{
  "fetched_at": "2026-10-19T06:25:35Z",
  "source_url": "https://www.kaggle.com/competitions/dlp-object-detection/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The dataset for this challenge is derived from a citizen science project focused on mosquito identification. It comprises 8025 real-world images of mosquitos captured by participants using mobile phone. These images offer a diverse representation of mosquitos in various scenarios and locations. Each image is labeled with bounding box coordinates and mosquito class information.\n\nThe dataset has been split into training and testing sets, with 93.5% of the images allocated for training (7500 images) and 6.5% for testing (525 images). This division provides participants with ample training data to develop their models and a separate evaluation set to assess the performance and generalization of their AI algorithms.\n\n## Files\n\n*   **train/images** - the training images\n*   **train/labels** - the training labels\n*   **test/images** - the testing images\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\nIn each .txt file in train/labels/ \n*   `class_label` - Label of the Image\n*   `bbx_xcenter` - X coordinate of center of Bounding Box\n*   `bbx_ycenter` - Y coordinate of center of Bounding Box\n*   `bbx_width` - Width of the Bounding Box\n*   `bbx_height` - Height of the Bounding Box\n\n\n6 Classes: {\n    \"aegypti\":      0,\n    \"albopictus\":   1,\n    \"anopheles\":    2,\n    \"culex\":        3,\n    \"culiseta\":     4,\n    \"japonicus/koreicus\": 5\n}\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, the goal is to develop a model capable of detecting and classifying mosquitoes into six distinct types using images. The dataset likely includes high-quality images of mosquitoes, and participants need to design a system that can accurately identify and differentiate between these species. This problem involves computer vision tasks such as object detection (to locate the mosquito within the image) and classification (to determine the mosquito's type).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on mAP score. mAP will be used to quantify the correctness of the bounding box predictions.\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\n      id,ImageID,LabelName,Conf,xcenter,ycenter,bbx_width,bbx_height\n      0,16dbbc39-fcb6-498e-963f-d3807fcc3cec.jpeg,albopictus,0.5,0.1,0.2,0.3,0.4\n      1,7daa68bd-928b-4b43-850f-4626f16d2c14.jpeg,albopictus,0.5,0.1,0.2,0.3,0.4\n      2,bb0986d9-fa04-40a5-8de2-c54045537e17.jpeg,albopictus,0.5,0.1,0.2,0.3,0.4\n      3,11924d04-69fe-469d-8d1c-119bc0f0b94f.jpeg,albopictus,0.5,0.1,0.2,0.3,0.4\n      4,db4ade79-fce4-4d77-a8fa-36b9e77dfd08.jpeg,albopictus,0.5,0.1,0.2,0.3,0.4",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Individuals are required to submit their entries in CSV (Comma-Separated Values) format. We wish you a enjoyable learning experience!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "# Low Light Object Detection and Classification of Mosquitos\n\nMosquitoes, small yet perilous insects, are responsible for transmitting diseases that pose a serious threat to humans and the environment. With over 3600 known species, a few of them have the ability to transmit various pathogens, leading to widespread illnesses such as Zika, Dengue, and Chikungunya. Controlling mosquito populations is vital to prevent disease outbreaks and protect communities worldwide.\n\nTraditional mosquito surveillance methods are expensive and time-consuming, but community-based approaches empower citizens to report and collect mosquito specimens. By leveraging machine learning and deep learning techniques, we aim to automate the labor-intensive image validation process, making mosquito identification more efficient and accurate.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}