PPD: Pyramid Patch Descriptor via Convolutional Neural Network

Abstract

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.

Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network

“…Detone's method [26]: This approach uses a fully convolutional neural network (Magic-Point) trained on an extensive synthetic dataset which poses a liability to real scenarios. The homographic adaptation (HA) strategy is employed to transform MagicPoint into SuperPoint, which boosts the performance of the detector and generate repeatable feature points.…”