Appropriate Site Specific Weed Management (SSWM) is crucial to ensure the crop yields. Within SSWM of large-scale area, remote sensing is a key technology to provide accurate weed distribution information. Compared with satellite and piloted aircraft remote sensing, unmanned aerial vehicle (UAV) is capable of capturing high spatial resolution imagery, which will provide more detailed information for weed mapping. The objective of this paper is to generate an accurate weed cover map based on UAV imagery. The UAV RGB imagery was collected in 2017 October over the rice field located in South China. The Fully Convolutional Network (FCN) method was proposed for weed mapping of the collected imagery. Transfer learning was used to improve generalization capability, and skip architecture was applied to increase the prediction accuracy. After that, the performance of FCN architecture was compared with Patch_based CNN algorithm and Pixel_based CNN method. Experimental results showed that our FCN method outperformed others, both in terms of accuracy and efficiency. The overall accuracy of the FCN approach was up to 0.935 and the accuracy for weed recognition was 0.883, which means that this algorithm is capable of generating accurate weed cover maps for the evaluated UAV imagery.

No abstract

Plant protection unmanned aerial vehicles (UAVs) consist of light and small UAVs with pesticide spraying equipment. The advantage of UAVs is using low-volume spray technology to replace the traditional large-volume mass locomotive spray technology. Defoliant spraying is a key link in the mechanized cotton harvest, as sufficient and uniform spraying can improve the defoliation quality and decrease the cotton trash content. However, cotton is planted at high density in Xinjiang, with leaves in two adjacent rows seriously overlapped, making the lower leaves poorly sprayed. Thus, the defoliation effect is poor, and the cotton quality is degraded. To improve the effect of defoliation and reduce the losses caused by boom sprayer rolling, the effect of defoliant dosage on defoliation, boll opening, absorption and decontamination in cotton leaves and the effect of spraying volume on absorption and decontamination in cotton leaves sprayed by UAVs are studied. The pooled results indicate that plant protection UAVs could be used for cotton defoliants spraying with a twice defoliant spraying strategy, and the defoliant dosage has no significant effect on seed cotton yield and fiber quality in Xinjiang. The residue of thidiazuron in cotton leaves reaches the maximum at four days after spraying, the residue of diuron in cotton leaves reaches the maximum at one day after second spraying. The thidiazuron and diuron residues are increased with spraying volume at rang of 17.6-29.0 L/ha. When the spraying volume is less than 17.6 L/ha, the residue of thidiazuron and diuron is reduced. The research results could provide a reference for further optimization of the spraying parameters of cotton defoliant by plant protection UAVs.

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.

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.

Unmanned aerial vehicle (UAV) variable-rate spraying technology, as the development direction of aviation for plant protection in the future, has been developed rapidly in recent years. In the actual agricultural production, the severity of plant diseases and insect pests varies in different locations. In order to reduce the waste of pesticides, pesticides should be applied according to the severity of pests, insects and weeds. On the basis of explaining the plant diseases and insect pests map in the target area, a pulse width modulation variable spray system is designed. Moreover, the STMicroelectronics-32 (STM32) chip is invoked as the core of the control system. The system combines with sensor technology to get the prescription value through real-time interpretation of prescription diagram in operation. Then, a pulse square wave with variable duty cycles is generated to adjust the flow rate. A closed-loop Proportional-Integral-Derivative (PID) control algorithm is used to shorten the time of system reaching steady state. The results indicate that the deviation between volume and target traffic is stable, which is within 2.16%. When the duty cycle of the square wave is within the range of 40% to 100%, the flow range of the single nozzle varies from 0.16 L/min to 0.54 L/min. Variable spray operation under different spray requirements is achieved. The outdoor tests of variable spray system show that the variable spray system can adjust the flow rapidly according to the prescription value set in the prescription map. The proportion of actual droplet deposition and deposition density in the operation unit is consistent with the prescription value, which proves the effectiveness of the designed variable spray system.

The timely and efficient generation of weed maps is essential for weed control tasks and precise spraying applications. Based on the general concept of site-specific weed management (SSWM), many researchers have used unmanned aerial vehicle (UAV) remote sensing technology to monitor weed distributions, which can provide decision support information for precision spraying. However, image processing is mainly conducted offline, as the time gap between image collection and spraying significantly limits the applications of SSWM. In this study, we conducted real-time image processing onboard a UAV to reduce the time gap between image collection and herbicide treatment. First, we established a hardware environment for real-time image processing that integrates map visualization, flight control, image collection, and real-time image processing onboard a UAV based on secondary development. Second, we exploited the proposed model design to develop a lightweight network architecture for weed mapping tasks. The proposed network architecture was evaluated and compared with mainstream semantic segmentation models. Results demonstrate that the proposed network outperform contemporary networks in terms of efficiency with competitive accuracy. We also conducted optimization during the inference process. Precision calibration was applied to both the desktop and embedded devices and the precision was reduced from FP32 to FP16. Experimental results demonstrate that this precision calibration further improves inference speed while maintaining reasonable accuracy. Our modified network architecture achieved an accuracy of 80.9% on the testing samples and its inference speed was 4.5 fps on a Jetson TX2 module (Nvidia Corporation, Santa Clara, CA, USA), which demonstrates its potential for practical agricultural monitoring and precise spraying applications.

No abstract