de Lorm Tijmen A, Horswill Catharine, Rabaiotti Daniella, Ewers Robert M, Groom Rosemary J, Watermeyer Jessica, Woodroffe Rosie
Department of Life Sciences Imperial College London Silwood Park UK.
Institute of Zoology Zoological Society of London London UK.
Ecol Evol. 2023 Jul 3;13(7):e10260. doi: 10.1002/ece3.10260. eCollection 2023 Jul.
Reliable estimates of population size and demographic rates are central to assessing the status of threatened species. However, obtaining individual-based demographic rates requires long-term data, which is often costly and difficult to collect. Photographic data offer an inexpensive, noninvasive method for individual-based monitoring of species with unique markings, and could therefore increase available demographic data for many species. However, selecting suitable images and identifying individuals from photographic catalogs is prohibitively time-consuming. Automated identification software can significantly speed up this process. Nevertheless, automated methods for selecting suitable images are lacking, as are studies comparing the performance of the most prominent identification software packages. In this study, we develop a framework that automatically selects images suitable for individual identification, and compare the performance of three commonly used identification software packages; Hotspotter, IS-Pattern, and WildID. As a case study, we consider the African wild dog, , a species whose conservation is limited by a lack of cost-effective large-scale monitoring. To evaluate intraspecific variation in the performance of software packages, we compare identification accuracy between two populations (in Kenya and Zimbabwe) that have markedly different coat coloration patterns. The process of selecting suitable images was automated using convolutional neural networks that crop individuals from images, filter out unsuitable images, separate left and right flanks, and remove image backgrounds. Hotspotter had the highest image-matching accuracy for both populations. However, the accuracy was significantly lower for the Kenyan population (62%), compared to the Zimbabwean population (88%). Our automated image preprocessing has immediate application for expanding monitoring based on image matching. However, the difference in accuracy between populations highlights that population-specific detection rates are likely and may influence certainty in derived statistics. For species such as the African wild dog, where monitoring is both challenging and expensive, automated individual recognition could greatly expand and expedite conservation efforts.
可靠的种群规模和人口统计率估计对于评估濒危物种的状况至关重要。然而，获取基于个体的人口统计率需要长期数据，而这通常成本高昂且难以收集。照片数据提供了一种廉价、非侵入性的方法，可用于对具有独特标记的物种进行基于个体的监测，因此可以增加许多物种可用的人口统计数据。然而，从照片目录中选择合适的图像并识别个体非常耗时。自动化识别软件可以显著加快这一过程。尽管如此，目前缺乏选择合适图像的自动化方法，也缺乏比较最著名识别软件包性能的研究。在本研究中，我们开发了一个框架，可自动选择适合个体识别的图像，并比较三种常用识别软件包（Hotspotter、IS-Pattern和WildID）的性能。作为案例研究，我们以非洲野犬为例，该物种的保护因缺乏具有成本效益的大规模监测而受到限制。为了评估软件包在种内性能的差异，我们比较了两个种群（肯尼亚和津巴布韦）之间的识别准确率，这两个种群的毛色图案明显不同。使用卷积神经网络自动选择合适图像的过程包括从图像中裁剪个体、过滤掉不合适的图像、分离左右侧翼并去除图像背景。Hotspotter对两个种群的图像匹配准确率最高。然而，肯尼亚种群（62%）的准确率明显低于津巴布韦种群（88%）。我们的自动化图像预处理可立即应用于基于图像匹配的扩展监测。然而，种群之间准确率的差异突出表明，特定种群的检测率可能存在，并且可能影响派生统计数据的确定性。对于非洲野犬这样监测既具有挑战性又昂贵的物种，自动化个体识别可以极大地扩展和加快保护工作。
