Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. We first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions.
Biodegradable materials are used in packaging, agriculture, medicine and other areas. In recent years there has been an increase in interest in biodegradable polymers. Two classes of biodegradable polymers can be distinguished: synthetic or natural polymers. There are polymers produced from feedstocks derived either from petroleum resources (non renewable resources) or from biological resources (renewable resources). In general natural polymers offer fewer advantages than synthetic polymers. The following review presents an overview of the different biodegradable polymers that are currently being used and their properties, as well as new developments in their synthesis and applications.
K. Esvelt, Andrea L. Smidler, F. Catteruccia
et al.
Gene drives may be capable of addressing ecological problems by altering entire populations of wild organisms, but their use has remained largely theoretical due to technical constraints. Here we consider the potential for RNA-guided gene drives based on the CRISPR nuclease Cas9 to serve as a general method for spreading altered traits through wild populations over many generations. We detail likely capabilities, discuss limitations, and provide novel precautionary strategies to control the spread of gene drives and reverse genomic changes. The ability to edit populations of sexual species would offer substantial benefits to humanity and the environment. For example, RNA-guided gene drives could potentially prevent the spread of disease, support agriculture by reversing pesticide and herbicide resistance in insects and weeds, and control damaging invasive species. However, the possibility of unwanted ecological effects and near-certainty of spread across political borders demand careful assessment of each potential application. We call for thoughtful, inclusive, and well-informed public discussions to explore the responsible use of this currently theoretical technology.
Abstract Barriers to dog vaccination in Tanzania in general, and in Kilosa District in particular, are not well understood. Therefore, this study sought to address the following research question: What are the multilevel barriers to the vaccination of dogs against rabies in Kilosa District? Guided by a socioecological model, the study explored the barriers to dog vaccination at multiple levels within the Kilosa District context. A case study design employing a qualitative research approach was used. Data were collected through focus group discussions (FGDs) and in-depth interviews to investigate contextual barriers to dog vaccination. The collected data were analyzed using a thematic analysis approach. The results are organized according to the levels of the socioecological model. At the individual level, barriers include limited literacy about rabies and dog rabies vaccination; low perceived risk of rabies transmission; low prioritization of dog vaccination in household financial decisions; and uncertainty regarding the cost of dog vaccination. At the organizational/health system level, barriers include fragmented provision of rabies-related health education, reactive rather than proactive sensitization efforts, and limited communication channels, primarily relying on loudspeaker announcements. At the community level, barriers include misconceptions about protection against rabies and mistrust in political leadership. In conclusion, Rabies vaccination uptake in Kilosa District is constrained by multilevel barriers. Individually, limited knowledge, low risk perception, and financial uncertainty reduce prioritization of dog vaccination. Organizational barriers include fragmented health education, weak cross-sector coordination, and reactive communication. At the community level, logistical challenges, absence of By-Laws, persistent misconceptions, and political mistrust further limit vaccination coverage.
Environmental sciences, Public aspects of medicine
K. B. Vedamurthy, Manojkumar Patil, Vaishnavi
et al.
India generates substantial volumes of public agricultural data, yet artificial intelligence (AI) adoption in farming remains limited and largely confined to pilot initiatives. This paper examines this gap by assessing India's agricultural data infrastructure against the requirements of AI systems deployed at scale. Drawing on a systematic review of major national datasets and digital initiatives including Soil Health Cards, crop insurance, AgriStack, and selected state platforms we identify persistent structural constraints, including temporal misalignment between data collection and agricultural decision cycles, spatial fragmentation arising from the absence of common geocodes linking soil, weather, and yield information, limited machine readability due to reliance on static data formats, and unclear governance frameworks that restrict data access and reuse. These deficiencies impede cross-dataset integration and automated decision support, with disproportionate consequences for smallholders, who constitute 86~\% of India's farmers and lack the capacity to compensate for weak data infrastructure. Drawing on implementation evidence from India and comparative international experiences, the paper identifies recurring features associated with scalable digital agriculture systems, including incentives linked to data provision, service bundling through local institutions, and sensor-enabled risk management.
The integration of emerging technologies such as robotics and artificial intelligence (AI) has the potential to transform agricultural harvesting by improving efficiency, reducing waste, lowering labor dependency, and enhancing produce quality. This paper presents the development of an intelligent robotic berry harvesting system that combines deep learning–based perception with autonomous robotic manipulation for real-time strawberry harvesting. A computer vision pipeline based on the YOLOv11 segmentation model was developed and integrated into a Smart Mobile Manipulator (SMM) equipped with autonomous navigation, a 6-degree-of-freedom (6-DoF) xArm 6 robotic arm, and ROS middleware to enable real-time operation. Using a publicly available strawberry dataset comprising 2,800 images collected under ridge-planted cultivation conditions, the proposed YOLOv11-small segmentation model achieved 84.41% mAP@0.5, outperforming YOLOv11 object detection, Faster R-CNN, and RT-DETR in segmentation quality while maintaining real-time performance at 10 FPS on an NVIDIA Jetson Orin Nano edge GPU. A PCA-based fruit orientation and geometric analysis method achieved 86.5% localization accuracy on 200 test images. Controlled indoor harvesting experiments using synthetic strawberries demonstrated an overall harvesting success rate of 72% across 50 trials. The proposed system provides a general-purpose platform for berry harvesting in controlled environments, offering a scalable and efficient solution for autonomous harvesting.
Elvis Frimpong Manso, Alfred Arthur, Joseph Osafo Eduah
et al.
Despite the differences in soil and fertilizer properties affecting fertilizer effectiveness, farmers often use nationwide blanket formulations, which may not optimize cocoa yield. Previous trials have shown that fertilizer application outcomes vary by soil type, prompting recommendations for site-specific fertilizer formulations. Nonetheless, the complexity of creating these models leaves farmers relying on available blanket fertilizers instead. To enable farmers to select fertilizer types that will best suit their soils, the effects of soil properties and fertilizer types on the solubility, availability of macronutrients, and pH in two cocoa soils were investigated. Five kilograms of ferralsol and acrisol were prepared in nursery bags, with five different fertilizers (A, B, C, D, and E) applied at rates of 375, 500, and 625 kg·ha−1 were set in factorial experiment laid in completely randomized design with four replicates each. Following a 3-week incubation, nutrient analysis was conducted weekly. Water solubility was assessed by weighing 1, 2, and 3 g of each fertilizer in 200 mL of distilled water and shaken for 3 hours. Results indicate that lower solute-to-solvent ratios decreased NPK, Ca, and Mg solubility. Fertilizer A increased soil pH from 6.81 to 7.45 in ferralsol and from 5.78 to 7.50 in acrisol. The different soils showed different release trends though the same fertilizers were applied. Available phosphorus rose from 4.76 to 166.69 mg·kg−1 in ferralsol and from 4.32 to 170.00 mg·kg−1 in acrisol, while total nitrogen rose from 0.22% to 0.30% in ferralsol and from 0.16% to 0.20% in acrisol. The findings highlight that soil properties influence fertilizer solubility and nutrient availability in cocoa soils.
Evan S. Ross, Lance C. Visser, Lalida Tantisuwat
et al.
ABSTRACT Background The effects of general anesthesia (GA) on less flow‐dependent (velocity ratio, velocity time integral [VTI] ratio and indexed pulmonary valve area [iPVA]) and flow‐dependent (mean [PVmeanPG] and maximum pressure gradient [PVmaxPG]) indices of severity of pulmonary stenosis (PS) are unclear. Objectives Determine the effects of GA on indices of severity of PS in dogs undergoing an interventional procedure (IP). Determine the reproducibility of indices of severity of PS. Animals Thirty‐nine dogs with PS. Methods Prospective cross‐sectional study. Five repeated echocardiograms were performed over 3 days. Day 1: two echocardiograms were performed by 2 different operators. Day 2: echocardiograms were performed before and after GA but before IP. Day 3: an echocardiogram was performed after the IP. Results After GA, median (IQR) cardiac index (2.1 [1.6–2.6] L/min/m2), PVmeanPG (45.0 [26.0–55.2] mmHg), PVmaxPG (76.6 [46.6–100.3] mmHg) were decreased (p ≤0.001) compared to before GA (2.8 [2.2–3.0] L/min/m2, 55.9 [47.6–73.1] mmHg, 96.1 [81.6–127.0] mmHg, respectively). There were no differences (p ≥0.35) in velocity ratio, VTI ratio, or iPVA after GA. Intra‐operator and inter‐operator coefficients of variation (95% CI) were highest for iPVA (13.8% [10.4–18.4] and 13.5% [11.0–18.4], respectively) and lowest for velocity ratio (9.2% [7.7–12.3] and 9.3% [7.7–12.4], respectively). Conclusions and Clinical Importance PVmeanPG and PVmaxPG might be misleading in states of reduced flow. An integrative assessment of severity of PS that includes less flow‐dependent indices is recommended. Reproducibility of indices of severity of PS should be considered when re‐evaluating dogs with PS.
Accurate crop disease diagnosis is essential for sustainable agriculture and global food security. Existing methods, which primarily rely on unimodal models such as image-based classifiers and object detectors, are limited in their ability to incorporate domain-specific agricultural knowledge and lack support for interactive, language-based understanding. Recent advances in large language models (LLMs) and large vision-language models (LVLMs) have opened new avenues for multimodal reasoning. However, their performance in agricultural contexts remains limited due to the absence of specialized datasets and insufficient domain adaptation. In this work, we propose AgriDoctor, a modular and extensible multimodal framework designed for intelligent crop disease diagnosis and agricultural knowledge interaction. As a pioneering effort to introduce agent-based multimodal reasoning into the agricultural domain, AgriDoctor offers a novel paradigm for building interactive and domain-adaptive crop health solutions. It integrates five core components: a router, classifier, detector, knowledge retriever and LLMs. To facilitate effective training and evaluation, we construct AgriMM, a comprehensive benchmark comprising 400000 annotated disease images, 831 expert-curated knowledge entries, and 300000 bilingual prompts for intent-driven tool selection. Extensive experiments demonstrate that AgriDoctor, trained on AgriMM, significantly outperforms state-of-the-art LVLMs on fine-grained agricultural tasks, establishing a new paradigm for intelligent and sustainable farming applications.
As a strategic pillar industry for human survival and development, modern agriculture faces dual challenges: optimizing production efficiency and achieving sustainable development. Against the backdrop of intensified climate change leading to frequent extreme weather events, the uncertainty risks in agricultural production systems are increasing exponentially. To address these challenges, this study proposes an innovative \textbf{M}ultimodal \textbf{A}gricultural \textbf{A}gent \textbf{A}rchitecture (\textbf{MA3}), which leverages cross-modal information fusion and task collaboration mechanisms to achieve intelligent agricultural decision-making. This study constructs a multimodal agricultural agent dataset encompassing five major tasks: classification, detection, Visual Question Answering (VQA), tool selection, and agent evaluation. We propose a unified backbone for sugarcane disease classification and detection tools, as well as a sugarcane disease expert model. By integrating an innovative tool selection module, we develop a multimodal agricultural agent capable of effectively performing tasks in classification, detection, and VQA. Furthermore, we introduce a multi-dimensional quantitative evaluation framework and conduct a comprehensive assessment of the entire architecture over our evaluation dataset, thereby verifying the practicality and robustness of MA3 in agricultural scenarios. This study provides new insights and methodologies for the development of agricultural agents, holding significant theoretical and practical implications. Our source code and dataset will be made publicly available upon acceptance.
Dinesh Jackson Samuel, Inna Skarga-Bandurova, David Sikolia
et al.
AgroLLM is an AI-powered chatbot designed to enhance knowledge-sharing and education in agriculture using Large Language Models (LLMs) and a Retrieval-Augmented Generation (RAG) framework. By using a comprehensive open-source agricultural database, AgroLLM provides accurate, contextually relevant responses while reducing incorrect information retrieval. The system utilizes the FAISS vector database for efficient similarity searches, ensuring rapid access to agricultural knowledge. A comparative study of three advanced models: Gemini 1.5 Flash, ChatGPT-4o Mini, and Mistral-7B-Instruct-v0.2 was conducted to evaluate performance across four key agricultural domains: Agriculture and Life Sciences, Agricultural Management, Agriculture and Forestry, and Agriculture Business. Key evaluation metrics included embedding quality, search efficiency, and response relevance. Results indicated that ChatGPT-4o Mini with RAG achieved the highest accuracy at 93%. Continuous feedback mechanisms enhance response quality, making AgroLLM a benchmark AI-driven educational tool for farmers, researchers, and professionals, promoting informed decision-making and improved agricultural practices.