{"id":19530822,"url":"https://github.com/alexeyev/hogweed-ground-level-view","last_synced_at":"2026-06-19T14:31:37.505Z","repository":{"id":74082035,"uuid":"398806849","full_name":"alexeyev/hogweed-ground-level-view","owner":"alexeyev","description":"A dataset for semantic segmentation of Sosnowsky's hogweed in the ground-level view photos taken in St. Petersburg, Malaya Vishera, Pushkin, etc.","archived":false,"fork":false,"pushed_at":"2021-10-03T18:20:50.000Z","size":20208,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-01-27T22:59:24.213Z","etag":null,"topics":["agtech","coco-format","computer-vision","data","dataset","ecology","plant-detection","robotic-vision","semantic-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alexeyev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2021-08-22T13:29:59.000Z","updated_at":"2025-11-27T05:50:02.000Z","dependencies_parsed_at":"2023-07-01T18:17:13.175Z","dependency_job_id":null,"html_url":"https://github.com/alexeyev/hogweed-ground-level-view","commit_stats":{"total_commits":44,"total_committers":1,"mean_commits":44.0,"dds":0.0,"last_synced_commit":"b47068553d5e04dd96d6de6c0cc47419b8081d81"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alexeyev/hogweed-ground-level-view","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fhogweed-ground-level-view","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fhogweed-ground-level-view/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fhogweed-ground-level-view/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fhogweed-ground-level-view/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alexeyev","download_url":"https://codeload.github.com/alexeyev/hogweed-ground-level-view/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fhogweed-ground-level-view/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34536274,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-19T02:00:06.005Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agtech","coco-format","computer-vision","data","dataset","ecology","plant-detection","robotic-vision","semantic-segmentation"],"created_at":"2024-11-11T01:36:23.160Z","updated_at":"2026-06-19T14:31:37.485Z","avatar_url":"https://github.com/alexeyev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Detecting Hogweed on the Ground-Level View Photographs: Dataset\n\nHogweed (Heracleum) is a herbs genus that features many invasive species such as giant hogweed \nor Sosnowsky's hogweed. This invasive species are particularly notorious due to the high \ncontent of phototoxic compounds, so that any contact with a plant may result in an intense skin burn. \n\nInvasion of the [Sosnowsky's hogweed](https://antiborschevik.info/) \\[lang:RU\\] in particular is major trouble \nin Central Russia, and by 2021 resolving the problem requires massive intervention. Agtech drones spraying \nherbicides are already used to eradicate the Sosnowsky's hogweed, and accompanying real-time detection \nalgorithms for UAVs are being developed (e.g. see [this paper](https://ieeexplore.ieee.org/document/9359491) \nand [the related dataset repository](https://github.com/DLopatkin/Heracleum-Dataset)).\n\nWe propose a dataset for detecting Sosnowsky's hogweed using the ground-level view as if we're \nlooking through the camera of an **autonomous unmanned ground vehicle** patrolling the hogweed-endangered \narea (e.g. a week after mowing or poisoning). It is not 100% clear whether this dataset can or should be \nused for training actual robotic vision algorithms or synthetic datasets construction. However, plant detection \nin the natural environment is quite a challenge, which makes such annotated images collections suitable \nfor competitions and/or ML homeworks. This is a *grassroot* (pun intended) initiative without any external \nfunding.\n\n## Data\n\nPhotographic images for the directory `prepared_data/images/` (CC-BY-4.0) can be **downloaded from Zenodo: [5233380](https://zenodo.org/record/5233380)**.\n\n**444** (311/133) photos are taken in different locations in Russia using a Samsung Galaxy A31 camera. \nThe images are annotated using https://supervise.ly/ (CE). \n\nA more detailed description of the data collection strategy and the dataset in general will be released during autumn.\nTest set annotations will be released after the end of the competition.\n\n## Format\n\nThe annotations are provided in COCO format. To inspect the annotations manually, please see \nthe Jupyter notebook `COCO-formatted-annotations-viewer.ipynb` adapted from \nthe [original Gist](https://gist.github.com/akTwelve/dc79fc8b9ae66828e7c7f648049bc42d) \nshared by [akTwelve](https://github.com/akTwelve).\n\n### Classification\n\nTo train a classifier, \n\n1. run a `get_data.sh` script,\n2. check out the Dataset object provided in `dataset.py` if you are planning to use PyTorch,\n3. consider using a baseline implemented in `prepared_pipeline_for_transfer.py` -- \nbased on a fine-tuned `ResNet18` model prepared by Dustin Franklin @dusty-nv. The training process\n is described in the [tutorial](https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-plants.md).\nThe model is available for [downloading](https://nvidia.box.com/s/dslt9b0hqq7u71o6mzvy07w0onn0tw66). All rights\nare reserved by NVIDIA.\n\n## How to cite\n\nWe would appreciate if you cite this dataset as\n\n```\n@dataset{alekseev_anton_2021_5233380,\n  author       = {Alekseev, Anton},\n  title        = {{Detecting Hogweed on the Ground-Level View Photographs: Dataset}},\n  month        = aug,\n  year         = 2021,\n  publisher    = {Zenodo},\n  version      = {0.1},\n  doi          = {10.5281/zenodo.5233380},\n  url          = {https://doi.org/10.5281/zenodo.5233380}\n}\n```\n\n## Acknowledgements\n\nI would like to thank Aleksey Artamonov, Andrey Savchenko and Mikhail Evtikhiev \nfor various consultations and proofreading.\n\n## Other materials\n\n* [A monster that devours Russia](https://www.youtube.com/watch?v=u5NxuEoXHn8) \\[YouTube video\\]\n* Different species, similar threat: [Giant Hogweed - The UK's Most Dangerous \u0026 Toxic Plant](https://www.youtube.com/watch?v=p2iCSHrYjoc) \\[YouTube video, possibly disturbing content\\]\n\n\n![Semantic segmentation](example_coco_annotation.jpg?raw=true \"Polygons obtained via manual annotation.\")\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexeyev%2Fhogweed-ground-level-view","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexeyev%2Fhogweed-ground-level-view","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexeyev%2Fhogweed-ground-level-view/lists"}