{ "fetched_at": "2026-10-19T07:23:55Z", "source_url": "https://www.kaggle.com/competitions/beyond-visible-spectrum-ai-for-agriculture-2024/data", "pages": [ { "name": "data-description", "content": "The hyperspectral imagery retrieval was carried out in two times, on 3 May and 8 May 2019. On 3 May 2019 wheat in the experimental area was in the pre-grouting stage, which is a critical period for the spread of downy mildew infestation. On 8 May 2019 wheat in the experimental area was in the middle of the grouting stage, which is the period when the symptoms of downy mildew are more obvious.\n\nA DJI M600 Pro UAV system (SZ DJI Technology Co Ltd., Gungdong, China) with a snapshot hyperspectral sensor was used for data acquisition. The model of the hyperspectral sensor was S185 which can obtain reflect radiation from the visible to near-infrared band between 450-950nm wavelength. The spectral resolution was 4nm. The raw data was recorded as a 1000*1000 panchromatic image and a 50*50 hyperspectral image with 125 bands. Since UAV hyperspectral data are interfered by noise in post-processing, which has a significant impact on the data at both ends of the bands, the first 10 bands as well as the last 14 bands were excluded from the study, leaving 100 bands. In this work, all the images were obtained at an altitude of 60 meters, with a spatial resolution close to 4cm per pixel. \n\n# Dataset Overview Paper \n[A Deep Learning-Based Approach for Automated Yellow Rust Disease Detection from High-Resolution Hyperspectral UAV Images](https://www.mdpi.com/2072-4292/11/13/1554)\n\n\n## Files\n\nThe training dataset
\nThe validation dataset\n\n##Submission Columns\n\n* `Id` - file name\n* `Category` - 1: Mild FHB 2: Serious FHB \n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "# Introduction\n\nParticipants from all over the world can take part in the challenge. \nYou must be over 18, or of legal age in your jurisdiction, in order to participate.\n\n\n# Timing and duration\nThe Crop disease challenge will take place online from **25 April to 21 July 2024**.\n\n\n# Creating and submitting a solution\n\n\n\n1. For the challenge, you will have access to the training datasets and a range of tools in the form of a Jupyter notebook (Starter Pack). No other datasets can be used for the development of your solution. However, pre-trained models are allowed.\n\n- The data for this competition is available in the Kaggle webpage. It can be downloaded or processed using Kaggle's computing services.\n\n- Here is a short code example for data reading and processing the data ([Starter](https://www.kaggle.com/code/robeson/starter)).\n\n2. Each participant will be allowed to upload their solutions every 12 hours (to avoid overload and unfair behaviors).\n\n3. The final submission of your solution must be made by **21 July, 2024**, and each valid submission must consist of a Jupyter notebook with the implementation of their final algorithm to allow the Organizers to reproduce the predictions.\n\n# Challenge evaluation\nThe evaluation of the solutions submitted will be performed in two stages:\n\n1. Quantitative analysis: live scoring of the quality of your solution throughout the challenge, which will be visible on the leaderboard on this platform; \n\n2. Qualitative analysis of your code performed by the Organizers. The qualitative analysis is performed only for proving the validity and reproducibility of your solution.\n\nThe final score is based solely on the quantitative evaluation. However, if the solution turns out to be not reproducible, or if any concerns about its validity arise, the organizers reserve the right to contact the team leader of the corresponding team to resolve such issues. If the issues cannot be resolved, the team will not be eligible to receive prizes.\n\nFor more details on the metrics, see the Metrics section in the Data page.\n\n\n\n\n\n\n\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "#Important Information\n\n\nPlease contact me (robeson1010@gmail.com) to verify the your results on our private dataset. We will award and certification after evaluation at August 18, 2024.\n\n@Roberto Chang S\n@VietNamese\n@early_bird\n@maimimib\n@DieNeuronaleCrew\n@NCKU_ACVLAB\n@Khao Cha\n@Jason Z88\n@AgMod\n@Roshan Rateria\n\n\n# Overview\n\nThe International Conference on Pattern Recognition (ICPR) 2024 Competition on “**Beyond Visible Spectrum: AI for Agriculture**” presents an exciting opportunity for researchers and practitioners to advance computer vision techniques in agricultural crop disease monitoring. By leveraging the vast multi/hyper spectral remote sensing image datasets, participants are encouraged to develop innovative deep learning algorithms. The primary aim is to enhance the accuracy and efficiency of identifying crop diseases, thereby contributing to sustainable agricultural practices and global food security.\n\nParticipants in this challenge will have the chance to contribute to significant advancements in precision farming and crop monitoring techniques. By improving the deep learning vision models, the competition aims to drive forward the capabilities of agricultural technology, making it more efficient, accurate, and sustainable. The ICPR 2024 Competition on “Beyond Visible Spectrum” is not just a competition; it is a call to action for the computer research community to bring about transformative changes in how agricultural data is analyzed and utilized, paving the way for smarter, more sustainable farming practices that can benefit communities worldwide.\n\n\nEarly accurate diagnosis and quantification of crop diseases are crucial for precision management by allowing targeted interventions at the field level. Effective diagnosis and control measures are dependent on symptom recognition and severity assessment (in the vast majority of cases, diseases exhibit a range of visual symptoms, e.g. coloured spots or streaks). At present, these are mainly achieved by visual observation and estimation. \n\nRecent advancements in digital imaging have facilitated the development of a variety of image-based methods for plant management that are capable of performing automated image acquisition and analysis. These methods have shown great potential for automated crop disease diagnosis based on images from RGB (red, green and blue), thermal, multispectral, and hyperspectral sensors.\n\nParticularly, hyperspectral imagery (HSI), which contains more narrow spectral bands over a contiguous spectral range, provides detailed spectral–spatial information of the disease infestation and offers the potential to provide better diagnostic accuracy.\n\nIn this challenge, we will mainly focus on the accurate diagnosis of crop diseases from hyperspectral imagery (in this case fusarium head blight, FHB). The benchmark model for this competition is based on our published paper on remote sensing [1]. \n\n[1. A Deep Learning-Based Approach for Automated Yellow Rust Disease Detection from High-Resolution Hyperspectral UAV Images](https://www.mdpi.com/2072-4292/11/13/1554)\n\n# Competition Schedule\n \n**Launch Date:** April 15, 2024\n\n**Submission Opening:** April 15, 2024\n\n**Submission Deadline:** July 21, 2024\n\n**Submission of Competition Reports Deadline:** August 18, 2024\n\n# Awards\n\nAll submissions before the deadline will receive a participation certificate\n\nThe top three places of each task will be awarded prizes to the value of:\n\n\n**1st Place:**\t$300\n\n**2nd Place:**\t$200\n\n**3rd Place:**\t$100\n\n\n\n\n# Challenge keywords\nRemote sensing; Hyperspectral; Crop disease; Deep learning ; Fusarium Head Blight\n\n\n# Workshop/conference\n\nThis challenge is part of the conference on \"The International Conference on Pattern Recognition (ICPR) (2024)\".\n\n\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation metric for this competition is the categorization accuracy.\n\nThree types are set as follows: Rust, Health and Other\n\n## Submission Format\n\nSubmission files should contain two columns: `Id` and `Category`. \n\nThe file should contain a header and have the following format:\n```\nId\tCategory\n0508_eeedf1ea8bf14dc5875a5ec121408f7d.pt\t1\n0508_d9573017385c4a27b7dfc80032a76378.pt\t1\n0508_142e8472d61347b68a8697a57567e8a1.pt\t2", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "People", "content": "# Organisers\nProf. Liangxiu Han, Manchester Metropolitan University\nProf. Wenjiang Huang, Aerospace Information Research Institute, Chinese Academy of Sciences\n\n# Technical Chairs\nDr. Xin Zhang, Manchester Metropolitan University\nDr. Yingying, Dong Aerospace Information Research Institute, Chinese Academy of Sciences\nTam Sobieh, Manchester Metropolitan University\n\n# Primary contact\nLiangxiu Han - Email: l.han@mmu.ac.uk\nWenjiang Huang - Email: huangwj@radi.ac.cn", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }