Search

LiDAR placement and field of view selection play a role in detecting the relative position and pose of vehicles in relocation maps based on high-precision map automatic navigation. When the LiDAR field of view is obscured or the LiDAR position is misplaced, this can easily lead to loss of repositioning or low repositioning accuracy. In this paper, a method of LiDAR layout and field of view selection based on high-precision map normal distribution transformation (NDT) relocation is proposed to solve the problem of large NDT relocation error and position loss when the occlusion field of view is too large. To simulate the real placement environment and the LiDAR obstructed by obstacles, the ROI algorithm is used to cut LiDAR point clouds and to obtain LiDAR point cloud data of different sizes. The cut point cloud data is first downsampled and then relocated. The downsampling points for NDT relocation are recorded as valid matching points. The direction and angle settings of the LiDAR point cloud data are optimized using RMSE values and valid matching points. The results show that in the urban scene with complex road conditions, there are more front and rear matching points than left and right matching points within the unit angle. The more matching points of the NDT relocation algorithm there are, the higher the relocation accuracy. Increasing the front and rear LiDAR field of view prevents the loss of repositioning. The relocation accuracy can be improved by increasing the left and right LiDAR field of view.

The use of plant-based indicators and other conventional means to detect the level of water stress in crops may be challenging, due to their difficulties in automation, their arduousness, and their time-consuming nature. Non-contact and non-destructive sensing methods can be used to detect the level of water stress in plants continuously and to provide automatic sensing and controls. This research aimed at determining the viability, efficiency, and swiftness in employing the commercial Workswell WIRIS Agro R infrared camera (WWARIC) in monitoring water stress and scheduling appropriate irrigation regimes in mandarin plants. The experiment used a four-by-three randomized complete block design with 80–100% FC water treatment as full field capacity and three deficit irrigation treatments at 70–75% FC, 60–65% FC, and 50–55% FC. Air temperature, canopy temperature, and vapor pressure deficits were measured and employed to deduce the empirical crop water stress index, using the Idso approach (CWSI(Idso)) as well as baseline equations to calculate non-water stress and water stressed conditions. The relative leaf water content (RLWC) of mandarin plants was also determined for the growing season. From the experiment, CWSI(Idso) and CWSI were estimated using the Workswell Wiris Agro R infrared camera (CWSIW) and showed a high correlation (R2 = 0.75 at p < 0.05) in assessing the extent of water stress in mandarin plants. The results also showed that at an altitude of 12 m above the mandarin canopy, the WWARIC was able to identify water stress using three modes (empirical, differential, and theoretical). The WWARIC’s color map feature, presented in real time, makes the camera a suitable device, as there is no need for complex computations or expert advice before determining the extent of the stress the crops are subjected to. The results prove that this novel use of the WWARIC demonstrated sufficient precision, swiftness, and intelligibility in the real-time detection of the mandarin water stress index and, accordingly, assisted in scheduling irrigation.

To optimize crop water consumption and adopt water-saving measures such as precision irrigation, early identification of plant water status is critical. This study explores the effectiveness of estimating water stress in choy sum (Brassica chinensis var. parachinensis) grown in pots in greenhouse conditions using Crop Water Stress Index (CWSI) and crop vegetation indicators to improve irrigation water management. Data on CWSI and Spectral reflectance were collected from choy sum plants growing in sandy loam soil with four different soil field capacities (FC): 90–100% FC as no water stress (NWS); 80–90% FC for light water stress (LWS); 70–80% FC for moderate water stress (MWS); and 60–70% FC for severe water stress (SWS). With four treatments and three replications, the experiment was set up as a completely randomized design (CRD). Throughout the growing season, plant water stress tracers such as leaf area index (LAI), canopy temperature (Tc), leaf relative water content (LRWC), leaf chlorophyll content, and yield were measured. Furthermore, CWSI estimated from the Workswell Wiris Agro R Infrared Camera (CWSIW) and spectral data acquisition from the Analytical Spectral Device on choy sum plants were studied at each growth stage. NDVI, Photochemical Reflectance Index positioned at 570 nm (PRI570), normalized PRI (PRInorm), Water Index (WI), and NDWI were the Vegetation indices (VIs) used in this study. At each growth stage, the connections between these CWSIW, VIs, and water stress indicators were statistically analyzed with R2 greater than 0.5. The results revealed that all VIs were valuable guides for diagnosing water stress in choy sum. CWSIW obtained from this study showed that Workswell Wiris Agro R Infrared Camera mounted on proximal remote sensing platform for assessing water stress in choy sum plant was rapid, non-destructive, and user friendly. Therefore, integrating CWSIW and VIs approach gives a more rapid and accurate approach for detecting water stress in choy sum grown under greenhouse conditions to optimize yield by reducing water loss and enhancing food security and sustainability.

At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.

Drought and water scarcity due to global warming, climate change, and social development have been the most death-defying threat to global agriculture production for the optimization of water and food security. Reflectance indices obtained by an Analytical Spectral Device (ASD) Spec 4 hyperspectral spectrometer from tomato growth in two soil texture types exposed to four water stress levels (70–100% FC, 60–70% FC, 50–60% FC, and 40–50% FC) was deployed to schedule irrigation and management of crops’ water stress. The treatments were replicated four times in a randomized complete block design (RCBD) in a 2 × 4 factorial experiment. Water stress treatments were monitored with Time Domain Reflectometer (TDR) every 12 h before and after irrigation to maintain soil water content at the desired (FC%). Soil electrical conductivity (Ec) was measured daily throughout the growth cycle of tomatoes in both soil types. Ec was revealing a strong correlation with water stress at R2 above 0.95 p < 0.001. Yield was measured at the end of the end of the growing season. The results revealed that yield had a high correlation with water stress at R2 = 0.9758 and 0.9816 p < 0.01 for sandy loam and silty loam soils, respectively. Leaf temperature (LT °C), relative leaf water content (RLWC), leaf chlorophyll content (LCC), Leaf area index (LAI), were measured at each growth stage at the same time spectral reflectance data were measured throughout the growth period. Spectral reflectance indices used were grouped into three: (1) greenness vegetative indices; (2) water overtone vegetation indices; (3) Photochemical Reflectance Index centered at 570 nm (PRI570), and normalized PRI (PRInorm). These reflectance indices were strongly correlated with all four water stress indicators and yield. The results revealed that NDVI, RDVI, WI, NDWI, NDWI1640, PRI570, and PRInorm were the most sensitive indices for estimating crop water stress at each growth stage in both sandy loam and silty loam soils at R2 above 0.35. This study recounts the depth of 858 to 1640 nm band absorption to water stress estimation, comparing it to other band depths to give an insight into the usefulness of ground-based hyperspectral reflectance indices for assessing crop water stress at different growth stages in different soil types.

The goal of this research is to use a WORKSWELL WIRIS AGRO R INFRARED CAMERA (WWARIC) to assess the crop water stress index (CWSIW) on tomato growth in two soil types. This normalized index (CWSI) can map water stress to prevent drought, mapping yield, and irrigation scheduling. The canopy temperature, air temperature, and vapor pressure deficit were measured and used to calculate the empirical value of the CWSI based on the Idso approach (CWSIIdso). The vegetation water content (VWC) was also measured at each growth stage of tomato growth. The research was conducted as a 2 × 4 factorial experiment arranged in a Completely Randomized Block Design. The treatments imposed were two soil types: sandy loam and silt loam, with four water stress treatment levels at 70–100% FC, 60–70% FC, 50–60% FC, and 40–50% FC on the growth of tomatoes to assess the water stress. The results revealed that CWSIIdso and CWSIW proved a strong correlation in estimating the crop water status at R2 above 0.60 at each growth stage in both soil types. The fruit expansion stage showed the highest correlation at R2 = 0.8363 in sandy loam and R2 = 0.7611 in silt loam. VWC and CWSIW showed a negative relationship with a strong correlation at all the growth stages with R2 values above 0.8 at p < 0.05 in both soil types. Similarly, the CWSIW and yield also showed a negative relationship and a strong correlation with R2 values above 0.95, which indicated that increasing the CWSIW had a negative effect on the yield. However, the total marketable yield ranged from 2.02 to 6.8 kg plant−1 in sandy loam soil and 1.75 to 5.4 kg plant−1 in silty loam soil from a low to high CWSIW. The highest mean marketable yield was obtained in sandy loam soil at 70–100% FC (0.0 < CWSIW ≤ 0.25), while the least-marketable yield was obtained in silty loam soil 40–50% FC (0.75 < CWSIW ≤ 1.0); hence, it is ideal for maintaining the crop water status between 0.0 < CWSIW ≤ 0.25 for the optimum yield. These experimental results proved that the WWARIC effectively assesses the crop water stress index (CWSIW) in tomatoes for mapping the yield and irrigation scheduling.

Leaf area index (LAI) is used to predict crop yield, and unmanned aerial vehicles (UAVs) provide new ways to monitor LAI. In this study, we used a fixed-wing UAV with multispectral cameras for remote sensing monitoring. We conducted field experiments with two peanut varieties at different planting densities to estimate LAI from multispectral images and establish a high-precision LAI prediction model. We used eight vegetation indices (VIs) and developed simple regression and artificial neural network (BPN) models for LAI and spectral VIs. The empirical model was calibrated to estimate peanut LAI, and the best model was selected from the coefficient of determination and root mean square error. The red (660 nm) and near-infrared (790 nm) bands effectively predicted peanut LAI, and LAI increased with planting density. The predictive accuracy of the multiple regression model was higher than that of the single linear regression models, and the correlations between Modified Red-Edge Simple Ratio Index (MSR), Ratio Vegetation Index (RVI), Normalized Difference Vegetation Index (NDVI), and LAI were higher than the other indices. The combined VI BPN model was more accurate than the single VI BPN model, and the BPN model accuracy was higher. Planting density affects peanut LAI, and reflectance-based vegetation indices can help predict LAI.

Unmanned Aerial Vehicles (UAVs) have been widely applied for pesticide spraying as they have high efficiency and operational flexibility. However, the pesticide droplet drift caused by wind may decrease the pesticide spraying efficiency and pollute the environment. A precision spraying system based on an airborne meteorological monitoring platform on manned agricultural aircrafts is not adaptable for. So far, there is no better solution for controlling droplet drift outside the target area caused by wind, especially by wind gusts. In this regard, a UAV trajectory adjustment system based on Wireless Sensor Network (WSN) for pesticide drift control was proposed in this research. By collecting data from ground WSN, the UAV utilizes the wind speed and wind direction as inputs to autonomously adjust its trajectory for keeping droplet deposition in the target spraying area. Two optimized algorithms, namely deep reinforcement learning and particle swarm optimization, were applied to generate the newly modified flight route. At the same time, a simplified pesticide droplet drift model that includes wind speed and wind direction as parameters was developed and adopted to simulate and compute the drift distance of pesticide droplets. Moreover, an LSTM-based wind speed prediction model and a RNN-based wind direction prediction model were established, so as to address the problem of missing the latest wind data caused by communication latency or a lack of connection with the ground nodes. Finally, experiments were carried out to test the communication latency between UAV and ground WSN, and to evaluate the proposed scheme with embedded Raspberry Pi boards in UAV for feasibility verification. Results show that the WSN-assisted UAV trajectory adjustment system is capable of providing a better performance of on-target droplet deposition for real time pesticide spraying with UAV.

The brown rice plant hopper (BRPH), Nilaparvata lugens (Stal), is one of the most important insect pests affecting rice and causes serious damage to the yield and quality of rice plants in Asia. This study used bionic electronic nose technology to sample BRPH volatiles, which vary in age and amount. Principal component analysis (PCA), linear discrimination analysis (LDA), probabilistic neural network (PNN), BP neural network (BPNN) and loading analysis (Loadings) techniques were used to analyze the sampling data. The results indicate that the PCA and LDA classification ability is poor, but the LDA classification displays superior performance relative to PCA. When a PNN was used to evaluate the BRPH age and amount, the classification rates of the training set were 100% and 96.67%, respectively, and the classification rates of the test set were 90.67% and 64.67%, respectively. When BPNN was used for the evaluation of the BRPH age and amount, the classification accuracies of the training set were 100% and 48.93%, respectively, and the classification accuracies of the test set were 96.67% and 47.33%, respectively. Loadings for BRPH volatiles indicate that the main elements of BRPHs’ volatiles are sulfur-containing organics, aromatics, sulfur-and chlorine-containing organics and nitrogen oxides, which provide a reference for sensors chosen when exploited in specialized BRPH identification devices. This research proves the feasibility and broad application prospects of bionic electronic noses for BRPH recognition.

Principal Component Analysis (PCA) is one of the main methods used for electronic nose pattern recognition. However, poor classification performance is common in classification and recognition when using regular PCA. This paper aims to improve the classification performance of regular PCA based on the existing Wilks ?-statistic (i.e., combined PCA with the Wilks distribution). The improved algorithms, which combine regular PCA with the Wilks ?-statistic, were developed after analysing the functionality and defects of PCA. Verification tests were conducted using a PEN3 electronic nose. The collected samples consisted of the volatiles of six varieties of rough rice (Zhongxiang1, Xiangwan13, Yaopingxiang, WufengyouT025, Pin 36, and Youyou122), grown in same area and season. The first two principal components used as analysis vectors cannot perform the rough rice varieties classification task based on a regular PCA. Using the improved algorithms, which combine the regular PCA with the Wilks ?-statistic, many different principal components were selected as analysis vectors. The set of data points of the Mahalanobis distance between each of the varieties of rough rice was selected to estimate the performance of the classification. The result illustrates that the rough rice varieties classification task is achieved well using the improved algorithm. A Probabilistic Neural Networks (PNN) was also established to test the effectiveness of the improved algorithms. The first two principal components (namely PC1 and PC2) and the first and fifth principal component (namely PC1 and PC5) were selected as the inputs of PNN for the classification of the six rough rice varieties. The results indicate that the classification accuracy based on the improved algorithm was improved by 6.67% compared to the results of the regular method. These results prove the effectiveness of using the Wilks ?-statistic to improve the classification accuracy of the regular PCA approach. The results also indicate that the electronic nose provides a non-destructive and rapid classification method for rough rice.

To overcome the dependence on sunlight of multi-spectral cameras, an active light source multi-spectral imaging system was designed and a preliminary experimental study was conducted at night without solar interference. The system includes an active light source and a multi-spectral camera. The active light source consists of four integrated LED (Light Emitting Diode) arrays and adjustable constant current power supplies. The red LED arrays and the near-infrared LED arrays are each driven by an independently adjustable constant current power supply. The center wavelengths of the light source are 668 nm and 840 nm, which are consistent with that of filter lens of the Rededge-M multi-spectral camera. This paper shows that the radiation intensity measured is proportional to the drive current and is inversely proportional to the radiation distance, which is in accordance with the inverse square law of light. Taking the inverse square law of light into account, a radiation attenuation model was established based on the principle of image system and spatial geometry theory. After a verification test of the radiation attenuation model, it can be concluded that the average error between the radiation intensity obtained using this model and the actual measured value using a spectrometer is less than 0.0003 w/m2. In addition, the fitting curve of the multi-spectral image grayscale digital number (DN) and reflected radiation intensity at the 668 nm (Red light) is y = −3484230x2 + 721083x + 5558, with a determination coefficient of R2 = 0.998. The fitting curve with the 840 nm (near-infrared light) is y = 491469.88x + 3204, with a determination coefficient of R2 = 0.995, so the reflected radiation intensity on the plant canopy can be calculated according to the grayscale DN. Finally, the reflectance of red light and near-infrared light can be calculated, as well as the Normalized Difference Vegetation Index (NDVI) index. Based on the above model, four plants were placed at 2.85 m away from the active light source multi-spectral imaging system for testing. Meanwhile, NDVI index of each plant was measured by a Greenseeker hand-held crop sensor. The results show that the data from the two systems were linearly related and correlated with a coefficient of 0.995, indicating that the system in this article can effectively detect the vegetation NDVI index. If we want to use this technology for remote sensing in UAV, the radiation intensity attenuation and working distance of the light source are issues that need to be considered carefully.

Recently, unmanned aerial vehicles (UAVs) have rapidly emerged as a new technology in the fields of plant protection and pest control in China. Based on existing variable spray research, a plant protection UAV variable spray system integrating neural network based decision making is designed. Using the existing data on plant protection UAV operations, combined with artificial neural network (ANN) technology, an error back propagation (BP) neural network model between the factors affecting droplet deposition is trained. The factors affecting droplet deposition include ambient temperature, ambient humidity, wind speed, flight speed, flight altitude, propeller pitch, nozzles pitch and prescription value. Subsequently, the BP neural network model is combined with variable rate spray control for plant protection UAVs, and real-time information is collected by multi-sensor. The deposition rate is determined by the neural network model, and the flow rate of the spray system is regulated according to the predicted deposition amount. The amount of droplet deposition can meet the prescription requirement. The results show that the training variance of the ANN is 0.003, and thus, the model is stable and reliable. The outdoor tests show that the error between the predicted droplet deposition and actual droplet deposition is less than 20%. The ratio of droplet deposition to prescription value in each unit is approximately equal, and a variable spray operation under different conditions is realized.

With the steady progress of China’s agricultural modernization, the demand for agricultural machinery for production is widely growing. Agricultural unmanned aerial vehicles (UAVs) are becoming a new force in the field of precision agricultural aviation in China. In those agricultural areas where ground-based machinery have difficulties in executing farming operations, agricultural UAVs have shown obvious advantages. With the development of precision agricultural aviation technology, one of the inevitable trends is to realize autonomous identification of obstacles and real-time obstacle avoidance (OA) for agricultural UAVs. However, the complex farmland environment and changing obstacles both increase the complexity of OA research. The objective of this paper is to introduce the development of agricultural UAV OA technology in China. It classifies the farmland obstacles in two ways and puts forward the OA zones and related avoidance tactics, which helps to improve the safety of aviation operations. This paper presents a comparative analysis of domestic applications of agricultural UAV OA technology, features, hotspot and future research directions. The agricultural UAV OA technology of China is still at an early development stage and many barriers still need to be overcome.

Chemical control is necessary in order to control weed infestation and to ensure a rice yield. However, excessive use of herbicides has caused serious agronomic and environmental problems. Site specific weed management (SSWM) recommends an appropriate dose of herbicides according to the weed coverage, which may reduce the use of herbicides while enhancing their chemical effects. In the context of SSWM, the weed cover map and prescription map must be generated in order to carry out the accurate spraying. In this paper, high resolution unmanned aerial vehicle (UAV) imagery were captured over a rice field. Different workflows were evaluated to generate the weed cover map for the whole field. Fully convolutional networks (FCN) was applied for a pixel-level classification. Theoretical analysis and practical evaluation were carried out to seek for an architecture improvement and performance boost. A chessboard segmentation process was used to build the grid framework of the prescription map. The experimental results showed that the overall accuracy and mean intersection over union (mean IU) for weed mapping using FCN-4s were 0.9196 and 0.8473, and the total time (including the data collection and data processing) required to generate the weed cover map for the entire field (50 × 60 m) was less than half an hour. Different weed thresholds (0.00–0.25, with an interval of 0.05) were used for the prescription map generation. High accuracies (above 0.94) were observed for all of the threshold values, and the relevant herbicide saving ranged from 58.3% to 70.8%. All of the experimental results demonstrated that the method used in this work has the potential to produce an accurate weed cover map and prescription map in SSWM applications.

Remote sensing can be a rapid, accurate, and simple method for assessing pest damage on plants. The objectives of this study were to identify spectral wavelengths sensitive to cotton aphid infestation. Then, the normalized difference spectral indices (NDSI) and ratio spectral indices (RSI) based on the leaf spectrum were obtained within 350–2500 nm, and their correlation with infestation were qualified. The results showed that leaf spectral reflectance decreased in the visible range (350–700 nm) and the near-infrared range (NIR, 700–1300 nm) as aphid damage severity increased, and significant differences were found in blue, green, red, NIR and short-wave infrared (SWIR) band regions between different grades of aphid damage severity. Decrease in Chlorophyll a (Chl a) pigment was more significant than that in Chlorophyll (Chl b) in the infested plants and the Chl a/b ratio showed a decreasing trend with increase in aphid damage severity. The sensitive spectral bands were mainly within NIR and SWIR ranges. The best spectral indices NDSI (R678, R1471) and RSI (R1975, R1904) were formulated with these sensitive spectral regions through reducing precise sampling method. These new indices along with 16 other stress related indices compiled from literature were further tested for their ability to detect aphid damage severity. The two indices in this study showed significantly higher coefficients of determination (R2 of 0.81 and 0.81, p < 0.01) and the least RMSE values (RMSE of 0.50 and 0.49), and hence have potential application in assessing aphid infestation severity in cotton.

Weed control is necessary in rice cultivation, but the excessive use of herbicide treatments has led to serious agronomic and environmental problems. Suitable site-specific weed management (SSWM) is a solution to address this problem while maintaining the rice production quality and quantity. In the context of SSWM, an accurate weed distribution map is needed to provide decision support information for herbicide treatment. UAV remote sensing offers an efficient and effective platform to monitor weeds thanks to its high spatial resolution. In this work, UAV imagery was captured in a rice field located in South China. A semantic labeling approach was adopted to generate the weed distribution maps of the UAV imagery. An ImageNet pre-trained CNN with residual framework was adapted in a fully convolutional form, and transferred to our dataset by fine-tuning. Atrous convolution was applied to extend the field of view of convolutional filters; the performance of multi-scale processing was evaluated; and a fully connected conditional random field (CRF) was applied after the CNN to further refine the spatial details. Finally, our approach was compared with the pixel-based-SVM and the classical FCN-8s. Experimental results demonstrated that our approach achieved the best performance in terms of accuracy. Especially for the detection of small weed patches in the imagery, our approach significantly outperformed other methods. The mean intersection over union (mean IU), overall accuracy, and Kappa coefficient of our method were 0.7751, 0.9445, and 0.9128, respectively. The experiments showed that our approach has high potential in accurate weed mapping of UAV imagery.