RECOGNITION OF GEOTAGGED AUDIOVISUAL AERIAL SCENE

Abstract

Aerial scene recognition is an essential task in remote sensing and has recently received enlarged attention. This paper studies the improving performance on the aerial scene recognition. This explores a novel audiovisual aerial scene recognition task using both images and sounds as input. Based on an observation that some specific sound events are more likely to be heard at a given geographic location, we propose to exploit the knowledge from the sound events to improve the performance on the aerial scene recognition. For this purpose, we have used dataset named AuDio Visual Aerial sceNe reCognition dataset. With the help of this dataset, we evaluate three proposed approaches for transferring the sound event knowledge to the aerial scene recognition task in a multimodal learning framework, and show the benefit of develop the audio information for the aerial scene recognition.