Search

Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation (EO) applications, such as land use land cover mapping, environment monitoring, and sustainable development. Driven by rapid developments in Artificial Intelligence (AI), deep learning (DL) has emerged as the mainstream tool for semantic segmentation and has achieved many breakthroughs in the field of remote sensing. However, the existing DL-based methods mainly focus on unimodal visual data while ignoring the rich multimodal information involved in the real world, usually demonstrating weak reliability and generlization. Inspired by the success of Vision Transformers and large language models, we propose a novel metadata-collaborative multimodal segmentation network (MetaSegNet) that applies vision-language representation learning for semantic segmentation of remote sensing images. Unlike the common model structure that only uses unimodal visual data, we extract the key characteristic (e.g. the climate zone) from freely available remote sensing image metadata and transfer it into knowledge-based text prompts via the generic ChatGPT. Then, we construct an image encoder, a text encoder and a cross-modal attention fusion subnetwork to extract the image and text feature and apply image-text interaction. Benefiting from such a design, the proposed MetaSegNet demonstrates superior generalization and achieves competitive accuracy with the state-of-the-art semantic segmentation methods on the large-scale OpenEarthMap dataset (68.6% mIoU) and Potsdam dataset (93.3% mean F1 score) as well as LoveDA dataset (52.2% mIoU).

Applications involving autonomous navigation and planning of mobile agents can benefit greatly by employing online Simultaneous Localization and Mapping (SLAM) techniques, however, their proper implementation still warrants an efficient amalgamation with any offline path planning method that may be used for the particular application. In this paper, such a case of amalgamation is considered for a LiDAR-based indoor mapping system which presents itself as a 2D coverage path planning problem implemented along with online SLAM. This paper shows how classic offline Coverage Path Planning (CPP) can be altered for use with online SLAM by proposing two modifications: (i) performing convex decomposition of the polygonal coverage area to allow for an arbitrary choice of an initial point while still tracing the shortest coverage path and (ii) using a new approach to stitch together the different cells within the polygonal area to form a continuous coverage path. Furthermore, an alteration to the SLAM operation to suit the coverage path planning strategy is also made that evaluates navigation errors in terms of an area coverage cost function. The implementation results show how the combination of the two modified offline and online planning strategies allow for an improvement in the total area coverage by the mapping system - the modification thus presents an approach for modifying offline and online navigation strategies for robust operation.

In many agricultural applications one wants to characterize physical properties of plants and use the measurements to predict, for example biomass and environmental influence. This process is known as phenotyping. Traditional collection of phenotypic information is labor-intensive and time-consuming. Use of imagery is becoming popular for phenotyping. In this paper, we present methods to estimate traits of sorghum plants from RBG cameras on board of an unmanned aerial vehicle (UAV). The position and orientation of the imagery together with the coordinates of sparse points along the area of interest are derived through a new triangulation method. A rectified orthophoto mosaic is then generated from the imagery. The number of leaves is estimated and a model-based method to analyze the leaf morphology for leaf segmentation is proposed. We present a statistical model to find the location of each individual sorghum plant., Comment: 8 pages, double-column