Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions

Tudur David; Matt Jones; Paul Cross; Cristiano Palego

doi:10.1109/EAIS51927.2022.9787692

Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions

Tudur David
, Matt Jones
, Paul Cross
, Cristiano Palego

Bangor University

Research output: Chapter in Book/Report/Conference proceeding › Other chapter contribution › peer-review

Abstract

Insects have experienced dramatic declines over the past 20 years. This has driven the need to monitor populations in relation to the impact of weather conditions and mitigations to conserve insect communities. A machine learning approach is introduced to detect insect collisions on car number plates by considering the differences between number plate images at the start and end of a journey. This is subsequently correlated with various weather conditions and journey parameters to monitor changing insect populations. The present approach does not impose stringent requirements on the resolution/format of plate images, nor involves application of physical frames for image collection.

Original language	English
Title of host publication	202022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)
Publisher	IEEE
Number of pages	5
DOIs	https://doi.org/10.1109/EAIS51927.2022.9787692
Publication status	Published - 6 Jun 2022

Publication series

Name	IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)
Publisher	IEEE
ISSN (Print)	2186-0151

Keywords

image analysis
insect monitoring
machine learning
number plate recognition
pattern recognition

Access to Document

10.1109/EAIS51927.2022.9787692

Cite this

David, T., Jones, M., Cross, P., & Palego, C. (2022). Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions. In 202022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS) (IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)). IEEE. https://doi.org/10.1109/EAIS51927.2022.9787692

@inbook{f909ad005b9c4dd881ed42c9e3dabfc7,

title = "Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions",

abstract = "Insects have experienced dramatic declines over the past 20 years. This has driven the need to monitor populations in relation to the impact of weather conditions and mitigations to conserve insect communities. A machine learning approach is introduced to detect insect collisions on car number plates by considering the differences between number plate images at the start and end of a journey. This is subsequently correlated with various weather conditions and journey parameters to monitor changing insect populations. The present approach does not impose stringent requirements on the resolution/format of plate images, nor involves application of physical frames for image collection.",

keywords = "image analysis, insect monitoring, machine learning, number plate recognition, pattern recognition",

author = "Tudur David and Matt Jones and Paul Cross and Cristiano Palego",

year = "2022",

month = jun,

day = "6",

doi = "10.1109/EAIS51927.2022.9787692",

language = "English",

series = "IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)",

publisher = "IEEE",

booktitle = "202022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)",

}

Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions. / David, Tudur; Jones, Matt; Cross, Paul et al.
202022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS). IEEE, 2022. (IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)).

Research output: Chapter in Book/Report/Conference proceeding › Other chapter contribution › peer-review

TY - CHAP

T1 - Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions

AU - David, Tudur

AU - Jones, Matt

AU - Cross, Paul

AU - Palego, Cristiano

PY - 2022/6/6

Y1 - 2022/6/6

N2 - Insects have experienced dramatic declines over the past 20 years. This has driven the need to monitor populations in relation to the impact of weather conditions and mitigations to conserve insect communities. A machine learning approach is introduced to detect insect collisions on car number plates by considering the differences between number plate images at the start and end of a journey. This is subsequently correlated with various weather conditions and journey parameters to monitor changing insect populations. The present approach does not impose stringent requirements on the resolution/format of plate images, nor involves application of physical frames for image collection.

AB - Insects have experienced dramatic declines over the past 20 years. This has driven the need to monitor populations in relation to the impact of weather conditions and mitigations to conserve insect communities. A machine learning approach is introduced to detect insect collisions on car number plates by considering the differences between number plate images at the start and end of a journey. This is subsequently correlated with various weather conditions and journey parameters to monitor changing insect populations. The present approach does not impose stringent requirements on the resolution/format of plate images, nor involves application of physical frames for image collection.

KW - image analysis

KW - insect monitoring

KW - machine learning

KW - number plate recognition

KW - pattern recognition

U2 - 10.1109/EAIS51927.2022.9787692

DO - 10.1109/EAIS51927.2022.9787692

M3 - Other chapter contribution

T3 - IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)

BT - 202022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)

PB - IEEE

ER -

Insect Collision Detection Using Machine Learning with Correlation to Climatic Conditions

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this