Abstract
Counting the number of wheat ears in images under natural light is an important way to evaluate the crop yield, thus, it is of great significance to modern intelligent agriculture. However, the distribution of wheat ears is dense, so the occlusion and overlap problem appears in almost every wheat image. It is difficult for traditional image processing methods to solve occlusion problem due to the deficiency of high-level semantic features, while existing deep learning based counting methods did not solve the occlusion efficiently. This article proposes an improved EfficientDet-D0 object detection model for wheat ear counting, and focuses on solving occlusion. First, the transfer learning method is employed in the pre-training of the model backbone network to extract the high-level semantic features of wheat ears. Secondly, an image augmentation method Random-Cutout is proposed, in which some rectangles are selected and erased according to the number and size of the wheat ears in the images to simulate occlusion in real wheat images. Finally, convolutional block attention module (CBAM) is adopted into the EfficientDet-D0 model after the backbone, which makes the model refine the features, pay more attention to the wheat ears and suppress other useless background information. Extensive experiments are done by feeding the features to detection layer, showing that the counting accuracy of the improved EfficientDet-D0 model reaches 94%, which is about 2% higher than the original model, and false detection rate is 5.8%, which is the lowest among comparative methods.
Highlights
The number of wheat ears is used as the essential information to study wheat yield (Prystupa et al, 2004; Peltonen-Sainio et al, 2007; Ferrante et al, 2017)
In the actual wheat ear counting task, the varieties and maturity of wheat will be different (Figure 1), which lies in the fact that the preset positive sample color cannot represent wheat ears under all conditions
Comparative experiments are first done to show that the modifications, such as transfer learning, image augmentation and convolutional block attention module (CBAM), works in performance promotion
Summary
The number of wheat ears is used as the essential information to study wheat yield (Prystupa et al, 2004; Peltonen-Sainio et al, 2007; Ferrante et al, 2017). Automatic counting methods based on image processing have been successfully used in practical applications, such as plant leaf counting and fruit counting (Giuffrida et al, 2015; Mussadiq et al, 2015; Maldonado and Barbosa, 2016; Stein et al, 2016; Aich and Stavness, 2017; Barré et al, 2017; Dobrescu et al, 2017). This type of method reduces the dependence on color information, the segmentation threshold is determined by experience, which makes the algorithm have no generalization ability and low robustness
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
