Abstract
Recent advances in Convolutional Neural Networks (CNNs) have attracted great attention in remote sensing due to their high capability to model high-level semantic content of Remote Sensing (RS) images. However, CNNs do not explicitly retain the relative position of objects in an image and, thus, the effectiveness of the obtained features is limited in the framework of the complex object detection problems. To address this problem, in this paper we introduce Capsule Networks (CapsNets) for object detection in Unmanned Aerial Vehicle-acquired images. Unlike CNNs, CapsNets extract and exploit the information content about objects’ relative position across several layers, which enables parsing crowded scenes with overlapping objects. Experimental results obtained on two datasets for car and solar panel detection problems show that CapsNets provide similar object detection accuracies when compared to state-of-the-art deep models with significantly reduced computational time. This is due to the fact that CapsNets emphasize dynamic routine instead of the depth.
Highlights
Unmanned Aerial Vehicles (UAVs) are miniaturized pilotless aircrafts that have proven very useful for a broad range of military applications and civilian/scientific applications
We evaluated the Capsule Networks (CapsNet) on two UAV datasets, which were acquired over different areas on the city of Trento, Italy by a Canon EOS 550D camera mounted on an UAV
The training set consists of 200 images (100 images include cars, while 100 images do not include cars) that were acquired over two parking lots in the city of Trento
Summary
Unmanned Aerial Vehicles (UAVs) are miniaturized pilotless aircrafts that have proven very useful for a broad range of military applications (e.g., bomb detection, surveillance) and civilian/scientific applications (e.g., item shipping, disaster management, precision agriculture, filming and journalism, archeological surveying, geographic mapping). Their size enables them to reach targets of interest that are rather inaccessible or hazardous for a human operative. They are environment-friendly, cost-effective, and operable (remotely) in real-time or pre-programmed, notwithstanding their customizability They can carry multiple sensors, which is very advantageous to acquire data in various modalities and fine details (e.g., high resolution images). For a more in-depth review regarding UAVs and their uses, the reader is referred to [7,8,9,10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
