Detection of Potassium Deficiency and Momentary Transpiration Rate Estimation at Early Growth Stages Using Proximal Hyperspectral Imaging and Extreme Gradient Boosting

Proximal hyperspectral sensing of abiotic stresses in plants

Recent attempts, advances and challenges, as well as future perspectives regarding the application of proximal hyperspectral sensing (where sensors are placed within 10 m above plants, either on land-based platforms or in controlled environments) to assess plant abiotic stresses have been critically reviewed. Abiotic stresses, caused by either physical or chemical reasons such as nutrient deficiency, drought, salinity, heavy metals, herbicides, extreme temperatures, and so on, may be more damaging than biotic stresses (affected by infectious agents such as bacteria, fungi, insects, etc.) on crop yields. The proximal hyperspectral sensing provides images at a sub-millimeter spatial resolution for doing an in-depth study of plant physiology and thus offers a global view of the plant's status and allows for monitoring spatio-temporal variations from large geographical areas reliably and economically. The literature update has been based on 362 research papers in this field, published from 2010, most of which are from four years ago and, in our knowledge, it is the first paper that provides a comprehensive review of the applications of the technique for the detection of various types of abiotic stresses in plants.

Irradiance Independent Spectrum Reconstruction from Camera Signals Using the Interpolation Method

The spectrum of light captured by a camera can be reconstructed using the interpolation method. The reconstructed spectrum is a linear combination of the reference spectra, where the weighting coefficients are calculated from the signals of the pixel and the reference samples by interpolation. This method is known as the look-up table (LUT) method. It is irradiance-dependent due to the dependence of the reconstructed spectrum shape on the sample irradiance. Since the irradiance can vary in field applications, an irradiance-independent LUT (II-LUT) method is required to recover spectral reflectance. This paper proposes an II-LUT method to interpolate the spectrum in the normalized signal space. Munsell color chips irradiated with D65 were used as samples. Example cameras are a tricolor camera and a quadcolor camera. Results show that the proposed method can achieve the irradiance independent spectrum reconstruction and computation time saving at the expense of the recovered spectral reflectance error. Considering that the irradiance variation will introduce additional errors, the actual mean error using the II-LUT method might be smaller than that of the ID-LUT method. It is also shown that the proposed method outperformed the weighted principal component analysis method in both accuracy and computation speed.

Continuous seasonal monitoring of nitrogen and water content in lettuce using a dual phenomics system

The collection and analysis of large amounts of information on a plant-by-plant basis contributes to the development of precision fertigation and may be achieved by combining remote-sensing technology with high-throughput phenotyping methods. Here, lettuce plants (Lactuca sativa) were grown under optimal and suboptimal nitrogen and irrigation treatments from seedlings to harvest. A Plantarray system was used to calculate and log weights, daily transpiration, and momentary transpiration rates throughout the experiment. From 15 d after planting until experiment termination, the entire array of plants was imaged hourly (from 09.00 h to 14.00 h) using a hyperspectral moving camera. Three vegetation indices were calculated from the plants' reflectance signal: red-edge chlorophyll index (RECI), photochemical reflectance index (PRI), and water index (WI), and combined treatments, physiological measurements, and vegetation indices were compared. RECI values differed significantly between nitrogen treatments from the first day of imaging, and WI values distinguished well-irrigated from drought-treated groups before detecting significant differences in daily transpiration rate. The PRI, calculated hourly during the drought-treatment phase, changed with the momentary transpiration rate. Thus, hyperspectral imaging might be used in growing facilities to detect nitrogen or water shortages in plants before their physiological response affects yields.

Spectral Reflectance Recovery from the Quadcolor Camera Signals Using the Interpolation and Weighted Principal Component Analysis Methods

The recovery of surface spectral reflectance using the quadcolor camera was numerically studied. Assume that the RGB channels of the quadcolor camera are the same as the Nikon D5100 tricolor camera. The spectral sensitivity of the fourth signal channel was tailored using a color filter. Munsell color chips were used as reflective surfaces. When the interpolation method or the weighted principal component analysis (wPCA) method is used to reconstruct spectra, using the quadcolor camera can effectively reduce the mean spectral error of the test samples compared to using the tricolor camera. Except for computation time, the interpolation method outperforms the wPCA method in spectrum reconstruction. A long-pass optical filter can be applied to the fourth channel for reducing the mean spectral error. A short-pass optical filter can be applied to the fourth channel for reducing the mean color difference, but the mean spectral error will be larger. Due to the small color difference, the quadcolor camera using an optimized short-pass filter may be suitable as an imaging colorimeter. It was found that an empirical design rule to keep the color difference small is to reduce the error in fitting the color-matching functions using the camera spectral sensitivity functions.

Prediction of Potassium in Peach Leaves Using Hyperspectral Imaging and Multivariate Analysis

Hyperspectral imaging (HSI) is an emerging technology being utilized in agriculture. This system could be used to monitor the overall health of plants or in pest/disease detection. As sensing technology advancement expands, measuring nutrient levels and disease detection also progresses. This study aimed to predict three different levels of potassium (K) concentration in peach leaves using principal component analysis (PCA) and develop models for predicting the K concentration of a peach leaf using a hyperspectral imaging technique. Hyperspectral images were acquired from a randomly selected fresh peach leaf from multiple trees over the spectral region between 500 and 900 nm. Leaves were collected from trees with varying potassium levels of high (2.7~3.2%), medium (2.0~2.6%), and low (1.3~1.9%). Four pretreatment methods (multiplicative scatter effect (MSC), Savitzky–Golay first derivative, Savitzky–Golay second derivative, and standard normal variate (SNV)) were applied to the raw data and partial least square (PLS) was used to develop a model for each of the pretreatments. The R2 values for each pretreatment method were 0.8099, 0.6723, 0.5586, and 0.8446, respectively. The SNV prediction model has the highest accuracy and was used to predict the K nutrient using the validation data. The result showed a slightly lower R2 = 0.8101 compared with the training. This study showed that HSI could measure K concentration in peach tree cultivars.

Proximal Remote Sensing-Based Vegetation Indices for Monitoring Mango Tree Stem Sap Flux Density

Plant water use is an important function reflecting vegetation physiological status and affects plant growth, productivity, and crop/fruit quality. Although hyperspectral vegetation indices have recently been proposed to assess plant water use, limited sample sizes for established models greatly astricts their wide applications. In this study, we have managed to gather a large volume of continuous measurements of canopy spectra through proximally set spectroradiometers over the canopy, enabling us to investigate the feasibility of using continuous narrow-band indices to trace canopy-scale water use indicated by the stem sap flux density measured with sap flow sensors. The results proved that the newly developed D (520, 560) index was optimal to capture the variation of sap flux density under clear sky conditions (R2 = 0.53), while the best index identified for non-clear sky conditions was the D (530, 575) (R2 = 0.32). Furthermore, the bands used in these indices agreed with the reported sensitive bands for estimating leaf stomatal conductance which has a critical role in transpiration rate regulation over a short time period. Our results should point a way towards using proximal hyperspectral indices to trace tree water use directly.

Recent Advances in Multi- and Hyperspectral Image Analysis

Current advancements in sensor technology bring new possibilities in multi- and hyperspectral imaging. Real-life use cases which can benefit from such imagery span across various domains, including precision agriculture, chemistry, biology, medicine, land cover applications, management of natural resources, detecting natural disasters, and more. To extract value from such highly dimensional data capturing up to hundreds of spectral bands in the electromagnetic spectrum, researchers have been developing a range of image processing and machine learning analysis pipelines to process these kind of data as efficiently as possible. To this end, multi- or hyperspectral analysis has bloomed and has become an exciting research area which can enable the faster adoption of this technology in practice, also when such algorithms are deployed in hardware-constrained and extreme execution environments; e.g., on-board imaging satellites.

New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection

In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications.

On the Optimization of Regression-Based Spectral Reconstruction

Spectral reconstruction (SR) algorithms attempt to recover hyperspectral information from RGB camera responses. Recently, the most common metric for evaluating the performance of SR algorithms is the Mean Relative Absolute Error (MRAE)-an ℓ1 relative error (also known as percentage error). Unsurprisingly, the leading algorithms based on Deep Neural Networks (DNN) are trained and tested using the MRAE metric. In contrast, the much simpler regression-based methods (which actually can work tolerably well) are trained to optimize a generic Root Mean Square Error (RMSE) and then tested in MRAE. Another issue with the regression methods is-because in SR the linear systems are large and ill-posed-that they are necessarily solved using regularization. However, hitherto the regularization has been applied at a spectrum level, whereas in MRAE the errors are measured per wavelength (i.e., per spectral channel) and then averaged. The two aims of this paper are, first, to reformulate the simple regressions so that they minimize a relative error metric in training-we formulate both ℓ2 and ℓ1 relative error variants where the latter is MRAE-and, second, we adopt a per-channel regularization strategy. Together, our modifications to how the regressions are formulated and solved leads to up to a 14% increment in mean performance and up to 17% in worst-case performance (measured with MRAE). Importantly, our best result narrows the gap between the regression approaches and the leading DNN model to around 8% in mean accuracy.