In Top-1% accuracy, there was a significant improvement over the baseline, increasing from 61.62% accuracy to 88.62%. The search region had 1449 different locations constituting a total area of 24km2. The models were then tested on a sequence of 4411 query images along a path in Jönköping. The models were trained on 2640 different locations in Linköping and Norrköping. Batch-Hard triplet loss, the Adam optimizer, and a different CNN backbone were tested as possible augmentations to this method. After training, the position of a given aerial image can then be estimated by finding the satellite image with a feature vector that is the most similar to that of the aerial image.Ī previous method called Where-CNN was used as a baseline model. The networks were also trained so that images taken from different locations had different feature vectors. Two networks were trained so that satellite and aerial images taken from different views of the same location had feature vectors that were similar. The flattened tensors at the final layers of a CNN can be viewed as vectors describing different input image features. In recent years Convolutional Neural Networks (CNNs) have seen huge success in the task of classifying images. The goal of this thesis has been global geolocalization using only visual input and a 3D database for reference. 2022 (English) Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE credits Student thesis Abstract
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |