{
  "fetched_at": "2026-10-24T15:15:53Z",
  "source_url": "https://www.kaggle.com/competitions/daphniacounter/data",
  "pages": [
    {
      "name": "data-description",
      "content": "You are provided with a large set of high-resolution Daphnia culture tank images. The training dataset is composed of 1) videos (as input, avi format), 2) individual frames (png format) and 3) the location of individually labeled objects (json format). To create a ground truth, we manually labeled individual animals using [*labelme*](https://github.com/wkentaro/labelme). \nFor the efficiency of labeling, we divided a frame into four pieces (top left - top right - bottom left - bottom right). \nThe total number of animals on each video is provided in metaData.csv file with supplementary information of each video. \n\n## File descriptions\n- DataForTraining: the training set\n- DataForValidation: the test set\n- metaData.csv: supplemental information about the data\n\n## Data fields\n- points: x, y point location (we used polygon shape to label object, so there can be multiple points to label a single animal. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The small crustacean [*Daphnia*](https://en.wikipedia.org/wiki/Daphnia) (also called \"water flea\") promises to be a powerful model organism for several reasons: 1) it is a diploid, parthenogenetic species with a relatively short median lifespan (50 ~ 100 days depending on environmental conditions), 2) it has a short reproductive cycle (e.g., a female can produce a clutch of 1-25 neonates every instar and 3) its genome and complex body plan are significantly more homologous to humans than a common aging model worm *C. elegans*, thus allowing more human-relevant, tissue-specific manifestations of aging to be analyzed.\n![daphnia image](https://upload.wikimedia.org/wikipedia/commons/c/c2/Daphnia_magna_asexual.jpg =200x100)\n\nWe developed an integrated platform that provides 1) a long-term culture with large sample size, 2) scalability provided by making an individual culture tank a module, and 3) controllability of stimuli for profiling behavioral responses of daphnids by implementing the mesh-based tank design and an integrated behavioral assay platform [[1]](https://www.biorxiv.org/content/10.1101/2021.05.30.446339v1). \n\n![tank image](https://i.imgur.com/nTN305B.gif =400x300)\n\nThe platform allows to count the number of alive animals for survival assay to build a lifespan curve and evaluate the effect of perturbations on lifespan. However, the manual live/dead assay is a heavily labor-intensive task and there is no available algorithm to conduct a fully automated *Daphnia* lifespan assay based on our knowledge. Therefore, an automated counter is required to build lifespan curves from our large-scale high-throughput longitudinal experiments. _However, since animals often overlap or touch each other in the high-density population case, it is not easy to accurately segment and detect all individuals to count them._ \n\n**The purpose of this competition is to develop an algorithm to count the number of live animals using machine learning techniques.** The winning models will be open sourced to maximize the impact such a model can have on improving the counting of small aquatic animals.\n\nThe dataset is intended for research purposes only and as such cannot be used commercially.\n\n**Reference**\n[1] [Cho, Yongmin, et al. \"\" Smart Tanks\": An Intelligent High-Throughput Intervention Testing Platform in Daphnia.\" bioRxiv (2021).](https://www.biorxiv.org/content/10.1101/2021.05.30.446339v1)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The aim of this competition is to count the number of live animals in each video. See the Data tab for more details. \n\nThe submission file should contain a header and have the following format:\n>Vidoe_id, Predicted Animal Number\n\nYour submission will be evaluated by their [MAE](https://en.wikipedia.org/wiki/Mean_absolute_error) from the human-labelled ground truth and estimated value. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}