Fleuré Valentine, Planolles Kévin, Claverie Thomas, Mulot Baptiste, Villéger Sébastien
MARBEC, University Montpellier, CNRS, Ifremer, IRD, Montpellier, France.
ZooParc de Beauval & Beauval Nature, Saint-Aignan, France.
PLoS One. 2025 Aug 11;20(8):e0327577. doi: 10.1371/journal.pone.0327577. eCollection 2025.
Assessing the escalating biodiversity crisis, driven by climate change, habitat destruction, and exploitation, necessitates efficient monitoring strategies to assess species presence and abundance across diverse habitats. Video-based surveys using remote cameras are a promising, non-invasive way to collect valuable data in various environments. Yet, the analysis of recorded videos remains challenging due to time and expertise constraints. Recent advances in deep learning models have enhanced image processing capabilities in both object detection and classification. However, the impacts on models' performances and usage on assessment of biodiversity metrics on videos is yet to be assessed. This study evaluates the impacts of video processing rates, detection and identification model performance, and post-processing algorithms on the accuracy of biodiversity metrics, using simulated remote videos of fish communities and 14,406 simulated automated processing pipelines. We found that a processing rate of one image per second minimizes errors while ensuring detection of all species. However, even near-perfect detection (both recall and precision of 0.99) and identification (accuracy of 0.99) models resulted in overestimation of total abundance, species richness and species diversity due to false positives. We reveal that post-processing model outputs using a confidence threshold approach (i.e., to discard most erroneous predictions while also discarding a smaller proportion of correct predictions) is the most efficient method to accurately estimate biodiversity from videos.
评估由气候变化、栖息地破坏和开发驱动的不断升级的生物多样性危机，需要有效的监测策略来评估不同栖息地中物种的存在和丰度。使用远程摄像头进行基于视频的调查是一种很有前景的非侵入性方法，可以在各种环境中收集有价值的数据。然而，由于时间和专业知识的限制，对录制视频的分析仍然具有挑战性。深度学习模型的最新进展提高了目标检测和分类中的图像处理能力。然而，对模型性能以及在视频生物多样性指标评估中的使用影响尚未得到评估。本研究使用鱼类群落的模拟远程视频和14406条模拟自动处理管道，评估了视频处理速率、检测和识别模型性能以及后处理算法对生物多样性指标准确性的影响。我们发现，每秒处理一张图像的速率在确保检测到所有物种的同时，将误差降至最低。然而，即使是近乎完美的检测（召回率和精确率均为0.99）和识别（准确率为0.99）模型，由于误报，也会导致总丰度、物种丰富度和物种多样性的高估。我们发现，使用置信阈值方法对模型输出进行后处理（即丢弃大多数错误预测，同时也丢弃一小部分正确预测）是从视频中准确估计生物多样性的最有效方法。
