A novel centerline extraction method for overlapping fish body length measurement in aquaculture images

Abstract

Information on the length of cultured fish is crucial to evaluate their growth status and biomass. However, existing methods to estimate fish body length are based primarily on manual sampling, which is invasive, time-consuming, and labor-intensive. In contrast, such information can be acquired via noncontact methods relying on images of the animals’ centerlines in an image. The centerline extraction method has been widely applied as an efficient approach. However, the greatest challenge in measuring the length of cultured fish is that of accurately extracting the animals’ centerlines when fish overlap in an image. To address this problem, we propose a method to obtain the centerlines of overlapping fish by processing images captured from a top-view perspective. First, fish contours are segmented using convex-concave points. Second, the contour segmentations belonging to each fish are identified by an algorithm that matches heads to tails; their centerlines are thus extracted and optimized. We conducted both laboratory and on-site experiments, and results show that the proposed method exhibited excellent performance in extracting fish centerline information, even for fish that overlapped in images captured from a top view. Moreover, it also improved on the performance of existing methods in measuring the length of cultured fish from such images.