Home >>  GOSC >>  Initiative >>  Case Studies

An open cloud service for camera trap data management and intelligent analysis


In the past 10 years, infrared trigger camera and camera trap technology have been widely used in nature reserves because of its obvious advantages over traditional survey methods, especially for the monitoring and research on the terrestrial large and medium-sized animals. According to incomplete statistics, camera trap technology has been used for wildlife monitoring and research in 80% of China's national nature reserves, and images and videos of more than 200 rare and endangered species have been obtained.

Followed by a large number of camera deployments and massive amounts of image and video data are two challenges to a nature reserve. One is how to effectively store, organize and manage massive amounts of camera trap data. The other one is how to intelligently analyze massive amounts of camera trap data. To help nature reserve solve these challenges, Chinese Biodiversity Observation Network – Mammals (Sino BON-Mammals) and Computer Network Information Center (CNIC), CAS developed an open cloud service for camera trap data management and intelligent analysis. Based on the cloud service, nature reserves will be able to create sample areas, add sample points, and upload camera trap data in a self-service manner. On the cloud side, the uploaded camera trap data is stored and managed, and through object detection and species identification, image and video data are intelligently analyzed based on deep learning technology.

We seek other biodiversity related initiatives to participate in this Case Study, particularly if focused on the technological challenges listed here and the integration and enrichment of biodiversity data.


The cloud service involves cloud computing, big data, artificial intelligence, data visualization, and other technologies, and requires interdisciplinary cooperation and multi-party coordination. Challenges include on the following issues:

  1. Stewardship of massive amounts of camera trap data storage, movement, management methods, and mechanisms under cloud environment.
  2. Deep learning algorithms and methods to improve intelligent analysis performance.
  3. Workflow or pipeline to implement camera trap data management, intelligent analysis, and visualization process automation.
  4. Mechanisms for integrating cloud computing, big data, artificial intelligence, and visualization technologies into a cloud service.
  5. Data standard specification, service integration standard, and multi-party collaboration mechanism.


This case deals with distributed big data management, intelligent analysis, and cloud computing for high-quality integration and optimization for camera trap data uploaded by a nature reserve. The cloud service will be a collaborative platform for global camera trap data sharing and analysis service and contributes to global biodiversity research and protection.

Joint work under the GOSC Initiative umbrella may include:

  1. Exploring alignment of the infrastructure supporting camera trap data storage and AI computing, for example, cloud storage space and GPU resources for AI models training and prediction, etc.
  2. A toolkit offering online cloud services of various modular functions, which may include but not be limited to real-time image processing, intelligent recognition, and other functions yet to be determined.
  3. Collaborations on necessary standards and specifications, training of data scientists and data managers, and other activities promoting the deployment of interoperable services in nature reserves around the world.


Anticipated outputs from this Case Study may focus on the following aspects:

  1. A software system for camera trap data management and intelligent analysis.
  2. Development of an online computing and processing toolkit for big data acquired from biosphere reserves.
  3. A specification for biosphere reserves data systems, comprising standards for data and metadata, for monitoring equipment, and for applications.
  4. Lessons and good practices for analogous cloud services.