School of Computer and Information, Anqing Normal University, Anqing, 246133, Anhui, China.
The Key Lab of Intelligent Perception and Computing of Anhui Province, Anqing, 246133, Anhui, China.
Sci Rep. 2020 Oct 29;10(1):18697. doi: 10.1038/s41598-020-75721-2.
Methods to detect directly aphids based on convolutional neural networks (CNNs) are unsatisfactory because aphids are small and usually are specially distributed. To enhance aphid detection efficiency, a framework based on oriented FAST and rotated BRIEF (ORB) and CNNs (EADF) is proposed by us to detect aphids in images. Firstly, the key point is to find regions of aphids. Points generated by the ORB algorithm are processed by us to generate suspected aphid areas. Regions are fed into convolutional networks to train the model. Finally, images are detected in blocks with the trained model. In addition, in order to solve the situation that the coordinates are not uniform after the image is segmented, we use a coordinate mapping method to unify the coordinates. We compare current mainstream target detection methods. Experiments indicate that our method has higher accuracy than state-of-the-art two-stage methods that the AP value of RetinaNet with EADF is 0.385 higher than RetinaNet without it and the Cascade-RCNN with EADF is more than without it by 43.3% on value of AP, which demonstrates its competency.
基于卷积神经网络（CNNs）直接检测蚜虫的方法并不令人满意，因为蚜虫很小，通常分布得很特别。为了提高蚜虫检测效率，我们提出了一种基于定向 FAST 和旋转 BRIEF（ORB）和 CNNs（EADF）的框架，用于在图像中检测蚜虫。首先，关键是要找到蚜虫的区域。通过 ORB 算法生成的点经过我们的处理，生成可疑的蚜虫区域。区域被馈送到卷积网络中进行模型训练。最后，使用训练好的模型以块的形式检测图像。此外，为了解决图像分割后坐标不均匀的情况，我们使用坐标映射方法来统一坐标。我们比较了当前主流的目标检测方法。实验表明，与先进的两阶段方法相比，我们的方法具有更高的精度，使用 EADF 的 RetinaNet 的 AP 值比不使用 EADF 的 RetinaNet 高 0.385，而使用 EADF 的 Cascade-RCNN 比不使用 EADF 的高 43.3%，这证明了它的能力。
