To meet demand for agriculture products, researchers have recently focused on precision agriculture to increase crop production with less input. Crop detection based on computer vision with unmanned aerial vehicle (UAV)-acquired images plays a vital role in precision agriculture. In recent years, machine learning has been successfully applied in image processing for classification, detection and segmentation. Accordingly, the aim of this study is to detect rice seedlings in paddy fields using transfer learning from two machine learning models, EfficientDet-D0 and Faster R-CNN, and to compare the results to the legacy approach—histograms of oriented gradients (HOG)-based support vector machine (SVM) classification. This study relies on a significant UAV image dataset to build a model to detect tiny rice seedlings. The HOG-SVM classifier was trained and achieved an F1-score of 99% in both training and testing. The performance of HOG-SVM, EfficientDet and Faster R-CNN models, respectively, were measured in mean average precision (mAP), with 70.0%, 95.5% and almost 100% in training and 70.2%, 83.2% and 88.8% in testing, and mean Intersection-over-Union (mIoU), with 46.5%, 67.6% and 99.6% in training and 46.6%, 57.5% and 63.7% in testing. The three models were also measured with three additional datasets acquired on different dates to evaluate model applicability with various imaging conditions. The results demonstrate that both CNN-based models outperform HOG-SVM, with a 10% higher mAP and mIoU. Further, computation speed is at least 1000 times faster than that of HOG-SVM with sliding window. Overall, the adoption of transfer learning allows for rapid establishment of object detection applications with promising performance.

Recently, unmanned aerial vehicles (UAVs) have been broadly applied to the remote sensing field. For a great number of UAV images, deep learning has been reinvigorated and performed many results in agricultural applications. The popular image datasets for deep learning model training are generated for general purpose use, in which the objects, views, and applications are for ordinary scenarios. However, UAV images possess different patterns of images mostly from a look-down perspective. This paper provides a verified annotated dataset of UAV images that are described in data acquisition, data preprocessing, and a showcase of a CNN classification. The dataset collection consists of one multi-rotor UAV platform by flying a planned scouting routine over rice paddies. This paper introduces a semi-auto annotation method with an ExGR index to generate the training data of rice seedlings. For demonstration, this study modified a classical CNN architecture, VGG-16, to run a patch-based rice seedling detection. The k-fold cross-validation was employed to obtain an 80/20 dividing ratio of training/test data. The accuracy of the network increases with the increase of epoch, and all the divisions of the cross-validation dataset achieve a 0.99 accuracy. The rice seedling dataset provides the training-validation dataset, patch-based detection samples, and the ortho-mosaic image of the field.

Background: Rice is a key global food crop. Rice lodging causes a reduction in plant height and crop yield, and rice is prone to lodging in the late growth stage because of panicle initiation. We used two water irrigation modes and four fertilizer application intervals to investigate the relationship between lodging and various cultivation conditions over 2 years. Results: Plant height data were collected and combined with aerial images, revealing that rice lodging was closely related to the nitrogen fertilizer content. The aerial images demonstrated that lodging mainly occurred in the fields treated with a high-nitrogen fertilizer, and analysis of variance revealed that plant height was signifi-cantly affected by nitrogen fertilizer. These results demonstrated that rice plant height in the booting stage was significantly positively correlated with the lodging results (r = 0.67) and nega-tively correlated with yield (r = − 0.46). If the rice plant height in the booting stage exceeded 70.7 cm and nitrogen fertilizer was continuously applied, according to the predicted growing curve of plant height, the plant would be at risk of lodging. Results showed more rainfall accumulated in the later stage of rice growth accompanied by strong instantaneous gusts, the risk of lodging in-creased. Conclusion: The results provide predictions that can be applied in intelligent production and lodging risk management, and they form the basis of cultivation management and response policies for each growth period.

Rice is one of the three major crops in the world and is the major crop in Asia. Climate change and water resource shortages may result in decreases in rice yields and possible food shortage crises. In this study, water-saving farming management was tested, and IOT field water level monitoring was used to regulate water inflow automatically. Plant height (PH) is an important phenotype to be used to determine difference in rice growth periods and yields using water-saving irrigation. An unmanned aerial vehicle (UAV) with an RGB camera captured sequential images of rice fields to estimate rice PH compared with PH measured on site for estimating rice growth stages. The test results, with two crop harvests in 2019, revealed that with adequate image calibration, the correlation coefficient between UAV-PH and field-PH was higher than 0.98, indicating that UAV images can accurately determine rice PH in the field and rice growth phase. The study demonstrated that water-saving farming is effective, decreasing water usage for the first and second crops of 2019 by 53.5% and 21.7%, respectively, without influencing the growth period and final yield. Coupled with an automated irrigation system, rice farming can be adaptive to water shortage situations.

Fruit characters affect consumer preferences and the market value of melons is determined by fruit quality. Most fruit quality-related traits are controlled by multiple genes, and are influenced by environmental factors. Furthermore, powdery mildew is another limiting factor in melon production. To develop new melon cultivars with disease resistance and high quality fruits using the molecular marker-assisted breeding strategy, identification of quantitative trait loci for fruit quality and disease resistance is required. The F2 populations from the cross of TARI-08874 (Cucumis melo ssp. melo) and ‘Bai-li-gua’ (C. melo ssp. agrestis) were used to map the quantitative trait loci (QTLs) for fruit-related traits and powdery mildew resistance in two trials. All traits were significantly different (P < 0.05) between parents. The generated linkage map consisted of twelve major linkage groups (LGs), spanning 626.1 cM in total, with an average distance of 8.3 cM between flanking markers. Nineteen QTLs were detected for seven melon traits, among which ten QTLs were localized to the same positions as the corresponding QTLs described in other studies. Four of these QTLs were detected in both trials. The results of identified QTLs in this study suggested that fruit size in the tested populations were mainly determined by fruit diameter and flesh thickness. All of the major QTLs for fruit diameter and flesh thickness were identified on LG5 and LG11. Four QTLs identified responsible for netting width of fruit rind were co-localized with the QTLs for netting density, suggesting similar genetic mechanisms affecting these two traits. Additionally, only one major QTL for powdery mildew resistance was detected on LG2, and it was closely linked to a simple sequence repeat (SSR) marker CMBR120 which was identified in a previous study. Because the netting feature is a crucial factor for external appearance of fruits in Asia market, we focus on mining the genetic information of fruit netting. This is the first report of QTL mapping to netting width. Furthermore, new QTLs were identified for netting density (qND4, qND6, and qND7) and netting width (qNW2, qNW4, qNW6, and qNW7) successfully. In addition, novel QTLs for fruit diameter (qFD5), flesh thickness (qFT11) were also detected.