PPD: Pyramid Patch Descriptor via Convolutional Neural Network
Local features play an important role in remote sensing image matching, and handcrafted features have been excessively used in this area for a long time. This article proposes a pyramid convolutional neural triplet network that extracts a 128-dimensional deep descriptor that significantly improves the matching performance. The proposed approach first extracts deep descriptors of the anchor patches and corresponding positive patches in a batch using the proposed pyramid convolutional neural network. Following this step, the approaches chooses the closest negative patch for each anchor patch and corresponding positive patch pair to form the triplet sample based on the descriptor distances among all other image patches in the batch. These triplets are used to optimize the parameters of the network using a new loss function. We evaluated the proposed deep descriptors on two benchmark data sets (Brown and HPatches) as well as real image data sets. The results reveal that the proposed descriptor achieves the state-of-the-art performance on the Brown data set and a comparatively very high performance on the HPatches data set. The proposed approach finds more correct matches than the classical handcrafted feature descriptors on aerial image pairs and is observed to be robust to variations in the viewpoint and illumination.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: September 1, 2019
More about this publication?
- The official journal of the American Society for Photogrammetry and Remote Sensing - the Imaging and Geospatial Information Society (ASPRS). This highly respected publication covers all facets of photogrammetry and remote sensing methods and technologies.
Founded in 1934, the American Society for Photogrammetry and Remote Sensing (ASPRS) is a scientific association serving over 7,000 professional members around the world. Our mission is to advance knowledge and improve understanding of mapping sciences to promote the responsible applications of photogrammetry, remote sensing, geographic information systems (GIS), and supporting technologies.
- Editorial Board
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Membership Information
- Information for Advertisers
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites