Multi-Scale Fish Segmentation Refinement and Missing Shape Recovery

Abstract

Image processing and analysis techniques have drawn increasing attention since they enable a non-extractive and non-lethal approach to collecting fisheries data, such as fish size measurement, catch estimation, regulatory compliance, species recognition, and population counting. Measuring fish size accurately requires reliable image segmentation. Major challenges that can easily affect the segmentation include blurring of image areas due to water drops on the camera lens and parts of a fish body being out of the camera view. In this paper, we address each of these issues with an innovative and effective contour-based segmentation and a missing shape recovery method from an arbitrary initial segmentation. The refinement is processed from the coarse level to the fine level. At the coarse level, we align the entire fish contour of the initial segmentation with trained representative contours by using iteratively reweighted least squares (IRLS). At finer levels, we iteratively refine contour segments to represent poorly segmented or missing shape parts. This method addresses the problems listed above and generates promising results with highly robust segmentation performance and length measurement.

Image Analysis and Computer Vision Applications in Animal Sciences: An Overview

“…There are also many attempts to develop CVS for automated prediction of body weight and body measurements in fish, where the main challenges are related to fish body positioning and segmentation, and external factors such as light and background conditions. To tackle these issues, one study in halibut developed a CVS based on multi-scale body contour matching and completion using a double local threshold model with body shape priors (80). The final model developed was able to estimate the fish body with an average intersection over union (IoU) of 95.6%.…”

“…Thus, in the last decade, several efforts have been made toward the measurement of group-level traits, such as group growth, activity, drinking and feeding behavior, and animal spatial distribution among others with most of the successful applications based on standard digital cameras implementing classic image analysis and machine learning algorithms. Nevertheless, most of the works in the literature deals with a small group of animals, with just a few works evaluating CVS in farm environments (14,66,67,97) or under challenging light and background conditions (80,81,90) with the application of more sophisticated machine learning algorithms.…”

Tilapia Hatchery Techniques (Oreochromis niloticus) at the Local Fish Seed Center, Singgamanik, Karo Regency, North Sumatra Province

“…This was also stated by Khairul (2003), that female tilapia can start to be spawned when it is mature (5-6 months) with a weight of 250-300 g. The ripening of the gonads is influenced by several factors, including environmental manipulation, namely drying the ponds, selecting a good parent, handling the gonads, and feeding them both quantity and quality. Fish food in the form of pellets can be sprinkled in a fixed place, this place is usually near the discharge of water [8]. It is intended that if there are leftovers that do not run out, the leftovers will be easily wasted with water through excretion so as to minimize pool contamination.…”

Fish Detection and Measurement based on Mask R-CNN

“…Portanto, a coleta das medidas de um peixe de forma manual, em um ambiente real, pode acarretar na limitação da sua qualidade e quantidade. Comparado com a classificação e medição manual, um sistema de processamento automático pode ser mais rápido, menos propenso a erros, mais escalável e mais vantajoso para indivíduos sem treinamento especializado [3]. Neste sentido, as técnicas de processamento e análise de imagens têm chamado cada vez mais atenção da indústria e da ciência da aquicultura [1], pois permitem uma abordagem não-extrativa e não-letal para a coleta de dados da pesca, como medição do tamanho dos peixes, estimativa de capturas, conformidade regulatória, reconhecimento de espécies e contagem populacional [3].…”

“…Comparado com a classificação e medição manual, um sistema de processamento automático pode ser mais rápido, menos propenso a erros, mais escalável e mais vantajoso para indivíduos sem treinamento especializado [3]. Neste sentido, as técnicas de processamento e análise de imagens têm chamado cada vez mais atenção da indústria e da ciência da aquicultura [1], pois permitem uma abordagem não-extrativa e não-letal para a coleta de dados da pesca, como medição do tamanho dos peixes, estimativa de capturas, conformidade regulatória, reconhecimento de espécies e contagem populacional [3]. A extração de contorno a partir de imagensé a base de muitas aplicações de imagem de peixes, como diagnóstico e alerta precoce de doenças, comportamento animal, processamento de produtos aquáticos [4].…”