Image background assessment as a novel technique for insect microhabitat
identification
- URL: http://arxiv.org/abs/2305.18207v1
- Date: Fri, 26 May 2023 13:14:26 GMT
- Title: Image background assessment as a novel technique for insect microhabitat
identification
- Authors: Sesa Singha Roy, Reid Tingley and Alan Dorin
- Abstract summary: Climate change, urbanisation and agriculture are changing the way insects occupy habitats.
Traditional studies of insect microhabitat use can now be supplemented by machine learning-based insect image analysis.
We analysed the microhabitats of three insect species common across Australia: Drone flies, European honeybees and European wasps.
We found flies and honeybees in natural microhabitats, confirming their need for natural havens within cities.
- Score: 2.1485350418225244
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The effects of climate change, urbanisation and agriculture are changing the
way insects occupy habitats. Some species may utilise anthropogenic
microhabitat features for their existence, either because they prefer them to
natural features, or because of no choice. Other species are dependent on
natural microhabitats. Identifying and analysing these insects' use of natural
and anthropogenic microhabitats is important to assess their responses to a
changing environment, for improving pollination and managing invasive pests.
Traditional studies of insect microhabitat use can now be supplemented by
machine learning-based insect image analysis. Typically, research has focused
on automatic insect classification, but valuable data in image backgrounds has
been ignored. In this research, we analysed the image backgrounds available on
the ALA database to determine their microhabitats. We analysed the
microhabitats of three insect species common across Australia: Drone flies,
European honeybees and European wasps. Image backgrounds were classified as
natural or anthropogenic microhabitats using computer vision and machine
learning tools benchmarked against a manual classification algorithm. We found
flies and honeybees in natural microhabitats, confirming their need for natural
havens within cities. Wasps were commonly seen in anthropogenic microhabitats.
Results show these insects are well adapted to survive in cities. Management of
this invasive pest requires a thoughtful reduction of their access to
human-provided resources. The assessment of insect image backgrounds is
instructive to document the use of microhabitats by insects. The method offers
insight that is increasingly vital for biodiversity management as urbanisation
continues to encroach on natural ecosystems and we must consciously provide
resources within built environments to maintain insect biodiversity and manage
invasive pests.
Related papers
- Artificial Immune System of Secure Face Recognition Against Adversarial Attacks [67.31542713498627]
optimisation is required for insect production to realise its full potential.
This can be by targeted improvement of traits of interest through selective breeding.
This review combines knowledge from diverse disciplines, bridging the gap between animal breeding, quantitative genetics, evolutionary biology, and entomology.
arXiv Detail & Related papers (2024-06-26T07:50:58Z) - A machine learning pipeline for automated insect monitoring [17.034158815607128]
Camera traps, conventionally used for monitoring terrestrial vertebrates, are now being modified for insects, especially moths.
We describe a complete, open-source machine learning-based software pipeline for automated monitoring of moths via camera traps.
arXiv Detail & Related papers (2024-06-18T19:51:16Z) - Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding [15.383106771910274]
Current machine vision model requires a large volume of data to achieve high performance.
We introduce a novel "Insect-1M" dataset, a game-changing resource poised to revolutionize insect-related foundation model training.
Covering a vast spectrum of insect species, our dataset, including 1 million images with dense identification labels of taxonomy hierarchy and insect descriptions, offers a panoramic view of entomology.
arXiv Detail & Related papers (2023-11-26T06:17:29Z) - SatBird: Bird Species Distribution Modeling with Remote Sensing and
Citizen Science Data [68.2366021016172]
We present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird.
We also provide a dataset in Kenya representing low-data regimes.
We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks.
arXiv Detail & Related papers (2023-11-02T02:00:27Z) - Deep learning powered real-time identification of insects using citizen
science data [17.13608307250744]
InsectNet can identify invasive species, provide fine-grained insect species identification, and work effectively in challenging backgrounds.
It can also abstain from making predictions when uncertain, facilitating seamless human intervention and making it a practical and trustworthy tool.
arXiv Detail & Related papers (2023-06-04T23:56:53Z) - Application of the YOLOv5 Model for the Detection of Microobjects in the
Marine Environment [101.18253437732933]
The efficiency of using the YOLOV5 machine learning model for solving the problem of automatic de-tection and recognition of micro-objects in the marine environment is studied.
arXiv Detail & Related papers (2022-11-28T10:58:50Z) - Neuroevolution-based Classifiers for Deforestation Detection in Tropical
Forests [62.997667081978825]
Millions of hectares of tropical forests are lost every year due to deforestation or degradation.
Monitoring and deforestation detection programs are in use, in addition to public policies for the prevention and punishment of criminals.
This paper proposes the use of pattern classifiers based on neuroevolution technique (NEAT) in tropical forest deforestation detection tasks.
arXiv Detail & Related papers (2022-08-23T16:04:12Z) - Florida Wildlife Camera Trap Dataset [48.99466876948454]
We introduce a challenging wildlife camera trap classification dataset collected from two different locations in Southwestern Florida.
The dataset consists of 104,495 images featuring visually similar species, varying illumination conditions, skewed class distribution, and including samples of endangered species.
arXiv Detail & Related papers (2021-06-23T18:53:15Z) - I-Nema: A Biological Image Dataset for Nematode Recognition [3.1918817988202606]
Nematode worms are one of most abundant metazoan groups on the earth, occupying diverse ecological niches.
Accurate recognition or identification of nematodes are of great importance for pest control, soil ecology, bio-geography, habitat conservation and against climate changes.
Computer vision and image processing have witnessed a few successes in species recognition of nematodes; however, it is still in great demand.
arXiv Detail & Related papers (2021-03-15T12:29:37Z) - Dynamic $\beta$-VAEs for quantifying biodiversity by clustering
optically recorded insect signals [0.6091702876917281]
We propose an adaptive variant of the variational autoencoder (VAE) capable of clustering data by phylogenetic groups.
We demonstrate the usefulness of the dynamic $beta$-VAE on optically recorded insect signals from regions of southern Scandinavia.
arXiv Detail & Related papers (2021-02-10T16:14:13Z) - Automatic image-based identification and biomass estimation of
invertebrates [70.08255822611812]
Time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed.
We propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology.
We use state-of-the-art Resnet-50 and InceptionV3 CNNs for the classification task.
arXiv Detail & Related papers (2020-02-05T21:38:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.