Skip to content
intermediateimage

iWildCam Wildlife Detection & Classification

Camera trap image classification for wildlife monitoring (Beery et al., CVPR 2019). Classify wildlife species from camera trap images across diverse ecosystems worldwide.

Get This Design

View on GitHub(opens in a new tab)

Clone or download from the repository

Quick start:

bash
git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/image/specialized/iwildcam
potato start config.yaml

Configuration File

This Potato config reproduces the annotation task. Save it as config.yaml and run potato start config.yaml to try it.

yaml
# iWildCam Wildlife Detection & Classification Configuration
# Based on Beery et al., CVPR 2019

annotation_task_name: "iWildCam Wildlife Classification"
task_dir: "."

data_files:
  - "sample-data.json"

item_properties:
  id_key: "id"
  text_key: "image_url"
  context_key: "location_info"

user_config:
  allow_all_users: true

annotation_schemes:
  - annotation_type: "radio"
    name: "primary_species"
    description: "Select the primary species visible"
    labels:
      - name: "empty"
        tooltip: "No animal visible"
      - name: "deer"
        tooltip: "Deer species"
      - name: "wild_boar"
        tooltip: "Wild boar/pig"
      - name: "raccoon"
        tooltip: "Raccoon"
      - name: "fox"
        tooltip: "Fox"
      - name: "coyote"
        tooltip: "Coyote"
      - name: "bear"
        tooltip: "Bear"
      - name: "mountain_lion"
        tooltip: "Mountain lion/cougar"
      - name: "rabbit"
        tooltip: "Rabbit/hare"
      - name: "squirrel"
        tooltip: "Squirrel"
      - name: "bird"
        tooltip: "Bird species"
      - name: "cattle"
        tooltip: "Cattle"
      - name: "domestic_dog"
        tooltip: "Domestic dog"
      - name: "domestic_cat"
        tooltip: "Domestic cat"
      - name: "human"
        tooltip: "Human"
      - name: "other"
        tooltip: "Other species"

  - annotation_type: "radio"
    name: "animal_count"
    description: "How many animals are visible?"
    labels:
      - name: "zero"
        tooltip: "No animals"
      - name: "one"
        tooltip: "Single animal"
      - name: "few"
        tooltip: "2-5 animals"
      - name: "many"
        tooltip: "More than 5 animals"

  - annotation_type: "radio"
    name: "image_quality"
    description: "Image quality"
    labels:
      - name: "clear"
        tooltip: "Clear, well-exposed"
      - name: "blurry"
        tooltip: "Motion blur"
      - name: "dark"
        tooltip: "Underexposed/dark"
      - name: "overexposed"
        tooltip: "Overexposed/washed out"
      - name: "partial"
        tooltip: "Animal partially visible"

  - annotation_type: "multiselect"
    name: "behavior"
    description: "Select observed behaviors (if animal present)"
    labels:
      - name: "walking"
        tooltip: "Walking or moving"
      - name: "running"
        tooltip: "Running"
      - name: "standing"
        tooltip: "Standing still"
      - name: "feeding"
        tooltip: "Eating/foraging"
      - name: "resting"
        tooltip: "Lying down/resting"
      - name: "looking_at_camera"
        tooltip: "Looking at camera"

  - annotation_type: "text"
    name: "specific_species"
    description: "Enter specific species name if known"

interface_config:
  item_display_format: "<img src='{{text}}' style='max-width:100%; max-height:500px;'/><br/><small>Location: {{context}}</small>"

output_annotation_format: "json"
output_annotation_dir: "annotations"

Sample Data

json
[
  {
    "id": "wild_001",
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/1/18/Dog_Breeds.jpg/1200px-Dog_Breeds.jpg",
    "location_info": "Camera trap image from North American forest. Identify species, count, and behavior."
  },
  {
    "id": "wild_002",
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/4/4d/Cat_November_2010-1a.jpg/1200px-Cat_November_2010-1a.jpg",
    "location_info": "Wildlife camera capture. Classify the animal species visible."
  }
]

// ... and 1 more items

Dataset & paper

Beery et al., CVPR 2019

Official dataset(opens in a new tab)Read the paper(opens in a new tab)

Citation (BibTeX)

bibtex
@article{beery2019iwildcam,
    title = "The {iWildCam} 2019 Challenge Dataset",
    author = "Beery, Sara  and Morris, Dan  and Perona, Pietro",
    journal = "arXiv preprint arXiv:1907.07617",
    year = "2019",
    url = "https://arxiv.org/abs/1907.07617"
}

Details

Annotation Types

multiselectradiotext

Domain

Computer VisionWildlife Conservation

Use Cases

Wildlife DetectionSpecies ClassificationCamera Trap Analysis

Tags

iwildcamwildlifecamera-trapconservationecologycvpr2019

Found an issue or want to improve this design?

Open an Issue(opens in a new tab)

Related Designs

CUB-200-2011: Fine-Grained Bird Species Dataset

CUB-200-2011 is a fine-grained bird image dataset of 11,788 photos across 200 species, each labeled with parts, attributes, and a bounding box (Wah et al., 2011). This Potato config reproduces the labeling task.

multiselectradio

FLAIR: French Land Cover from Aerospace Imagery

Land use and land cover classification from high-resolution aerial imagery. Annotators classify the primary land use category of aerial image patches and identify any secondary land uses present. Based on the FLAIR dataset from the French National Institute of Geographic and Forest Information (IGN).

multiselectradio

MMBench: Multimodal Vision-Language Benchmark

MMBench is a multiple-choice benchmark of about 2,974 questions testing vision-language models across 20 ability dimensions (Liu et al., ECCV 2024). This Potato config reproduces image-question answering with skill tagging.

radiotext