A highly sensitive underwater video system for use in turbid aquaculture ponds

Abstract

The turbid, low-light waters characteristic of aquaculture ponds have made it difficult or impossible for previous video cameras to provide clear imagery of the ponds’ benthic habitat. We developed a highly sensitive, underwater video system (UVS) for this particular application and tested it in shrimp ponds having turbidities typical of those in southern Taiwan. The system’s high-quality video stream and images, together with its camera capacity (up to nine cameras), permit in situ observations of shrimp feeding behavior, shrimp size and internal anatomy, and organic matter residues on pond sediments. The UVS can operate continuously and be focused remotely, a convenience to shrimp farmers. The observations possible with the UVS provide aquaculturists with information critical to provision of feed with minimal waste; determining whether the accumulation of organic-matter residues dictates exchange of pond water; and management decisions concerning shrimp health.

Intelligent feeding control methods in aquaculture with an emphasis on fish: a review

“…; Hung et al . ). Commercial video‐based feeding systems have been used in aquaculture (AQ1SYSTEMS, ).…”

“…; Hung et al . ). Furthermore, the cost of this technology is also very low, and the methods are easy to develop.…”

“…Underwater images are usually of poor quality due to the limited range of visibility, low and uneven illumination, bright artefacts, noise, blurring, diminishing colour, etc. (Ghani & Isa 2015), but some algorithms have been developed to address these issues and determine the shape, size and orientation of swimming fish (Atienza-Vanacloig et al 2016;Hung et al 2016). Commercial video-based feeding systems have been used in aquaculture (AQ1SYSTEMS, 2017).…”

“…In agriculture, its application has been extended to obtaining crop growth data, nondestructive testing of agricultural products and other aspects. In some aquaculture facilities, light conditions are usually insufficient, resulting in images with low brightness and high contrast (Zhou et al 2017a); however, near-infrared computer vision technology is not affected by visible light intensity and can yield good imaging results in environments with relatively dim light (Farokhi et al 2016;Hung et al 2016). Furthermore, the cost of this technology is also very low, and the methods are easy to develop.…”

An adaptive image enhancement method for a recirculating aquaculture system

“…Practice has shown that near infrared and vision-based computer vision is quite suitable for image acquisition and fish monitoring in an RAS 5 , 6 . However, because of the insufficient and uneven illumination in commercial fish farms and because most species of fish can change their skin colour to adapt to the ambient colour 7 – 9 , the captured images always have both low contrast and very bright backgrounds. As a result, detailed information can easily be lost 10 , 11 , which makes it difficult to recognize the intended targets and distinguish them from other fish 12 .…”