About this Research Topic
In this Research Topic, we welcome contributions that can advance the research area of pattern recognition in UAV-acquired images in natural and urban environments. These patterns may be natural, such as the composition of plant species or forest health condition, as well as human or animal behavior in natural environments (e.g. individual pathways). Pattern detection, semantic segmentation of images into pattern-defined classes, and change detection problems are of special interest for this collection. We particularly aim at multidisciplinary contributions with strong AI (or computer vision) foundations that can have an immediate practical application in related areas. Special care should be taken to show how the techniques used are adequate for the task at hand but also how this research works have the potential to affect end-users (forest managers, ecosystem preservation entities, urban planners, etc.)
According to the goal of this Research Topic we welcome works from the following topics using UAV acquired image and AI and computer vision techniques:
• Tree and plant species classification, either using image classification or semantic segmentation approaches.
• Individual tree detection, with a special focus on instance segmentation and object detection approaches.
• Anomaly detection in natural environments, including but not limited to tree and plant health, infestation or disease monitoring, or forest fires.
• Human and nature interaction, such as the adoption of habitats or human impact on natural ecosystems.
• Ecosystem services of natural environments, including but not limited to the use of green spaces, recreation patterns, VGI, etc.
Keywords: Deep Learning, UAV, Sustainability, Volunteered Geographic Information (VGI)
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.