UAV Navigation System Autonomous Correction Algorithm Based on Road and River Network Recognition
A. P. Tanchenko, A. M. Fedulin, R.R. Bikmaev et al. · Gyroscopy and Navigation · 2020
Abstract—The paper considers an original autonomous correction algorithm for UAV navigation system based on comparison between terrain images obtained by onboard machine vision system and vector topographic map images. Comparison is performed by calculating the homography of vision system images segmented using the convolutional neural network and the vector map images. The presented results of mathematical and flight experiments confirm the algorithm effectiveness for navigation applications.
Cited by 10 works. doi:10.1134/s2075108720040100
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- Lecture Notes in Computer Science 1205
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Random sample consensus
- Speeded-Up Robust Features (SURF)
- Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images
- Remote Sensing and Spatial Information Sciences
- Integrated position estimation using aerial image sequences
- Wide-Area Image Geolocalization with Aerial Reference Imagery
- Journal of Computer and Systems Sciences International