https://fordatis.fraunhofer.de/handle/fordatis/7 2026-05-07T21:08:07Z https://fordatis.fraunhofer.de/handle/fordatis/500 Titel: WheatFormer3D: Segmentation and Phenotyping of Wheat Heads with Transformers Datenautorinnen und Datenautoren: Singh, Ashutosh Zusammenfassung: 3D Computer vision offers powerful tools for efficient agricultural analysis by enabling automated extraction of quantitative traits using point clouds of field scenes. In the context of wheat, accurate analysis of wheat head morphology is challenging because the acquisition of high resolution point clouds is difficult and annotating them for instance segmentation requires substantial manual effort. While 3D instance segmentation has shown promise for such tasks by explicitly modeling geometric structure, existing approaches often use simulated data or data obtained in highly controlled indoor setups. As a result, they struggle to achieve reliable instance coverage in real field conditions. In this work, we study 3D instance segmentation of wheat heads in real in-field point clouds and introduce WheatFormer3D, a transformer-based framework designed to improve query coverage of individual wheat heads in crowded scenes. We further propose domain-specific geometric augmentations that increase data efficiency and robustness in data-scarce agricultural settings. Extensive experiments demonstrate that the proposed approach consistently outperforms recent transformer-based baselines, including OneFormer3D and Mask3D, on wheat head instance segmentation, achieving 87.96 AP@50 and 77.99 AP overall. In addition, we investigate the use of segmentation outputs for downstream phenotyping tasks and construct a reference organ-level dataset with paired indoor and in-field wheat head scans and reference volume measurements. Using this dataset, we explore the feasibility and current limitations of learning-based volume estimation from real-world point clouds, highlighting challenges associated with noisy in-field reconstructions. 2026-01-01T00:00:00Z https://fordatis.fraunhofer.de/handle/fordatis/492 Titel: ConJEB: A Large Elastic Contact Jet Engine Bracket Quadratic Program Dataset Datenautorinnen und Datenautoren: Ferreira, Stephanie; Giebel, Andreas; Mueller-Roemer, Johannes Zusammenfassung: This dataset contains large-scale, sparse quadratic programs (QPs) derived from physically-based animation scenarios with contact interactions. It extends the SimJEB dataset (Wahlen et al. 2021) by introducing explicit contact handling: the abstract contact force in the original GE Jet Engine Bracket Challenge model is replaced with a detailed cylinder mesh pin. This modification yields realistic large-scale sparse QPs with hundreds of thousands to millions of degrees of freedom. The dataset is designed to enable fair, reproducible benchmarking and evaluation of QP solvers in computer graphics and related fields. 2026-04-01T00:00:00Z https://fordatis.fraunhofer.de/handle/fordatis/485 Titel: Fish Motion Approximation using ML-based Relative Depth Estimation and Object Tracking Datenautorinnen und Datenautoren: Lintao, Fang Zusammenfassung: Fish motion is a very important indicator of various health conditions of fish swarms in the fish farming industry. Many researchers have successfully analyzed fish motion information with the help of special sensors or computer vision, but their research results were either limited to few robotic fishes for ground-truth reasons or restricted to 2D space. Therefore, there is still a lack of methods that can accurately estimate the motion of a real fish swarm in 3D space. Here we present our Fish Motion Estimation (FME) algorithm that uses multi-object tracking, monocular depth estimation, and our novel post-processing approach to estimate fish motion in the world coordinate system. Our results show that the estimated fish motion approximates the ground truth very well and the achieved accuracy of 81.0% is sufficient for the use case of fish monitoring in fish farms. 2024-07-01T00:00:00Z