2022
DOI: 10.1016/j.isci.2022.104784
|View full text |Cite
|
Sign up to set email alerts
|

Computer vision for assessing species color pattern variation from web-based community science images

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 11 publications
(8 citation statements)
references
References 54 publications
0
8
0
Order By: Relevance
“…iNaturalist has generally been used more for outreach and education (Aristeidou et al, 2021) and investigations of regional species diversity and species geographic ranges (Rosa et al, 2022) than for ecological and evolutionary studies, but this is now changing (Aguillon & Shultz, 2022; Bolt et al, 2022; Fritz & Ihlow, 2022; Putman et al, 2021). Analytical methods for tapping the full potential of citizen science photos (Hantak, Guralnick, Zare, et al, 2022; Leighton et al, 2016; Schiller et al, 2021), and better methods for imaging wildlife and specimens, including camera traps (Steenweg et al, 2017) and 3D models (Medina et al, 2020), will facilitate future studies bringing together photos and specimens in biodiversity science.…”
Section: Discussionmentioning
confidence: 99%
“…iNaturalist has generally been used more for outreach and education (Aristeidou et al, 2021) and investigations of regional species diversity and species geographic ranges (Rosa et al, 2022) than for ecological and evolutionary studies, but this is now changing (Aguillon & Shultz, 2022; Bolt et al, 2022; Fritz & Ihlow, 2022; Putman et al, 2021). Analytical methods for tapping the full potential of citizen science photos (Hantak, Guralnick, Zare, et al, 2022; Leighton et al, 2016; Schiller et al, 2021), and better methods for imaging wildlife and specimens, including camera traps (Steenweg et al, 2017) and 3D models (Medina et al, 2020), will facilitate future studies bringing together photos and specimens in biodiversity science.…”
Section: Discussionmentioning
confidence: 99%
“…The large amount of natural history data we gathered for T. ornata would not have been possible without dedicated researchers that tracked wild turtles with radiotelemetry and individuals willing to contribute observations to citizen science platforms (Irwin, 2018). Citizen science platforms, in fact, represent important sources of biodiversity data that can be leveraged to study organisms across unprecedented spatiotemporal scales of analysis (e.g., Hantak et al, 2022; Perry et al, 2022). Citizen science helped us elucidate the reproductive phenology T. ornata , and it will continue to be important for biodiversity in the future.…”
Section: Discussionmentioning
confidence: 99%
“…Using Google Images, Leighton et al [39] spearheaded the use of community-sourced images to study trait variation. More recently, studies have harnessed the abundance of iNaturalist community science images to examine intraspecific variation in traits like coloration [40][41][42][43], in addition to studying phenological trends [44][45][46][47] and predation rates [16]. Our study is the first to test range-wide colour and climate associations in North American ratsnakes, which is likely due to the challenges with documenting colour in these snakes.…”
Section: (C) Community Science For Examining Species Colour Variationmentioning
confidence: 99%
“…For example, de Solan et al [48] used deep learning to quantify snake mimicry from standardized digital photographs. However, image heterogeneity is inherent in community science images, and Hantak et al [42] developed a highly accurate deep learning model to score a salamander colour polymorphism from iNaturalist images. That study was based on a simple binary classifier (stripe presence/absence), while ratsnake colour categorization is more challenging as colour variation may be more continuous rather than discrete.…”
Section: (C) Community Science For Examining Species Colour Variationmentioning
confidence: 99%