Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
This paper evaluates the performances of several salient feature detectors, namely; Harris detector, Minimum Eigenvalue (MinEig), Scale Invariant Feature Transform (SIFT), Maximally Stable Extremal Region (MSER), Speeded Up Robust Feature (SURF), Features from Accelerated Segment Test (FAST), and Binary Robust Scale Invariant Keypoint (BRISK), in order to assess the suitability in the application of the proposed visual-based attitude estimation system. Throughout the experiment, three main requirements have been investigated which include Time-to-Complete (TTC), detection rate, and matching rate. It was found that SURF fulfills each of the system’s requirements. Moreover, it was also found that keypoints detection capabilities affect the processing time, and the clustering patterns in the results may assist in automated inspection of correct and false matching.
Tamjis, M. Ridhwan and Lim, Samsung
"An On-Board Visual-Based Attitude Estimation System For Unmanned Aerial Vehicle Mapping,"
Free and Open Source Software for Geospatial (FOSS4G) Conference Proceedings: Vol. 15
, Article 33.
Available at: https://scholarworks.umass.edu/foss4g/vol15/iss1/33