Evaluating Cross-Applicability of Weed Detection Models Across Different Crops in Similar Production Environments

Research Progress of Spectral Imaging Techniques in Plant Phenotype Studies

Spectral imaging technique has been widely applied in plant phenotype analysis to improve plant trait selection and genetic advantages. The latest developments and applications of various optical imaging techniques in plant phenotypes were reviewed, and their advantages and applicability were compared. X-ray computed tomography (X-ray CT) and light detection and ranging (LiDAR) are more suitable for the three-dimensional reconstruction of plant surfaces, tissues, and organs. Chlorophyll fluorescence imaging (ChlF) and thermal imaging (TI) can be used to measure the physiological phenotype characteristics of plants. Specific symptoms caused by nutrient deficiency can be detected by hyperspectral and multispectral imaging, LiDAR, and ChlF. Future plant phenotype research based on spectral imaging can be more closely integrated with plant physiological processes. It can more effectively support the research in related disciplines, such as metabolomics and genomics, and focus on micro-scale activities, such as oxygen transport and intercellular chlorophyll transmission.

More eyes on the prize: open-source data, software and hardware for advancing plant science through collaboration

Automating the analysis of plants using image processing would help remove barriers to phenotyping and large-scale precision agricultural technologies, such as site-specific weed control. The combination of accessible hardware and high-performance deep learning (DL) tools for plant analysis is becoming widely recognised as a path forward for both plant science and applied precision agricultural purposes. Yet, a lack of collaboration in image analysis for plant science, despite the open-source origins of much of the technology, is hindering development. Here, we show how tools developed for specific attributes of phenotyping or weed recognition for precision weed control have substantial overlapping data structure, software/hardware requirements and outputs. An open-source approach to these tools facilitates interdisciplinary collaboration, avoiding unnecessary repetition and allowing research groups in both basic and applied sciences to capitalise on advancements and resolve respective bottlenecks. The approach mimics that of machine learning in its nascence. Three areas of collaboration are identified as critical for improving efficiency, (1) standardized, open-source, annotated dataset development with consistent metadata reporting; (2) establishment of accessible and reliable training and testing platforms for DL algorithms; and (3) sharing of all source code used in the research process. The complexity of imaging plants and cost of annotating image datasets means that collaboration from typically distinct fields will be necessary to capitalize on the benefits of DL for both applied and basic science purposes.

Use of synthetic images for training a deep learning model for weed detection and biomass estimation in cotton

Site-specific treatment of weeds in agricultural landscapes has been gaining importance in recent years due to economic savings and minimal impact on the environment. Different detection methods have been developed and tested for precision weed management systems, but recent developments in neural networks have offered great prospects. However, a major limitation with the neural network models is the requirement of high volumes of data for training. The current study aims at exploring an alternative approach to the use of real images to address this issue. In this study, synthetic images were generated with various strategies using plant instances clipped from UAV-borne real images. In addition, the Generative Adversarial Networks (GAN) technique was used to generate fake plant instances which were used in generating synthetic images. These images were used to train a powerful convolutional neural network (CNN) known as "Mask R-CNN" for weed detection and segmentation in a transfer learning mode. The study was conducted on morningglories (MG) and grass weeds (Grass) infested in cotton. The biomass for individual weeds was also collected in the field for biomass modeling using detection and segmentation results derived from model inference. Results showed a comparable performance between the real plant-based synthetic image (mean average precision for mask-mAPm: 0.60; mean average precision for bounding box-mAPb: 0.64) and real image datasets (mAPm: 0.80; mAPb: 0.81). However, the mixed dataset (real image  + real plant instance-based synthetic image dataset) resulted in no performance gain for segmentation mask whereas a very small performance gain for bounding box (mAPm: 0.80; mAPb: 0.83). Around 40-50 plant instances were sufficient for generating synthetic images that resulted in optimal performance. Row orientation of cotton in the synthetic images was beneficial compared to random-orientation. Synthetic images generated with automatically-clipped plant instances performed similarly to the ones generated with manually-clipped instances. Generative Adversarial Networks-derived fake plant instances-based synthetic images did not perform as effectively as real plant instance-based synthetic images. The canopy mask area predicted weed biomass better than bounding box area with R2 values of 0.66 and 0.46 for MG and Grass, respectively. The findings of this study offer valuable insights for guiding future endeavors oriented towards using synthetic images for weed detection and segmentation, and biomass estimation in row crops.

YOLOX-based blue laser weeding robot in corn field

A YOLOX convolutional neural network-based weeding robot was designed for weed removal in corn seedling fields, while verifying the feasibility of a blue light laser as a non-contact weeding tool. The robot includes a tracked mobile platform module, a weed identification module, and a robotic arm laser emitter module. Five-degree-of-freedom robotic arm designed according to the actual weeding operation requirements to achieve precise alignment of the laser. When the robot is in operation, it uses the texture and shape of the plants to differentiate between weeds and corn seedlings. The robot then uses monocular ranging to calculate the coordinates of the weeds using the triangle similarity principle, and it controls the end actuator of the robotic arm to emit the laser to kill the weeds. At a driving speed of 0.2 m·s^-1 on flat ground, the weed robot's average detection rate for corn seedlings and weeds was 92.45% and 88.94%, respectively. The average weed dry weight prevention efficacy was 85%, and the average seedling injury rate was 4.68%. The results show that the robot can accurately detect weeds in corn fields, and the robotic arm can precisely align the weed position and the blue light laser is effective in removing weeds.