Automated processing and identification of benthic invertebrate samples

Lytle, David A.; Martínez-Muñoz, Gonzalo; Zhang, Wei; Larios, Natalia; Shapiro, Linda G.; Paasch, Robert; Moldenke, Andrew R.; Mortensen, Eric N.; Todorovic, Sinisa; Dietterich, Thomas G.

doi:10.1899/09-080.1

Cited by 61 publications

(58 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automated insect species identification presents several chal- lenges, such as small inter-species differences due to closely related species and significant intra-species variation due to changes in position, orientation, pose, and variations in developmental and degradation stages overcome by our method. Our set of experiments with 29 insect taxa are more ambitious in scope than previous studies [9,12,13] with 9 taxa and show promise for real-world automated biomonitoring systems. The spatial-pyramid kernel classifiers achieve higher classification rates than the random trees and RBF kernel classifiers, reaching a similar performance with just a single type of feature.…”

Section: Resultsmentioning

confidence: 97%

See 1 more Smart Citation

Stacked spatial-pyramid kernel: An object-class recognition method to combine scores from random trees

Larios

Lin

Zhang

et al. 2011

2011 IEEE Workshop on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

The combination of local features, complementary feature types, and relative position information has been successfully applied to many object-class recognition tasks. Stacking is a common classification approach that combines the results from multiple classifiers, having the added benefit of allowing each classifier to handle a different feature space. However, the standard stacking method by its own nature discards any spatial information contained in the features, because only the combination of raw classification scores are input to the final classifier. The objectclass recognition method proposed in this paper combines different feature types in a new stacking framework that efficiently quantizes input data and boosts classification accuracy, while allowing the use of spatial information. This classification method is applied to the task of automated insect-species identification for biomonitoring purposes.The test data set for this work contains 4722 images with 29 insect species, belonging to the three most common orders used to measure stream water quality, several of which are closely related and very difficult to distinguish. The specimens are in different 3D positions, different orientations, and different developmental and degradation stages with wide intra-class variation. On this very challenging data set, our new algorithm outperforms other classifiers, showing the benefits of using spatial information in the stacking framework with multiple dissimilar feature types.

show abstract

Section: Resultsmentioning

confidence: 97%

“…In [9,12,13] experiments on nine stonefly taxa (Plecoptera) obtained very low classification errors. Earlier research [8] from the same group of authors evaluated the feasibility of automated stonefly species identification with existing computer vision and machine learning methods.…”

Section: Insect-species Classificationmentioning

confidence: 99%

Stacked spatial-pyramid kernel: An object-class recognition method to combine scores from random trees

Larios

Lin

Zhang

et al. 2011

2011 IEEE Workshop on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…Computer vision technologies can support the study of a variety of animal populations in their natural environment [1], [2], [3], [4], [5]. However, the technical constraints of insitu video monitoring yield potential errors in the extracted data.…”

Section: Introductionmentioning

confidence: 99%

“…3 Species often swimming in and out cameras' field of view are over-estimated. 4 Fish in groups occlude each other and are under-estimated. 5 Large granularity of nets' and fish traps' mesh can let small fish slip through.…”

mentioning

confidence: 99%

Multifactorial uncertainty assessment for monitoring population abundance using computer vision

Beauxis-Aussalet

Hardman

2015

2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

Abstract-Computer vision enables in-situ monitoring of animal populations at a lower cost and with less ecosystem disturbance than with human observers. However, computer vision uncertainty may not be fully understood by end-users, and the uncertainty assessments performed by technology experts may not fully address end-user needs. This knowledge gap can yield misinterpretations of computer vision data, and trust issues impeding the transfer of valuable technologies. We bridge this gap with a user-centered analysis of the uncertainty issues. Key uncertainty factors, and their interactions, are identified from the perspective of a core task in ecology research and beyond: counting individuals from different classes. We highlight factors for which uncertainty assessment methods are currently unavailable. The remaining uncertainty assessment methods are not interoperable. Hence it is currently difficult to assess the combined results of multiple uncertainty factors, and their impact on end-user counting tasks. We propose a framework for assessing the multifactorial uncertainty propagation along the data processing pipeline. It integrates methods from both computer vision and ecology domains, and aims at supporting the statistical analysis of abundance trends for population monitoring. Our typology of uncertainty factors and our assessment methods were drawn from interviews with marine ecology and computer vision experts, and from prior work for a fish monitoring application. Our findings contribute to enabling scientific research based on computer vision.

show abstract

“…Currently, identification process is made manually by biologists or taxonomists. Automated benthic macroinvertebrate identification [6]- [10], [12]- [14], [16], [17], [19], [20] has gained a scant attention among computer scientists, but it can save resources and enable wider and more efficient biomonitoring.…”

Section: Introductionmentioning

confidence: 99%

Half-against-half structure in classification of benthic macroinvertebrate images

Joutsijoki

2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Benthic macroinvertebrates play a key role when water quality assessments are made. Benthic macroinvertebrates are difficult to identify and their identification need special expertise. Furthermore, manual identification is slow and expensive process. This paper concerns benthic macroinverte-brate classification when Half-Against-Half (HAH) structure was applied to Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) and Minimum Mahalanobis Distance Classifier (MMDC) classifiers. Especially, LDA, QDA and MMDC classifiers were for first time applied with HAH structure to benthic macroinvertebrate classification. We performed thorough experiments altogether with ten methods. In the case of HAH-SVM we managed to improve classification results from the earlier research by using a different approach to class division problem. We obtained 96.1% classification accuracy with Radial Basis Function (RBF) kernel. Moreover, new variants of LDA, QDA and MMDC classification methods achieved 89.5% and 91.6% classification accuracies which can be considered as a good result in such a difficult classification task.

show abstract

Automated processing and identification of benthic invertebrate samples

Cited by 61 publications

References 8 publications

Stacked spatial-pyramid kernel: An object-class recognition method to combine scores from random trees

Stacked spatial-pyramid kernel: An object-class recognition method to combine scores from random trees

Multifactorial uncertainty assessment for monitoring population abundance using computer vision

Half-against-half structure in classification of benthic macroinvertebrate images

Contact Info

Product

Resources

About