Abstract
Unmanned Aerial Vehicle (UAV) imagery is gaining a lot of momentum lately. Indeed, gathered information from a bird-point-of-view is particularly relevant for numerous applications, from agriculture to surveillance services. We herewith study visual saliency to verify whether there are tangible differences between this imagery and more conventional contents. We first describe typical and UAV contents based on their human saliency maps in a high-dimensional space, encompassing saliency map statistics, distribution characteristics, and other specifically designed features. Thanks to a large amount of eye tracking data collected on UAV, we stress the differences between typical and UAV videos, but more importantly within UAV sequences. We then designed a process to extract new visual attention biases in the UAV imagery, leading to the definition of a new dictionary of visual biases. We then conduct a benchmark on two different datasets, whose results confirm that the 20 defined biases are relevant as a low-complexity saliency prediction system.
Highlights
Visual attention is the mechanism developed by the Human Visual System (HVS) to cope with the large quantity of information it is presented with
We note that Unmanned Aerial Vehicle (UAV) videos are located moderately apart from conventional videos, especially these coming from UAV123 and DTB70
In order to verify the external validity of the bank of biases, we carry out the same study than above on another dataset, namely, EyeTrackUAV1
Summary
Visual attention is the mechanism developed by the Human Visual System (HVS) to cope with the large quantity of information it is presented with. When watching natural scenes on a screen, observers tend to look at the center irrespective of the content [1,2] This center bias is attributed to several effects such as the photographer bias [2], the viewing strategy, the central orbital position [3], the re-centering bias, the motor bias [4,5], the screen center bias [1], and the fact that the center is the optimized location to access most visual information at once [1]. Other biases are present in gaze deployment, mainly due to differences in context, i.e., observational task [8], population sample [9], psychological state [10], or content types [11,12,13]
Sign-in/Register to view highlights & summary 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.
