基于低秩矩阵恢复的作物器官自动提取方法

为了解决精准农业中作物器官的自动提取问题, 以玉米雄穗为例, 提出一种基于低秩矩阵恢复的作物器官自动提取方法。 作物生长图像是由背景和器官两大元素组成, 在图像特征空间则表现为一个低秩矩阵和一个稀疏矩阵之和。 利用低秩矩阵恢复算法求解代表器官的稀疏矩阵。 为了保证恢复时背景是低秩的, 利用作物生长历史数据, 学习最佳的转换矩阵。 最后, 利用动态阈值分割以及色度鄄亮度查找表完成器官的准确提取。实验结果表明, 该方法取得了93. 9%的最高性能值和2. 86%的最低标准差, 在多品种、 实际农田复杂环境下能获得更好的提取结果。

Image-Based Method for Automatic Crop Organ Extractio by Low-Rank Matrix Recovery

In order to extract crop organ from images accurately in precision agriculture, an image-based method based on low-rank matrix recovery is proposed. A crop image is considered to be compose of two factors: background and organ. In a certain feature space, the image is represented as a low-rank matrix plus sparse noises. The organ is then extracted by identifying the sparse noises when using low-rank matrix recovery algorithm. To ensure the rank of background is low, a linear transform for the feature space is introduced and that historical data is ured . Dynamic threshold segmentation followed by vegetation removing techniques are ultimately adopted in the final step. The experimental results on the benchmark farmland show that our method achieves competitive performance, compared to the other well-established methods, yielding the highest performance of 93. 9% with the lowest standard deviation of 2. 86%, which means our method is more robust and not sensitive to the complex environmental elements and different cultivars.