Publikasjoner
NIBIOs ansatte publiserer flere hundre vitenskapelige artikler og forskningsrapporter hvert år. Her finner du referanser og lenker til publikasjoner og andre forsknings- og formidlingsaktiviteter. Samlingen oppdateres løpende med både nytt og historisk materiale. For mer informasjon om NIBIOs publikasjoner, besøk NIBIOs bibliotek.
2025
Sammendrag
Single-class object detection, which focuses on identifying, counting, and tracking a specific animal species, plays a vital role in optimizing farm operations. However, dense occlusion among individuals in group activity scenarios remains a major challenge. To address this, we propose YOLO-SDD, a dense detection network designed for single-class densely populated scenarios. First, we introduce a Wavelet-Enhanced Convolution (WEConv) to improve feature extraction under dense occlusion. Following this, we propose an occlusion perception attention mechanism (OPAM), which further enhances the model’s ability to recognize occluded targets by simultaneously leveraging low-level detailed features and high-level semantic features, helping the model better handle occlusion scenarios. Lastly, a Lightweight Shared Head (LS Head) is incorporated and specifically optimized for single-class dense detection tasks, enhancing efficiency while maintaining high detection accuracy. Experimental results on the ChickenFlow dataset, which we developed specifically for broiler detection, show that the n, s, and m variants of YOLO-SDD achieve AP50:95 improvements of 2.18%, 2.13%, and 1.62% over YOLOv8n, YOLOv8s, and YOLOv8m, respectively. In addition, our model surpasses the detection performance of the latest real-time detector, YOLOv11. YOLO-SDD also achieves state-of-the-art performance on the publicly available GooseDetect and SheepCounter datasets, confirming its superior detection capability in crowded livestock settings. YOLO-SDD’s high efficiency enables automated livestock tracking and counting in dense conditions, providing a robust solution for precision livestock farming.
Forfattere
Frank Thomas Ndjomatchoua Richard Olaf James Hamilton Stutt Ritter Atoundem Guimapi Luca Rossini Christopher A GilliganSammendrag
Empirical field data and simulation models are often used separately to monitor and analyse the dynamics of insect pest populations over time. Greater insight may be achieved when field data are used directly to parametrize population dynamic models. In this paper, we use a differential evolution algorithm to integrate mechanistic physiologicalbased population models and monitoring data to estimate the population density and the physiological age of the first cohort at the start of the field monitoring. We introduce an ad hoc temperature-driven life-cycle model of Bemisia tabaci in conjunction with field monitoring data. The likely date of local whitefly invasion is estimated, with a subsequent improvement of the model’s predictive accuracy. The method allows computation of the likely date of the first field incursion by the pest and demonstrates that the initial physiological age somewhat neglected in prior studies can improve the accuracy of model simulations. Given the increasing availability of monitoring data and models describing terrestrial arthropods, the integration of monitoring data and simulation models to improve model prediction and pioneer invasion date estimate will lead to better decision-making in pest management.
Sammendrag
Det er ikke registrert sammendrag
Forfattere
Wiesław Olek Waldemar Perdoch Andreas Treu Jerzy Majka Łukasz Czajkowski Bartłomiej Mazela Jerzy WeresSammendrag
The interaction of cellulose paper with water is a major hindrance to its broader application. This study, which introduces a novel approach to understand water vapor difusion in both untreated and treated paper, aims to identify the difusion coefcient, a crucial property in improving the hydrophobicity of paper. The treatment process utilized an aqueous solution of starch or starch modifed with methyltrimethoxysilane (MTMS). While the initial sorption method is frequently used to determine the difusion coefcient, this study found that it could lead to signifcant errors due to the non-Fickian behavior exhibited by lignocellulosic materials. This behavior causes that the hygroscopic equilibrium is not instantly obtained by surface of paper. It also induces slowing down moisture difusion in its fnal stage due to molecular relaxation. For the frst time, the modifed convective boundary condition was introduced into the moisture difusion model in paper materials. The results from vapor sorption experiments demonstrated this non-Fickian behavior, particularly at high values of air relative humidity. The study also revealed that the commonly applied frst kind boundary condition is not applicable, even for thin paper samples, inhibiting the use of the initial sorption method for determining the difusion coefcient. While the treatment with starch and MTMS signifcantly improved the hydrophobic properties of paper, it didn’t alter substantially its hygroscopic properties, potentially due to not blocking active sorption sites of cellulose fbers. This research underscores the need for further investigation into the chemical modifcation of cellulose fbers to improve the hydrophobicity of paper.
Sammendrag
Det er ikke registrert sammendrag
Sammendrag
Det er ikke registrert sammendrag
Redaktører
Randi HesjedalSammendrag
Det er ikke registrert sammendrag
Forfattere
Gunnhild SøgaardSammendrag
Det er ikke registrert sammendrag
Forfattere
Gunnhild SøgaardSammendrag
Det er ikke registrert sammendrag
Forfattere
Gunnhild SøgaardSammendrag
Det er ikke registrert sammendrag