Daniel Marley | Searcharxiv

arXiv2026

Automated SysML-Based Verification of Discipline-Specific Models

Current examples of SysML-based verification of discipline-specific models in the literature typically have two flaws. Firstly, they are developed in a tool-specific manner using proprietary APIs, limiting portability. Secondly, they focus on performance properties modelled via parametric diagrams, overlooking behavioural and interface properties that also require verification. This project addresses the problem with a verification process tailored to model-based verification, informed by common SysML tool capabilities and the UML Testing Profile, that enables automated verification of discipline\-/specific models from SysML test cases and returns the results to the SysML model for traceability. A mixed-method approach combining literature research and stakeholder interviews was used to derive validated stakeholder needs, which drove the specification and design of the process. The process was demonstrated end-to-end in two independent SysML tool-chains to evidence tool-agnosticism, and was shown to verify behavioural and interface requirements, including ordering, timing, and state-based responses, using SysML behavioural diagram constructs that parametric approaches alone cannot address.

cs.SE↗

arXiv2023

Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis

A key challenge for much of the machine learning work on remote sensing and earth observation data is the difficulty in acquiring large amounts of accurately labeled data. This is particularly true for semantic segmentation tasks, which are much less common in the remote sensing domain because of the incredible difficulty in collecting precise, accurate, pixel-level annotations at scale. Recent efforts have addressed these challenges both through the creation of supervised datasets as well as the application of self-supervised methods. We continue these efforts on both fronts. First, we generate and release an improved version of the Agriculture-Vision dataset (Chiu et al., 2020b) to include raw, full-field imagery for greater experimental flexibility. Second, we extend this dataset with the release of 3600 large, high-resolution (10cm/pixel), full-field, red-green-blue and near-infrared images for pre-training. Third, we incorporate the Pixel-to-Propagation Module Xie et al. (2021b) originally built on the SimCLR framework into the framework of MoCo-V2 Chen et al.(2020b). Finally, we demonstrate the usefulness of this data by benchmarking different contrastive learning approaches on both downstream classification and semantic segmentation tasks. We explore both CNN and Swin Transformer Liu et al. (2021a) architectures within different frameworks based on MoCo-V2. Together, these approaches enable us to better detect key agricultural patterns of interest across a field from aerial imagery so that farmers may be alerted to problematic areas in a timely fashion to inform their management decisions. Furthermore, the release of these datasets will support numerous avenues of research for computer vision in remote sensing for agriculture.

cs.CV↗