Riechmann, Miklas; Gardiner, Ross; Waddington, Kai; Rueger, Ryan; Leymarie, Frederic Fol and Rueger, Stefan. 2022. Motion vectors and deep neural networks for video camera traps. Ecological Informatics, 69, 101657. ISSN 1574-9541 [Article]

Preview	Text 1-s2.0-S1574954122001066-main.pdf - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview
	Text (Plain Text Bibliography) bibliography.txt - Bibliography Download (8kB)

Abstract or Description

Commercial camera traps are usually triggered by a Passive Infra-Red (PIR) motion sensor necessitating a delay between triggering and the image being captured. This often seriously limits the ability to record images of small and fast moving animals. It also results in many “empty” images, e.g., owing to moving foliage against a background of different temperature. In this paper we detail a new triggering mechanism based solely on the camera sensor. This is intended for use by citizen scientists and for deployment on an affordable, compact, low-power Raspberry Pi computer (RPi). Our system introduces a video frame filtering pipeline consisting of movement and image-based processing. This makes use of Machine Learning (ML) feasible on a live camera stream on an RPi. We describe our free and open-source software implementation of the system; introduce a suitable ecology efficiency measure that mediates between specificity and recall; provide ground-truth for a video clip collection from camera traps; and evaluate the effectiveness of our system thoroughly. Overall, our video camera trap turns out to be robust and effective.

Item Type:	Article
Identification Number (DOI):	https://doi.org/10.1016/j.ecoinf.2022.101657
Additional Information:	This research is supported in part by the project COS4CLOUD, which has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 863463. COS4CLOUD is a project coordinated by the Institut de Ciències del Mar ICM-CSIC, based in Barcelona (Spain).
Keywords:	AI, Computer vision, Machine learning, Motion vectors, Video camera trap, Video pipeline
Departments, Centres and Research Units:	Computing
Dates:	Date Event July 2022 Published 18 May 2022 Published Online 25 April 2022 Accepted 9 September 2021 Submitted
Item ID:	31943
Date Deposited:	23 Jun 2022 15:41
Last Modified:	23 Jun 2022 15:41
Peer Reviewed:	Yes, this version has been peer-reviewed.
URI:	https://research.gold.ac.uk/id/eprint/31943

View statistics for this item...

Edit Record (login required)