Broad Dataset and Methods for Counting and Localization of On-Ear Corn Kernels

Abstract

Crop monitoring and yield prediction are central to management decisions for farmers. One key task is counting the number of kernels on an ear of corn to estimate yield in a field. As ears of corn can easily have 400–900 kernels, manual counting is unrealistic; traditionally, growers have approximated the number of kernels on an ear of corn through a mixture of counting and estimation. With the success of deep learning, these human estimates can now be replaced with more accurate machine learning models, many of which are efficient enough to run on a mobile device. Although a conceptually simple task, the counting and localization of hundreds of instances in an image is challenging for many image detection algorithms which struggle when objects are small in size and large in number. We compare different detection-based frameworks, Faster R-CNN, YOLO, and density-estimation approaches for on-ear corn kernel counting and localization. In addition to the YOLOv5 model which is accurate and edge-deployable, our density-estimation approach produces high-quality results, is lightweight enough for edge deployment, and maintains its computational efficiency independent of the number of kernels in the image. Additionally, we seek to standardize and broaden this line of work through the release of a challenging dataset with high-quality, multi-class segmentation masks. This dataset firstly enables quantitative comparison of approaches within the kernel counting application space and secondly promotes further research in transfer learning and domain adaptation, large count segmentation methods, and edge deployment methods.

Earbox, an open tool for high-throughput measurement of the spatial organization of maize ears and inference of novel traits

“…For example, cameras can be replaced for higher resolutions or multispectral acquisition for characterization of grain physiology [ 31 , 32 , 55 – 59 ]. Additional steps of deep learning would probably be sufficient to develop a method for the recognizing and classifying of maize diseases [ 60 , 31 , 32 ], or for characterising early grain development, by processing immature ears and grains a few days after flowering. Finally, the results of this work pave the way for future development of tools for inflorescence phenotyping of other crops, such as wheat and sunflower, for which the present system will be adapted.…”

Earbox, an open tool for high-throughput measurement of the spatial organization of maize ears and inference of novel traits

“…Zhang et al, 2020;Zhou et al, s. d.). Additional steps of deep learning would probably be sufficient to develop a method for the recognizing and classifying of maize diseases (Hobbs et al, 2021;J. Zhang et al, 2020), or for characterising early grain development, by processing immature ears and grains a few days after flowering.…”

Application and Evaluation of a Cross-Fertilization Methodology in the AEC Industry: New Technologies, Digitalization and Robotization

“…In the Agribusiness Sector the introduction of AI and robots that facilitate harvesting process face some challenges attributable to SoW tracking and processing verification. Computer vision technologies are being investigated to identify fruits and vegetables in plantations and locate their position through image retrieval for algorithm operation [63,64]; another issue concerns the study of manipulators, which must be robust enough to be able to rip the fruit from its seat, but sensitive enough to avoid compromising its integrity [64,65].…”