Call for papers on Theme Issue “Multi-Modal Learning in Photogrammetry and Remote Sensing”
Michael Ying Yang (University of Twente, The Netherlands)
Loic Landrieu (IGN, France)
Devis Tuia (Wageningen University& Research, The Netherlands)
Charles Toth (The Ohio State University, USA)
Planned publication date: Autumn 2021
In the last decade, there have been ever-increasing amount of multi-modal data acquired from different platforms, such as airplanes, satellites, autonomous vehicles, surveillance cameras, and unmanned aerial vehicles (UAVs), for different Photogrammetry & Remote Sensing applications. However, the majority of the tasks tackled so far involve only one modality, e.g. RGB images, Lidar point clouds, infrared images, or IMU data. This is due in part to the differences in structure among modalities, which complicates their joint analysis. Another issue is the unbalanced number of labelled samples available among modalities, resulting in a significant gap in performance when algorithms are trained separately. Clearly, the Photogrammetry & Remote Sensing community has not exploited the full potential of multi-modal data. Additionally, it is undeniable that deep learning has transformed the field of computer vision, and now rivals human-level performance in certain tasks such as image recognition and semantic segmentation. In this context, there is a strong need for research and development of approaches for multi-sensory and multi-modal deep learning within the new recognition frameworks. With a special issue on “Multi-Modal Learning in Photogrammetry and Remote Sensing” we aim at fostering collaboration between the Photogrammetry & Remote Sensing and the Computer Vision& Machine Learning communities.
The “Multi-Modal Learning in Photogrammetry and Remote Sensing” theme issue deals with multi-modal data for 3D modelling, semantic interpretation, and static or dynamic scene understanding. Topics of multi-modal, multi-temporal, and multi-scale data analysis and learning are therefore of particular relevance for this theme issue:
– Multimodal learning, self-supervised/unsupervised learning for multimodal data;
– Multimodal data generation and transfer learning;
– Multimodal data fusion and data representation;
– Scene understanding from multi-sensory data: object recognition, semantic segmentation, tracking, and 3D reconstruction;
– Multimodal applications with multispectral data, hyperspectral data, airborne/terrestrial imagery and point cloud data.
Prospective authors are cordially invited to contribute to this theme issue by submitting an original article relating to of one of the sub-fields. All submitting authors are encouraged to test their method on a relevant benchmark data set and to publicly release source code and potentially the data used in the paper upon acceptance.
Papers must be original contributions, not previously published or submitted to other journals. Papers published or submitted for publication in conference proceedings may be considered provided that they are considerably extended and improved. Substantive research and relevant-for-practice papers will be preferred. Papers must follow the instructions for authors at http://www.elsevier.com/journals/isprsjournal-of-photogrammetry-and-remote-sensing/0924-2716/guide-for-authors..
Please submit the full manuscript to https://ees.elsevier.com/photo/ by 30 September 2020.
Dr. Michael Ying Yang
Group, ITC Faculty,
University of Twente,
Dr. Loic Landrieu
Prof. Devis Tuia
and Remote Sensing Lab,
Prof. Charles Toth
Dept. of Civil,
Environmental & Geodetic
The Ohio State University,