The object detection method based on deep learning convolutional neural network (CNN) significantly improves the detection performance of wheat head on wheat images obtained from the near ground. Nevertheless, for wheat head images of different stages, high density, and overlaps captured by the aerial-scale unmanned aerial vehicle (UAV), the existing deep learning-based object detection methods often have poor detection effects. Since the receptive field of CNN is usually small, it is not conducive to capture global features. The visual Transformer can capture the global information of an image; hence we introduce Transformer to improve the detection effect and reduce the computation of the network. Three object detection networks based on Transformer are designed and developed, including the two-stage method FR-Transformer and the one-stage methods R-Transformer and Y-Transformer. Compared with various other prevalent object detection CNN methods, our FR-Transformer method outperforms them by 88.3% for AP₅₀ and 38.5% for AP₇₅. The experiments represent that the FR-Transformer method can gratify requirements of rapid and precise detection of wheat heads by the UAV in the field to a certain extent. These more relevant and direct information provide a reliable reference for further estimation of wheat yield.

Near-infrared (874–1734 nm) hyperspectral imaging technology combined with chemometrics was used to identify parental and hybrid okra seeds. A total of 1740 okra seeds of three different varieties, which contained the male parent xiaolusi, the female parent xianzhi, and the hybrid seed penzai, were collected, and all of the samples were randomly divided into the calibration set and the prediction set in a ratio of 2:1. Principal component analysis (PCA) was applied to explore the separability of different seeds based on the spectral characteristics of okra seeds. Fourteen and 86 characteristic wavelengths were extracted by using the successive projection algorithm (SPA) and competitive adaptive reweighted sampling (CARS), respectively. Another 14 characteristic wavelengths were extracted by using CARS combined with SPA. Partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were developed based on the characteristic wavelength and full-band spectroscopy. The experimental results showed that the SVM discriminant model worked well and that the correct recognition rate was over 93.62% based on full-band spectroscopy. As for the discriminative model that was based on characteristic wavelength, the SVM model based on the CARS algorithm was better than the other two models. Combining the CARS+SVM calibration model and image processing technology, a pseudo-color map of sample prediction was generated, which could intuitively identify the species of okra seeds. The whole process provided a new idea for agricultural breeding in the rapid screening and identification of hybrid okra seeds.

Rice seed vigor plays a significant role in determining the quality and quantity of rice production.

The feasibility of using the fourier transform infrared (FTIR) spectroscopic technique with a stacked sparse auto-encoder (SSAE) to identify orchid varieties was studied. Spectral data of 13 orchids varieties covering the spectral range of 4000–550 cm⁻¹ were acquired to establish discriminant models and to select optimal spectral variables. K nearest neighbors (KNN), support vector machine (SVM), and SSAE models were built using full spectra. The SSAE model performed better than the KNN and SVM models and obtained a classification accuracy 99.4% in the calibration set and 97.9% in the prediction set. Then, three algorithms, principal component analysis loading (PCA-loading), competitive adaptive reweighted sampling (CARS), and stacked sparse auto-encoder guided backward (SSAE-GB), were used to select 39, 300, and 38 optimal wavenumbers, respectively. The KNN and SVM models were built based on optimal wavenumbers. Most of the optimal wavenumbers-based models performed slightly better than the all wavenumbers-based models. The performance of the SSAE-GB was better than the other two from the perspective of the accuracy of the discriminant models and the number of optimal wavenumbers. The results of this study showed that the FTIR spectroscopic technique combined with the SSAE algorithm could be adopted in the identification of the orchid varieties.

Glyphosate is a widely used nonselective herbicide. Probing the glyphosate tolerance mechanism is necessary for the screening and development of resistant cultivars. In this study, a hyperspectral image was used to develop a more robust leaf chlorophyll content (LCC) prediction model based on different datasets to finally analyze the response of LCC to glyphosate-stress. Chlorophyll a fluorescence (ChlF) was used to dynamically monitor the photosynthetic physiological response of transgenic glyphosate-resistant and wild glyphosate-sensitive maize seedlings and applying chemometrics methods to extract time-series features to screen resistant cultivars. Six days after glyphosate treatment, glyphosate-sensitive seedlings exhibited significant changes in leaf reflection and photosynthetic activity. By updating source domain and transfer component analysis, LCC prediction model performance was improved effectively (the coefficient of determination value increased from 0.65 to 0.84). Based on the predicted LCC and ChlF data, glyphosate-sensitive plants are too fragile to protect themselves from glyphosate stress, while glyphosate-resistant plants were able to maintain normal photosynthetic physiological activity. JIP-test parameters, φ_E0, V_J, ψ_E0, and M₀, were used to indicate the degree of plant damage caused by glyphosate. This study constructed a transferable model for LCC monitoring to finally evaluate glyphosate tolerance in a time-series manner and verified the feasibility of ChlF in screening glyphosate-resistant cultivars.

Remote sensing coupled with hyperspectral technology has become increasingly popular to investigate plant traits, showcasing its advantages in studying plant growth, health, and productivity. The quality of the collected hyperspectral images is crucial for subsequent data analysis and plant phenotyping studies. However, diurnal variations in spectral characteristics introduce more data variance in canopy reflectance spectra, raising the cost of subsequent analyses and compromising the performance of trait estimation models. In this study, a fixed gantry platform in a cornfield was used to capture visible and near-infrared (VNIR) hyperspectral images of corn canopies at consecutive time intervals. By applying reference board calibration and locally weighted scatterplot smoothing to minimize the effects of ambient light and daily growth, diurnal spectral changes across all involved VNIR wavelengths were investigated. Several distinct diurnal patterns were observed to have close connections with the plants’ physiological effects. Diurnal calibration models were established at every wavelength by employing the least squares polynomial algorithm, with the highest coefficient of determination reaching 0.84. Moreover, by employing diurnal calibration in canopy spectra processing, the reduction in spectral variance brought about by varying imaging time was evidently exhibited. This study not only reveals the diurnal spectral variation pattern at VNIR bands but also offers a reliable, straightforward, and low-cost approach to improve the quality of remote sensing data and reduce the inherent variance brought about via the different imaging times ensuring that comparable spectral analysis can be performed under relatively fair conditions.