Semiautomated identification of a large number of hoverfly (Diptera: Syrphidae) species based on wing measurements

Mielczarek, Łukasz; Tofilski, Adam

doi:10.1080/00305316.2017.1404947

Cited by 6 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Larvae of a great number of hoverfly species are predacious on various agricultural pests, for example, softbodied Hemiptera (especially aphids), larvae of other Diptera, Acari and so on (Rojo et al 2003), and can be used as important biocontrol agents (Wojciechowicz-_ Zytko and Wnuk 2012). Despite of the great ecological and economic value, classification of this huge family is still confined to traditional morphological taxonomy and reliable identification can only be achieved by limited experienced taxonomists (Mielczarek and Tofilski 2018). To facilitate the species diagnosis, molecular biology and DNA barcoding studies on Syrphidae should be payed enough attention to.…”

mentioning

confidence: 99%

Characterization and phylogenetic analysis of the complete mitochondrial genome of Eristalia cerealis (Diptera: Syrphidae)

Yan

Feng

Song

et al. 2020

Mitochondrial DNA Part B

View full text Add to dashboard Cite

The complete mitochondrial genome of Eristalia cerealis was sequenced and reported here. The circle genome of the syrphid fly is 15,348 bp in length. There are 38 sequence elements including 13 protein coding genes, 22 tRNA genes, 2 rRNA genes, and a control region. The order of all elements was the same with that of E. tenax. With 2 species from Muscidae and Drosophilidae as outgroups, phylogenetic relationships of 10 Syrphidae species based on mitogenomes were in complete agreement with their taxonomic relationships based on morphological characteristics. Our result will provide more fundamental data to the development of the molecular systematics of Syrphidae.

show abstract

mentioning

confidence: 99%

Characterization and phylogenetic analysis of the complete mitochondrial genome of Eristalia cerealis (Diptera: Syrphidae)

Yan

Feng

Song

et al. 2020

Mitochondrial DNA Part B

View full text Add to dashboard Cite

show abstract

“…The development of AI tools for arthropod classification started with a focus on particular taxa and/or the identification of museum specimens with a homogeneous image background. For example, pictures taken of arthropod wings in controlled settings (i.e., under the microscope) can identify several groups of bees 19 , butterflies 20 , 21 and syrphid flies 22 . The application of CNNs on arthropod identification ranges from a few to multiple taxa and considers a growing number of images, for example, nine tiger beetles genera and 380 images 23 , nine groups of arthropods and nearly 2000 images 24 , ten butterfly species and nearly 18,000 images 21 , 36 bumble bee species and nearly 90,000 images 6 .…”

Section: Introductionmentioning

confidence: 99%

YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images

Stark,

Ştefan,

Wurm

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Develoment of image recognition AI algorithms for flower-visiting arthropods has the potential to revolutionize the way we monitor pollinators. Ecologists need light-weight models that can be deployed in a field setting and can classify with high accuracy. We tested the performance of three deep learning light-weight models, YOLOv5nano, YOLOv5small, and YOLOv7tiny, at object recognition and classification in real time on eight groups of flower-visiting arthropods using open-source image data. These eight groups contained four orders of insects that are known to perform the majority of pollination services in Europe (Hymenoptera, Diptera, Coleoptera, Lepidoptera) as well as other arthropod groups that can be seen on flowers but are not typically considered pollinators (e.g., spiders-Araneae). All three models had high accuracy, ranging from 93 to 97%. Intersection over union (IoU) depended on the relative area of the bounding box, and the models performed best when a single arthropod comprised a large portion of the image and worst when multiple small arthropods were together in a single image. The model could accurately distinguish flies in the family Syrphidae from the Hymenoptera that they are known to mimic. These results reveal the capability of existing YOLO models to contribute to pollination monitoring.

show abstract

“…The development of AI tools for arthropod classification started with a focus on particular taxa and/or the identification of museum specimens with a homogeneous image background. For example, pictures taken of arthropod wings in controlled settings (i.e., under the microscope) can identify several groups of bees 19 , butterflies 20,21 and syrphid flies 22 . The application of CNNs on arthropod identification ranges from a few to multiple taxa and considers a growing number of images, for example, nine tiger beetles genera and 380 images 23 , nine groups of arthropods and nearly 2000 images 24 , ten butterfly species and nearly 18,000 images 21 , 36 bumble bee species and nearly 90,000 images 6 .…”

Section: Introductionmentioning

confidence: 99%

YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images

Stark

Ștefan

Wurm

et al. 2023

Preprint

View full text Add to dashboard Cite

Develoment of image recognition AI algorithms for flower-visiting arthropods has the potential to revolutionize the way we monitor pollinators. Ecologists need light-weight models that can be deployed in a field setting and can classify with high accuracy. We tested the performance of three deep learning light-weight models, YOLOv5nano, YOLOv5small, and YOLOv7tiny, at object recognition and classification in real time on eight groups of flower-visiting arthropods using open-source image data. These eight groups contained four orders of insects that are known to perform the majority of pollination services in Europe (Hymenoptera, Diptera, Coleoptera, Lepidoptera) as well as other arthropod groups that can be seen on flowers but are not typically considered pollinators (e.g., spiders-Araneae). All three models had high accuracy, ranging from 93% to 97%. Intersection over union (IoU) depended on the relative area of the bounding box, and the models performed best when a single arthropod comprised a large portion of the image and worst when multiple small arthropods were together in a single image. The model could accurately distinguish flies in the family Syrphidae from the Hymenoptera that they are known to mimic. These results reveal the capability of existing YOLO models to contribute to pollination monitoring.

show abstract

Semiautomated identification of a large number of hoverfly (Diptera: Syrphidae) species based on wing measurements

Cited by 6 publications

References 45 publications

Characterization and phylogenetic analysis of the complete mitochondrial genome of Eristalia cerealis (Diptera: Syrphidae)

Characterization and phylogenetic analysis of the complete mitochondrial genome of Eristalia cerealis (Diptera: Syrphidae)

YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images

YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images

Contact Info

Product

Resources

About