ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

2025-05-24

AI Summary

Plankton identification in underwater video faces challenges including highly similar backgrounds (e.g., marine snow), minute target sizes, and difficulty distinguishing live specimens. General-purpose computer vision methods exhibit insufficient robustness on real-world oceanic footage. To address this, we introduce ZooGeo—the first fine-grained visual benchmark for plankton with precise geospatial metadata (latitude, longitude, depth, timestamp)—supporting detection, classification, and tracking tasks. We explicitly model three core challenges: background similarity, dynamic scale variation, and ecological state discrimination (e.g., live vs. dead). A novel geoinformation-integrated annotation paradigm enables reproducible evaluation of Geo-AI, few-shot learning, and weakly supervised methods in realistic underwater settings. ZooGeo significantly improves model generalization to complex marine environments and establishes a standardized evaluation platform for marine ecological monitoring and fisheries resource forecasting.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Plankton are small drifting organisms found throughout the world's oceans. One component of this plankton community is the zooplankton, which includes gelatinous animals and crustaceans (e.g. shrimp), as well as the early life stages (i.e., eggs and larvae) of many commercially important fishes. Being able to monitor zooplankton abundances accurately and understand how populations change in relation to ocean conditions is invaluable to marine science research, with important implications for future marine seafood productivity. While new imaging technologies generate massive amounts of video data of zooplankton, analyzing them using general-purpose computer vision tools developed for general objects turns out to be highly challenging due to the high similarity in appearance between the zooplankton and its background (e.g., marine snow). In this work, we present the ZooplanktonBench, a benchmark dataset containing images and videos of zooplankton associated with rich geospatial metadata (e.g., geographic coordinates, depth, etc.) in various water ecosystems. ZooplanktonBench defines a collection of tasks to detect, classify, and track zooplankton in challenging settings, including highly cluttered environments, living vs non-living classification, objects with similar shapes, and relatively small objects. Our dataset presents unique challenges and opportunities for state-of-the-art computer vision systems to evolve and improve visual understanding in a dynamic environment with huge variations and be geo-aware.

Problem

• Develop geo-aware zooplankton recognition in marine environments
• Classify zooplankton in cluttered, dynamic ocean conditions
• Track small, similar-looking plankton in video data

Innovation

• Geo-aware dataset with rich metadata
• Challenging tasks for zooplankton recognition
• Improves computer vision in dynamic environments