NOT PEER REVIEWED

Authors

Chibuzo Nwadike¹

Conference / event: International Conference on Computer Vision and Virtual Reality 2023, November 2023 (Sanya, China)

Poster summary: This research project encompasses an in-depth exploration of semantic segmentation methods for pet detection using the Oxford Pets Dataset. The primary objective involves the development of a convolutional neural network model rooted in deep-learning principles, designed to achieve precise segmentation and detection of pets within images. The approach integrates advanced image processing techniques, leveraging deep learning methodologies, and dataset augmentation strategies to enhance pet detection accuracy substantially. The outcomes underscore the considerable potential of semantic segmentation in elevating the effectiveness of pet detection applications. This study offers promising avenues for practical integration in real-world contexts such as pet care and surveillance systems. The achieved advancements underscore the proposed technique's viability and contribute to the broader discourse on enhancing object detection through sophisticated segmentation strategies.

Keywords: Deep Learning, Machine Learning, Computer Vision, Convolutional Neural Network, Image Processing, Semantic Segmentation

Additional information

Data availability statement: The datasets generated during and / or analyzed during the current study are available from the corresponding author on reasonable request.

Creative Commons license: Copyright © 2023 Nwadike. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.