Topological mapping using monocular camera for object-level change detection

Date

2025-12

Author

Fırat, Ata Baran

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

117
views

0
downloads

Cite This

This thesis introduces a pose-free, monocular-camera framework for topological mapping, designed to serve as a foundation for object-level change detection. The proposed method identifies object instances through segmentation and sparse feature matching across video frames, and treats these instances as stable features for building a topology that captures their co-occurrence patterns and structure across views, without relying on metric depth or camera pose estimation. The primary focus of this work is the generation and validation of this topological map. Experimental results show that the extracted features and their geometric relationships yield a consistent topological model, demonstrating its potential as a basis for object-level change analysis.

Subject Keywords

Change detection, Topological mapping, Monocular vision

URI

https://hdl.handle.net/11511/118427

Collections

Graduate School of Natural and Applied Sciences, Thesis