The Institute for Sustainable Industries and Liveable Cities (ISILC), College of Engineering and Science, Victoria University, Melbourne, Australia.
School of Computing and Mathematics, Charles Sturt University, Port Macquarie, NSW, Australia.
PLoS One. 2022 Jul 27;17(7):e0270625. doi: 10.1371/journal.pone.0270625. eCollection 2022.
Automated monitoring of vegetation health in a landscape is often attributed to calculating values of various vegetation indexes over a period of time. However, such approaches suffer from an inaccurate estimation of vegetational change due to the over-reliance of index values on vegetation's colour attributes and the availability of multi-spectral bands. One common observation is the sensitivity of colour attributes to seasonal variations and imaging devices, thus leading to false and inaccurate change detection and monitoring. In addition, these are very strong assumptions in a citizen science project. In this article, we build upon our previous work on developing a Semantic Vegetation Index (SVI) and expand it to introduce a semantic vegetation health monitoring platform to monitor vegetation health in a large landscape. However, unlike our previous work, we use RGB images of the Australian landscape for a quarterly series of images over six years (2015-2020). This Semantic Vegetation Index (SVI) is based on deep semantic segmentation to integrate it with a citizen science project (Fluker Post) for automated environmental monitoring. It has collected thousands of vegetation images shared by various visitors from around 168 different points located in Australian regions over six years. This paper first uses a deep learning-based semantic segmentation model to classify vegetation in repeated photographs. A semantic vegetation index is then calculated and plotted in a time series to reflect seasonal variations and environmental impacts. The results show variational trends of vegetation cover for each year, and the semantic segmentation model performed well in calculating vegetation cover based on semantic pixels (overall accuracy = 97.7%). This work has solved a number of problems related to changes in viewpoint, scale, zoom, and seasonal changes in order to normalise RGB image data collected from different image devices.
自动化监测景观中的植被健康状况通常归因于在一段时间内计算各种植被指数的值。然而，由于指数值过分依赖植被的颜色属性和多光谱波段的可用性，因此这种方法存在植被变化估计不准确的问题。一个常见的观察结果是颜色属性对季节性变化和成像设备的敏感性，从而导致错误和不准确的变化检测和监测。此外，这些在公民科学项目中是非常强的假设。在本文中，我们基于之前开发语义植被指数（SVI）的工作，并对其进行扩展，引入了一个语义植被健康监测平台，以监测大面积景观中的植被健康状况。然而，与我们之前的工作不同，我们使用澳大利亚景观的 RGB 图像进行了六年（2015-2020 年）的季度系列图像。这个语义植被指数（SVI）是基于深度学习的语义分割来整合公民科学项目（Fluker Post）进行自动化环境监测的。它已经收集了来自澳大利亚各地的 168 个不同地点的数千张由不同访客分享的植被图像，这些图像来自六年。本文首先使用基于深度学习的语义分割模型对重复拍摄的植被进行分类。然后计算语义植被指数并在时间序列中绘制，以反映季节性变化和环境影响。结果显示了每年植被覆盖的变化趋势，并且语义分割模型在基于语义像素计算植被覆盖方面表现良好（总体准确性=97.7%）。这项工作解决了与视角、比例、缩放和季节性变化有关的许多问题，以便对来自不同图像设备的 RGB 图像数据进行归一化。
