当前位置: X-MOL 学术Ecol. Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Advances in image acquisition and processing technologies transforming animal ecological studies
Ecological Informatics ( IF 5.1 ) Pub Date : 2021-01-20 , DOI: 10.1016/j.ecoinf.2021.101212
Sajid Nazir , Muhammad Kaleem

Images and videos have become pervasive in ecological research and the ease of acquiring image data and its subsequent processing can provide answers in research areas such as species recognition, animal behaviour, and population studies which are critical for animal conservation and biodiversity. Technological advances in imaging are enabling data collection from new areas such as from underwater, new modalities such as thermal and new ways of processing such as deep learning. These advances are accelerating due to ease of data collection, better storage and processing technologies with associated lowering costs. The advancements in state-of-the-art machine learning for image and video classification and analysis can directly be applied in ecology. Ecological applications are generally conducted in remote and harsh deployment environments, and therefore present formidable challenges that require appreciation of the limitations of such technologies. The ecological field is poised to make use of images acquired through drones, robotics, and satellites through machine learning for rapid advancements in critical research areas. Timely insights from such data help to understand and protect the species and environment. This paper provides a review of the advancements in image acquisition and processing technologies used in animal ecological studies. We also discuss concepts and technologies that would help foster future ecological research methodologies potentially opening new insights and quickening growth to an already rich and data-intensive field.



中文翻译:

图像采集和处理技术的进步改变了动物的生态学研究

图像和视频已广泛用于生态研究,并且易于获得图像数据及其后续处理可在诸如物种识别,动物行为以及对动物保护和生物多样性至关重要的种群研究等研究领域提供答案。成像技术的进步使人们能够从水下等新领域,热学等新形式以及深度学习等新的处理方式中收集数据。由于数据收集的简便性,更好的存储和处理技术以及相关的降低成本,这些进步正在加速。用于图像和视频分类和分析的最新机器学习技术的进步可以直接应用于生态学。生态应用通常在偏远和恶劣的部署环境中进行,因此提出了艰巨的挑战,需要认识到此类技术的局限性。生态学领域准备利用通过无人机,机器人技术和卫星获取的图像通过机器学习在关键研究领域中快速发展。这些数据的及时见解有助于理解和保护物种和环境。本文概述了动物生态学研究中使用的图像采集和处理技术的进展。我们还将讨论一些概念和技术,这些概念和技术将有助于培养未来的生态研究方法,从而有可能开启新的见解,并加速本已丰富且数据密集的领域的发展。生态学领域准备利用通过无人机,机器人技术和卫星获取的图像通过机器学习在关键研究领域中快速发展。这些数据的及时见解有助于理解和保护物种和环境。本文概述了动物生态学研究中使用的图像采集和处理技术的进展。我们还将讨论一些概念和技术,这些概念和技术将有助于发展未来的生态研究方法,从而有可能开启新的见解并加快本已丰富且数据密集型领域的发展。生态学领域准备利用通过无人机,机器人技术和卫星获取的图像通过机器学习在关键研究领域中快速发展。这些数据的及时见解有助于理解和保护物种和环境。本文概述了动物生态学研究中使用的图像采集和处理技术的进展。我们还将讨论一些概念和技术,这些概念和技术将有助于发展未来的生态研究方法,从而有可能开启新的见解,并加速本已丰富且数据密集的领域的发展。本文概述了动物生态学研究中使用的图像采集和处理技术的进展。我们还将讨论一些概念和技术,这些概念和技术将有助于发展未来的生态研究方法,从而有可能开启新的见解,并加速本已丰富且数据密集的领域的发展。本文概述了动物生态学研究中使用的图像采集和处理技术的进展。我们还将讨论一些概念和技术,这些概念和技术将有助于培养未来的生态研究方法,从而有可能开启新的见解,并加速本已丰富且数据密集的领域的发展。

更新日期:2021-01-29
down
wechat
bug