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.

🖼️

image annotation

Configuration Fileconfig.yaml

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

annotation_task_name: "iWildCam Wildlife Classification"

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 Datasample-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

Get This Design

View on GitHub

Clone or download from the repository

Quick start:

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

Details

Annotation Types

radiomultiselectbbox

Domain

Computer VisionWildlife Conservation

Use Cases

Wildlife DetectionSpecies ClassificationCamera Trap Analysis

Related Designs

CUB-200-2011 Fine-Grained Bird Classification

Fine-grained visual categorization of 200 bird species (Wah et al., 2011). Annotate bird images with species labels, part locations, and attribute annotations.

radiomultiselect

DeepFashion Fine-Grained Fashion Classification

Large-scale fashion dataset with attribute prediction, consumer-to-shop matching, and landmark detection (Liu et al., CVPR 2016). Annotate clothing with 1000 categories and 50 attributes.