Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty
This addresses the challenge of label uncertainty and data heterogeneity in remote sensing for applications like agriculture, though it is incremental as it builds on existing fusion methods.
The paper tackles the problem of fusing multi-resolution, multi-modal remote sensing data with imprecise labels by proposing a Multiple Instance Multi-Resolution Fusion (MIMRF) framework, resulting in improved and consistent performance in scene understanding and agricultural applications compared to traditional methods.
In remote sensing, each sensor can provide complementary or reinforcing information. It is valuable to fuse outputs from multiple sensors to boost overall performance. Previous supervised fusion methods often require accurate labels for each pixel in the training data. However, in many remote sensing applications, pixel-level labels are difficult or infeasible to obtain. In addition, outputs from multiple sensors often have different resolution or modalities. For example, rasterized hyperspectral imagery presents data in a pixel grid while airborne Light Detection and Ranging (LiDAR) generates dense three-dimensional (3D) point clouds. It is often difficult to directly fuse such multi-modal, multi-resolution data. To address these challenges, we present a novel Multiple Instance Multi-Resolution Fusion (MIMRF) framework that can fuse multi-resolution and multi-modal sensor outputs while learning from automatically-generated, imprecisely-labeled data. Experiments were conducted on the MUUFL Gulfport hyperspectral and LiDAR data set and a remotely-sensed soybean and weed data set. Results show improved, consistent performance on scene understanding and agricultural applications when compared to traditional fusion methods.