Contour Matching for Fish Species Recognition and Migration Monitoring

Lee, Dah-Jye; Archibald, James K.; Schoenberger, Robert B.; Dennis, Aaron; Shiozawa, Dennis K.

doi:10.1007/978-3-540-78534-7_8

Cited by 30 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The differences of relative errors yield the following outcome ∆ ± σ∆ = 0.111 ± 0.034. Applying the same statistics like in the metal dataset for J = 240 and n2 = n1 = 175 (see equation (1)) one obtains the same correction factor C(240) ≈ 1.002. Again, setting the confidence level to α = 0.01 we can reject the null hypothesis that both distance measures perform equally well since t(240) ≈ 3.278 1.002 > 3 > T239 1 − α 2 ≈ 2.596 .…”

Section: Fish Datasetmentioning

confidence: 74%

“…The parameter α1 ∈ [0, 1] can be interpreted as flexibility of the trend adjustment: Big values refer to a narrow window τ which causes localized offset removal and vice versa. 1 Please note, we do not claim that a windowed average cannot be calculated in constant time which is indeed possible with the help of prefix sums.…”

Section: Moving Average With Constant Memorymentioning

confidence: 98%

“…The fish dataset [1] consists of 350 time series extracted from the silhouettes of fish and exhibits seven distinguishable classes. Five members of the first category are exemplary shown in Fig.…”

Section: Fish Datasetmentioning

confidence: 99%

“…They can be extracted from images by the parametrization of one-dimensional submanifolds in higher dimensional data. [1] and [2] are examples of how fish shapes and motion tracking data can be transformed to such scalar functions.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Gem

Hundt

Schmidt

Schömer

et al. 2014

Proceedings of the 29th Annual ACM Symposium on Applied Computing

View full text Add to dashboard Cite

The widespread use of digital sensor systems causes a tremendous demand for high-quality time series analysis tools. In this domain the majority of data mining algorithms relies on established distance measures like Dynamic Time Warping (DTW) or Euclidean distance (ED). However, the notion of similarity induced by ED and DTW may lead to unsatisfactory clusterings. In order to address this shortcoming we introduce the Gliding Elastic Match (GEM) algorithm. It determines an optimal local similarity measure of a query time series Q and a subject time series S. The measure is invariant under both local deformation on the measurementaxis and scaling in the time domain. GEM is compared to ED and (un)constrained DTW in terms of matching quality for several datasets and outperforms the competitors in most cases. In order to accelerate the application of GEM to large-scale datasets, we further present an efficient CUDA parallelization.

show abstract

Section: Fish Datasetmentioning

confidence: 74%

Section: Moving Average With Constant Memorymentioning

confidence: 98%

Section: Fish Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Gem

Hundt

Schmidt

Schömer

et al. 2014

Proceedings of the 29th Annual ACM Symposium on Applied Computing

View full text Add to dashboard Cite

show abstract

“…A real challenge for this kind of application is the automatic discrimination of isolated fish in the image, ensuring that the object identified is a whole fish (hereinafter "goodfish") rather than a portion of it, or two or more overlapped fish (hereinafter "bad-fish") (Costa 2006 et al). The characterisation of a single fish is an essential processing step in the most significant applications of underwater video, such as fish detection, species identification (Spampiato et al, 2010) (Zion et al, 2007), biometric measurements (Tillett et al 2000) (Harvey et al 2003) (Costa et al 2006), biomass estimation in fish cages or tanks (Lines et al 2001) (Martinez et al 2003, tracking and counting fish (Lee et al 2004).…”

Section: Introductionmentioning

confidence: 99%

Vision-based discrimination of tuna individuals in grow-out cages through a fish bending model

Atienza-Vanacloig

Andreu-Garcı́a

López-García

et al. 2016

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

This paper proposes a robust deformable adaptive 2D model, based on computer vision methods, that automatically fits the body (ventral silhouette) of Bluefin tuna while swimming. Our model (without human intervention) adjusts to fish shape and size, obtaining fish orientation, bending to fit their flexion motion and has proved robust enough to overcome possible segmentation inaccuracies. Once the model has been successfully fitted to the fish it can ensure that the detected object is a tuna and not parts of fish or other objects. Automatic requirements of the fishing industry like biometric measurement, specimen counting or catch biomass estimation could then be addressed using a stereoscopic system and meaningful information extracted from our model. We also introduce a fitting procedure based on a fitting parameter-Fitting Error Index (FEI)-which permits us to know the quality of the results. In the experiments our model has achieved very high success rates (up to 90%) discriminating individuals in highly complex images acquired for us in real conditions in the Mediterranean Sea. Conclusions and future improvements to the proposed model are also discussed.

show abstract