Retrieving Aerial Scene Images with Learned Deep Image-SketchFeatures

This paper investigates the problem of retrieving aerial scene images by using semantic sketches, since thestate-of-the-art retrieval systems turn out to be invalid when there is no exemplar query aerial image available. However,due to the complex surface structures and huge variations of resolutions of aerial images, it is very challenging to retrieveaerial images with sketches and few studies have been devoted to this task. In this article, for the first time to our knowledge,we propose a framework to bridge the gap between sketches and aerial images. First, an aerial sketch-image database iscollected, and the images and sketches it contains are augmented to various levels of details. We then train a multi-scaledeep model by the new dataset. The fully-connected layers of the network in each scale are finally connected and used ascross-domain features, and the Euclidean distance is used to measure the cross-domain similarity between aerial images andsketches. Experiments on several commonly used aerial image datasets demonstrate the superiority of the proposed methodcompared with the traditional approaches.