Automatic image-based detection technology for two critical growth stages of maize: Emergence and three-leaf stage

Growth stage information of field crops is not only an important basic data for analyzing the relationship between the crop growth process and the agrometeorological conditions, but it is also useful for various aspects of precision agriculture. Up to now, it is primarily obtained manually, which is time-consuming, labor-intensive, subjective and discontinuous. Therefore, a noninvasive method to note observations that also proves to be more efficient, continuous, and automatic is needed. At present, an alternative method based on computer vision has been widely used for monitoring crop growth status due to advantages linked to its low-cost, its intuitiveness and non-contact manner of data gathering it provides. However, little research has been done to improve close observation of different growth stages of field crops using digital cameras. To overcome the drawbacks caused by the current manual observation, a study was conducted to explore the application of computer vision technology for the automatic detection technology of two critical growth stages of maize (emergence and three-leaf stage). In order to identify the growth stages, the first task is to extract the plants from images properly. According to complex factors on farm fields, we proposed a novel crops segmentation method (AP-HI) which is robust and not sensitive to the challenging variation of outdoor luminosity and complex environmental elements. It has laid the foundation for subsequent studies. By virtue of the AP-HI, two automatic detection methods based on imaging were investigated for the two critical growth stages of maize. The former method uses the spatial distribution feature to judge accurately whether the field crop has reached the emergence stage or not. The latter uses the skeleton endpoint to characterize the leaf of seedling and transforms a matter of judgment into that of probability estimation, which leads to the final conclusion. In order to verify the feasibility and validity of our proposed methods, the comparing experiments have been carried out. Five well-established algorithms were utilized to make comparison with AP-HI and its results showed that our method outperformed the other algorithms in yielding the highest performance of 96.68% with the lowest standard deviation of 2.37%. As for the two automatic detection methods, the crops of two experimental fields located in Zhengzhou, Henan and Taian, Shandong provinces in China were observed both with a human observer and by using automated routines to process images obtained from a camera. In determining the time at which a growth stage occurred, the proposed methods produced the similar results to the manual observation method. Overall, the automated methods can meet the demand for practical observation needed for agronomic modeling and in triggering action alerts to farmers.