Design and Implementation of an Assistive Real‐Time Red Lionfish Detection System for AUV/ROVs

Abstract

In recent years, the Pterois Volitans, also known as the red lionfish, has become a serious threat by rapidly invading US coastal waters. Being a fierce predator, having no natural predator, being adaptive to different habitats, and being with high reproduction rates, the red lionfish has enervated current endeavors to control their population. This paper focuses on the first steps to reinforce these efforts by employing autonomous vehicles. To that end, an assistive underwater robotic scheme is designed to aid spear-hunting divers to locate and more efficiently hunt the lionfish. A small-sized, open source ROV with an integrated camera is programmed using Deep Learning methods to detect red lionfish in real time. Dives are restricted to a certain depth range, time, and air supply. The ROV program is designed to allow the divers to locate the red lionfish before each dive, so that they can plan their hunt to maximize their catch. Lightweight, portability, user-friendly interface, energy efficiency, and low cost of maintenance are some advantages of the proposed scheme. The developed system’s performance is examined in areas currently invaded by the red lionfish in the Gulf of Mexico. The ROV has shown success in detecting the red lionfish with high confidence in real time.

Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories

“…Changing the dataset would be challenging, as we could select images or videos with other characteristics, such as a moving background similar to [95], where they collected underwater sea videos using an ROV camera. Other possibilities include modifying the dataset, cropping images, or dividing fish into pieces to compare results, similar to [96].…”

Deep learning for smart fish farming: applications, opportunities and challenges

“…However, two of the papers reviewed here use a GAN, three use an RNN, two use an LSTM, two use both an LSTM and a CNN, and two papers use a DBN and YOLO, respectively. Some CNN models are combined with output-layer classifiers, such as SVM and Softmax (Qin et al 2016;Sun et al 2018) or Softmax (Naddaf-Sh et al 2018;Zhao et al 2018b) classifiers. (2) Frameworks.…”

“…The inputs include public data sets such as the ImageNet data set, the Fish4Knowledge (F4K) data set and the Croatian and Queensland University of Technology (QUT) fish data sets. Other data sets include data collected and produced in the field or obtained through Internet search engines, such as Google (Meng et al 2018;Naddaf-Sh et al 2018).…”

“…2018); the average time to detect lionfish in each frame was only 0.097 s (Naddaf‐Sh et al . 2018). Therefore, under the premise of reasonable accuracy, a DL model's recognition speed can satisfy real‐time requirements (Villon et al .…”

“…2018; Naddaf‐Sh et al . 2018). Combining optical sensors and machine vision with DL systems provides possibilities for developing faster, cheaper and noninvasive methods for in situ monitoring and post‐harvesting quality monitoring in aquaculture (Saberioon et al .…”