ABSTRACT

The work proposed a method for recognising the green grapes in the orchard based on multi-source image fusion. First, the acquired multi-source images were denoised based on median filtering and wavelet transform. After extracting the feature points by the improved SURF (speeded up robust features) method, the registration was completed based on the consistency of feature offset and the affine relationship between images. The registered multi-source images were fused based on the CS (compressed sensing) and NSCT-DWT (non-down sampled contourlet transform-discrete wavelet transform). Then the MI-OPT (mutual-information optimal threshold) and the minimum circumscribed rectangle were used to segment the fused images and recognise fruits. The experimental results showed that the information of the target fruits in the fused images was complete. Therefore, compared with the K-means method using colour components of the visible light image and the OTSU (proposed by Nobuyuki Otsu and named after him) method based on near-infrared image, the fruit region obtained by the algorithm in the work was complete. On this basis, the average recognition rate of green grapes reached 92.1%.

摘要

提出了一种基于多源图像融合的果园绿葡萄识别方法。首先，基于中值滤波和小波变换对获取的多源图像进行去噪。通过改进的SURF（加速鲁棒特征）方法提取特征点后，基于特征偏移的一致性和图像之间的仿射关系完成配准。基于 CS（压缩感知）和 NSCT-DWT（非下采样轮廓波变换-离散小波变换）对配准的多源图像进行融合。然后使用MI-OPT（互信息最优阈值）和最小外接矩形对融合图像进行分割并识别水果。实验结果表明，融合图像中目标水果的信息是完整的。因此，与使用可见光图像颜色分量的K-means方法和基于近红外图像的OTSU（由Nobuyuki Otsu提出并以他的名字命名）方法相比，工作中算法得到的水果区域是完整的. 在此基础上，绿葡萄的平均识别率达到92.1%。