MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard
MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard
复制标题
DOI：
10.1016/j.engappai.2018.09.011
复制
发表时间：
2019-01-01
影响因子：
8
通讯作者：
Narasipura, Omkar
中科院分区：
文献类型：
--
作者：
Kestur, Ramesh;Meduri, Avadesh;Narasipura, Omkar
这项工作提出了一种在RGB图像中检测和计数芒果的方法，以进一步估计产量。RGB图像是在收获前阶段的一个芒果果园的开阔田野条件下获得的。该方法采用基于深度卷积神经网络的芒果语义分割检测体系结构。此外，使用基于轮廓的连接对象检测在语义分割输出中检测芒果对象。MangoNet使用从40张图像中获得的大小为200 x 200的11096个图像块进行训练。对4张测试图像生成的1500个图像块进行测试。对结果进行了分析，对芒果进行了分割和检测。利用由权变矩阵导出的精密度、召回率和漏检率参数对结果进行了分析。结果表明，该方法对尺度、遮挡、距离和光照条件等多种因素的检测具有鲁棒性。将MangoNet的性能与在相同数据上训练的FCN变体体系结构进行了比较。MangoNet优于其变体架构。
This work presents a method for detection and counting of mangoes in RGB images for further yield estimation. The RGB images are acquired in open field conditions from a mango orchard in the pre-harvest stage. The proposed method uses MangoNet, a deep convolutional neural network based architecture for mango detection using semantic segmentation. Further, mango objects are detected in the semantic segmented output using contour based connected object detection. The MangoNet is trained using 11,096 image patches of size 200 x 200 obtained from 40 images. Testing was carried out on 1500 image patches generated from 4 test images. The results are analyzed for performance of segmentation and detection of mangoes. Results are analyzed using the precision, recall, Fl parameters derived from contingency matrix. Results demonstrate the robustness of detection for a multitude of factors such as scale, occlusion, distance and illumination conditions, characteristic to open field conditions. The performance of the MangoNet is compared with FCN variant architectures trained on the same data. MangoNet outperforms its variant architectures.