eprintid: 10203021 rev_number: 6 eprint_status: archive userid: 699 dir: disk0/10/20/30/21 datestamp: 2025-01-08 10:32:28 lastmod: 2025-01-08 10:32:28 status_changed: 2025-01-08 10:32:28 type: article metadata_visibility: show sword_depositor: 699 creators_name: Jenkins, Marcus creators_name: Franklin, Kirsty A creators_name: Nicoll, Malcolm AC creators_name: Cole, Nik C creators_name: Ruhomaun, Kevin creators_name: Tatayah, Vikash creators_name: Mackiewicz, Michal title: Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring ispublished: pub divisions: UCL divisions: B02 divisions: C08 divisions: D09 divisions: F99 keywords: YOLO; object detection; time-lapse imagery; camera-trap imagery; temporal features; spatio-temporal features; wildlife monitoring note: © 2024 by the Authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). abstract: Monitoring animal populations is crucial for assessing the health of ecosystems. Traditional methods, which require extensive fieldwork, are increasingly being supplemented by time-lapse camera-trap imagery combined with an automatic analysis of the image data. The latter usually involves some object detector aimed at detecting relevant targets (commonly animals) in each image, followed by some postprocessing to gather activity and population data. In this paper, we show that the performance of an object detector in a single frame of a time-lapse sequence can be improved by including spatio-temporal features from the prior frames. We propose a method that leverages temporal information by integrating two additional spatial feature channels which capture stationary and non-stationary elements of the scene and consequently improve scene understanding and reduce the number of stationary false positives. The proposed technique achieves a significant improvement of 24% in mean average precision (mAP@0.05:0.95) over the baseline (temporal feature-free, single frame) object detector on a large dataset of breeding tropical seabirds. We envisage our method will be widely applicable to other wildlife monitoring applications that use time-lapse imaging. date: 2024 date_type: published publisher: MDPI AG official_url: https://doi.org/10.3390/s24248002 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2347030 doi: 10.3390/s24248002 lyricists_name: Nicoll, Malcolm lyricists_id: MNICO77 actors_name: Nicoll, Malcolm actors_id: MNICO77 actors_role: owner full_text_status: public publication: Sensors volume: 24 number: 24 article_number: 8002 citation: Jenkins, Marcus; Franklin, Kirsty A; Nicoll, Malcolm AC; Cole, Nik C; Ruhomaun, Kevin; Tatayah, Vikash; Mackiewicz, Michal; (2024) Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring. Sensors , 24 (24) , Article 8002. 10.3390/s24248002 <https://doi.org/10.3390/s24248002>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10203021/1/Jenkins_2024.pdf