Zhou Tao, Pan Jianjun, Zhang Peiyu, Wei Shanbao, Han Tao
College of Resources and Environmental Sciences, Nanjing Agricultural University, Nanjing 210095, China.
College of Public Administration, Nanjing Agricultural University, Nanjing 210095, China.
Sensors (Basel). 2017 May 25;17(6):1210. doi: 10.3390/s17061210.
Winter wheat is the second largest food crop in China. It is important to obtain reliable winter wheat acreage to guarantee the food security for the most populous country in the world. This paper focuses on assessing the feasibility of in-season winter wheat mapping and investigating potential classification improvement by using SAR (Synthetic Aperture Radar) images, optical images, and the integration of both types of data in urban agricultural regions with complex planting structures in Southern China. Both SAR (Sentinel-1A) and optical (Landsat-8) data were acquired, and classification using different combinations of Sentinel-1A-derived information and optical images was performed using a support vector machine (SVM) and a random forest (RF) method. The interference coherence and texture images were obtained and used to assess the effect of adding them to the backscatter intensity images on the classification accuracy. The results showed that the use of four Sentinel-1A images acquired before the jointing period of winter wheat can provide satisfactory winter wheat classification accuracy, with an F1 measure of 87.89%. The combination of SAR and optical images for winter wheat mapping achieved the best F1 measure-up to 98.06%. The SVM was superior to RF in terms of the overall accuracy and the kappa coefficient, and was faster than RF, while the RF classifier was slightly better than SVM in terms of the F1 measure. In addition, the classification accuracy can be effectively improved by adding the texture and coherence images to the backscatter intensity data.
冬小麦是中国第二大粮食作物。获取可靠的冬小麦种植面积对于保障世界上人口最多国家的粮食安全至关重要。本文重点评估中国南方种植结构复杂的城市农业区域内冬小麦季中制图的可行性，并研究利用合成孔径雷达（SAR）图像、光学图像以及这两种数据的融合来改进分类的潜力。获取了SAR（哨兵-1A）和光学（陆地卫星-8）数据，并使用支持向量机（SVM）和随机森林（RF）方法，利用哨兵-1A衍生信息和光学图像的不同组合进行分类。获取了干涉相干和纹理图像，并用于评估将它们添加到后向散射强度图像对分类精度的影响。结果表明，使用在冬小麦拔节期之前获取的4幅哨兵-1A图像能够提供令人满意的冬小麦分类精度，F1值为87.89%。用于冬小麦制图的SAR和光学图像组合实现了最佳F1值——高达98.06%。在总体精度和kappa系数方面，SVM优于RF，且比RF速度更快，而RF分类器在F1值方面略优于SVM。此外，将纹理和相干图像添加到后向散射强度数据中可以有效提高分类精度。
