Automated Coral Spawn Monitoring for Reef Restoration: The Coral Spawn and Larvae Imaging Camera System (CSLICS)

Abstract

Coral aquaculture for reef restoration requires accurate and continuous spawn counting for resource distribution and larval health monitoring, but current methods are labor-intensive and represent a critical bottleneck in the coral production pipeline. We propose the Coral Spawn and Larvae Imaging Camera System (CSLICS), which uses low cost modular cameras and object detectors trained using human-in-the-loop labeling approaches for automated spawn counting in larval rearing tanks. This paper details the system engineering, dataset collection, and computer vision techniques to detect, classify and count coral spawn. Experimental results from mass spawning events demonstrate an F1 score of 82.4% for surface spawn detection at different embryogenesis stages, 65.3% F1 score for sub-surface spawn detection, and a saving of 5,720 hours of labor per spawning event compared to manual sampling methods at the same frequency. Comparison of manual counts with CSLICS monitoring during a mass coral spawning event on the Great Barrier Reef demonstrates CSLICS' accurate measurement of fertilization success and sub-surface spawn counts. These findings enhance the coral aquaculture process and enable upscaling of coral reef restoration efforts to address climate change threats facing ecosystems like the Great Barrier Reef.

Figures (7)

• Figure 1: The Coral Spawn and Larval Imaging Camera System (CSLICS) mounted above the larval rearing tank during surface monitoring with the coral spawn floating inside (left). Sample CSLICS detections highlight the developmental progression of coral embryogenesis, from unfertilized eggs, followed by first cleavage (the first confirmation of fertilization), then two-cell, four-to-eight and advanced cell stages (right).
• Figure 2: Current methods of counting coral spawn are intensely time-consuming and manual, involving stirring the larval culture to homogenize the larvae and sampling from the tanks multiple times (left), and then counting individual corals with a stereo microscope (right).
• Figure 3: CSLICS has two operational modes for different stages of spawn development: a) for the first 12-24 hours (t0--t1), CSLICS is in surface operation, and after t1 it switches to b) sub-surface operation (t1--t2). The larval rearing process is described in red, with the parallel tank settings made by an operator (shown in blue), and the simultaneous CSLICS operations (in purple).
• Figure 4: The CSLICS system boundary diagram, illustrating the major inputs and outputs.
• Figure 5: Manual annotation of CSLICS images: surface (left) and sub-surface (right), highlighting the challenging visual characteristics of the coral spawn. The sub-surface detection task (right) is further complicated as we aim to detect only corals that are in-focus.