Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Two-Signal Set and Adaptive Spectral Decomposition Algorithm for Estimating the Phase Velocity of Dispersive Lamb Wave Mode.

Sensors (Basel, Switzerland)·2026
Same author

Smart Capacitive Transducer for High-Frequency Vibration Measurement.

Sensors (Basel, Switzerland)·2025
Same author

IoT Sensor Network for Wild-Animal Detection near Roads.

Sensors (Basel, Switzerland)·2023
See all related articles

Related Experiment Video

Updated: Jan 16, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K

Image Processing Algorithms Analysis for Roadside Wild Animal Detection.

Mindaugas Knyva1, Darius Gailius2, Šarūnas Kilius1

  • 1Department of Electronics Engineering, Kaunas University of Technology, Studentu Str. 50-457, 51368 Kaunas, Lithuania.

Sensors (Basel, Switzerland)
|September 27, 2025
PubMed
Summary

A motion detection method offers the best solution for roadside wild animal detection using thermal imagery, achieving high accuracy and sensitivity to prevent wildlife-vehicle collisions in embedded systems.

Keywords:
embedded systemsimage processing algorithmsmotion detectionroadside surveillancethermal imagingwild animal detection

More Related Videos

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Related Experiment Videos

Last Updated: Jan 16, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K
SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Wildlife Management

Background:

  • Wildlife-vehicle collisions pose significant risks to both animals and humans.
  • Effective detection systems are crucial for mitigating these collisions.
  • Embedded systems offer a viable solution for real-time roadside monitoring.

Purpose of the Study:

  • To comparatively analyze five image processing techniques for roadside wild animal detection.
  • To identify an optimal method for implementation in embedded systems.
  • To enhance road safety by reducing wildlife-vehicle collisions.

Main Methods:

  • Evaluated bilateral filtering with SIFT, Gaussian filtering with Canny edge detection, color quantization, motion detection, and YOLOv8n neural network.
  • Applied algorithms to thermal imagery from a custom roadside surveillance system.
  • Assessed performance based on execution time, sensitivity, specificity, and accuracy.

Main Results:

  • Motion detection yielded the highest sensitivity (92.31%) and accuracy (87.50%).
  • Bilateral filtering offered the fastest execution time (0.093 s).
  • Canny edge detection provided high specificity (90.00%).

Conclusions:

  • Motion detection is the preferred method for reliable roadside animal detection due to its high sensitivity and accuracy.
  • The chosen method demonstrates robustness across diverse datasets, though performance may vary.
  • Further development is recommended for integration into embedded systems for collision mitigation.