A review of techniques for the identification and measurement of fish in underwater stereo-video image sequences

Shortis, Mark R.; Ravanbakskh, Mehdi; Shaifat, Faisal; Harvey, Euan S.; Mian, Ajmal; Seager, James; Culverhouse, Phil F.; Cline, Danelle E.; Edgington, D.R.

doi:10.1117/12.2020941

Cited by 60 publications

(36 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of dead fish, studies may involve systems coupled with conveyor belts that are equipped with cameras and software for digital editing and measurement, such as the identification and classification of fish (White et al, 2006;Rutjes et al, 2009;Shortis et al, 2013). However, this new technology is complex, expensive and not accessible to the majority of fish farmers or researchers, and error management (random and systematic) associated as much with the measurement process as with the observer, could result in incorrect a posteriori interpretations of these estimations (White et al, 2006;Goodennough et al, 2010Goodennough et al, , 2012Sidek & Halawani, 2010;Yajing, 2012).…”

Section: __________________ Corresponding Editor: Guido Plazamentioning

confidence: 99%

“…3), which causes bias in the biometric information; therefore, this deviation was a critical variable in the validation of the IchthyoJHOL, a factor controlled by the cylindrical cone. To reduce distortion of the focal plane when measuring fish in vivo, Harvey (2003), Costa et al (2006) and Shortis et al (2013) use a stereo-video system, while Chang et al (2010) and Hsieh et al (2011) minimize projection error in photographic images using geometric transformations.…”

Section: Orthogonality On Bidimensional Planementioning

confidence: 99%

See 1 more Smart Citation

A suitable ichthyometer for systemic application

Lezama-Cervantes

Godínez-Domínguez

Gómez-Morales

et al. 2017

lajar

View full text Add to dashboard Cite

ABSTRACT. An excessive and inappropriate handling of live fish is currently performed to obtain its size and weight. As an ameliorative attempt, a system named "IchthyoJHOL" was devised for the measurement of live specimens of fusiform fish species. The system holds the fish ventrally between supports and is mounted upon a scale. An image is captured on camera and processed with a digital measurement system. The system generates biometric data such as length, height, and weight. This methodology creates a two-stage biometric process, the first being the capture of the images and the second their digital analysis, allowing for each stage to be carried out at distinct times and places. With this methodology, a reliability of over 96.8% is achieved, similar to that produced by the traditional system, but with a significant reduction in handling time and stress induced on the fish, allowing for large-scale biometric analysis. In addition, the library of fish images can be shared for posterior evaluation, redescription studies or a more extensive morphometric analysis.

show abstract

Section: __________________ Corresponding Editor: Guido Plazamentioning

confidence: 99%

Section: Orthogonality On Bidimensional Planementioning

confidence: 99%

A suitable ichthyometer for systemic application

Lezama-Cervantes

Godínez-Domínguez

Gómez-Morales

et al. 2017

lajar

View full text Add to dashboard Cite

show abstract

“…Once these interfaces are defined, the implementations of each step can be changed, switched out and redefined without affecting the others. This breakdown was based on Shortis et al's proposed approach to fish recognition [12], although we vary some of their suggestions.…”

Section: A Modulesmentioning

confidence: 99%

“…Larsen et al were able to find a set of features that provided a 76% resubstitution rate using linear discriminant analysis [11]. Shortis et al [12] suggest using a Nearest Neighbour Classifier to validate the candidate regions as 'fish' or 'not fish of interest'.…”

Section: Introductionmentioning

confidence: 99%

A Modular Learning Approach for Fish Counting and Measurement Using Stereo Baited Remote Underwater Video

Westling

Sun

Wang

2014

2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

An approach is suggested for automating fish identification and measurement using stereo Baited Remote Underwater Video footage. Simple methods for identifying fish are not sufficient for measurement, since the snout and tail points must be found, and the stereo data should be incorporated to find a true measurement. We present a modular framework that ties together various approaches in order to develop a generalised system for automated fish detection. A method is also suggested for using machine learning to improve identification. Experimental results indicate the suitability of our approach.

show abstract

“…Examples include fish counting, size measurement, species identification, and behavioral analysis [1,7,9,12,13,18,24,20,27,25,26].…”

Section: Introductionmentioning

confidence: 99%

Automated Analysis of Wild Fish Behavior in a Natural Habitat

Wang

Cullis-Suzuki

Albu

2015

Proceedings of the 2nd International Workshop on Environmental Multimedia Retrieval

View full text Add to dashboard Cite

This paper proposes a novel approach for the analysis of movement and behavior of the Plainfin midshipman (Porichthys notatus) in the wild. It is based on underwater video recordings of the fish in their natural habitat taken inside their nests during reproductive months. During this time, alpha male Plainfin midshipmen rarely leave their nests as they are guarding their eggs, so the proposed approach addresses the issue of detecting subtle motion and nesting behavior as the fish remains relatively sedentary. To the best of our knowledge, this is the first paper to propose an automated method to analyze subtle movements of a highly territorial animal in its natural habitat.Motion detection uses the displacement of SURF (Interest point algorithm) key-point movements from frame to frame to analyze the amount of movement by the fish. Kmeans clustering and other outlier removal techniques are then used to differentiate fish motion from small moving objects in the background and foreground. The analysis of fish behavior uses similarity-based periodicity detection combined with the K-neighbors classifier. Experimental validation with respect to expert-annotated ground truth shows excellent performance for both motion and behavior detection approaches.

show abstract

A review of techniques for the identification and measurement of fish in underwater stereo-video image sequences

Cited by 60 publications

References 29 publications

A suitable ichthyometer for systemic application

A suitable ichthyometer for systemic application

A Modular Learning Approach for Fish Counting and Measurement Using Stereo Baited Remote Underwater Video

Automated Analysis of Wild Fish Behavior in a Natural Habitat

Contact Info

Product

Resources

About