Precise underwater fish measurement: A geometric approach leveraging medium regression

Abstract

Accurate estimation of fish length is crucial aquaculture processes. Precise and real-time estimation of fish length aids fish farmers in formulating effective farming strategies. Existing methods for estimating the length of underwater fish have made significant advancements in overcoming the interferences present in complex underwater environments. Nevertheless, the measurement results of some methods continue to be limited by variations in the refractive index of multiple media and deviations in imaging angles, resulting in measurement errors and diminished practicality. Consequently, we propose a measurement method that aims to address the aforementioned challenges in fisheries aquaculture by providing more accurate and cost-effective solutions. This method initially introduces the concept of regressing multiple media into a single medium to correct underwater depth estimation and enhance underwater imaging quality. Subsequently, an accurate plane fitting algorithm is applied to precisely fit the fish body plane and extract its corresponding normal vector information. Finally, taking into account the light propagation path and accounting for the limitations of precise values, we utilize the geometric relationship between the length of the bounding box and the actual length of the fish to calculate a more accurate estimation of fish body length. Experimental validation showcases the applicability of our measurement method to diverse fish species and substantiates its exceptional performance in both experimental and real-world scenarios. The maximum average relative errors for each group are within 8%, and the average relative error is 3.28% under the exact value constraints presented in the experiments. This method makes a significant contribution to fish length estimation and offers valuable insights for applications in fisheries and aquaculture.