Plant phenomics has been rapidly advancing over the past few years. This advancement is attributed to the increased innovation and availability of new technologies which can enable the high-throughput phenotyping of complex plant traits. The application of artificial intelligence in various domains of science has also grown exponentially in recent years. Notably, the computer vision, machine learning, and deep learning aspects of artificial intelligence have been successfully integrated into non-invasive imaging techniques. This integration is gradually improving the efficiency of data collection and analysis through the application of machine and deep learning for robust image analysis. In addition, artificial intelligence has fostered the development of software and tools applied in field phenotyping for data collection and management. These include open-source devices and tools which are enabling community driven research and data-sharing, thereby availing the large amounts of data required for the accurate study of phenotypes. This paper reviews more than one hundred current state-of-the-art papers concerning AI-applied plant phenotyping published between 2010 and 2020. It provides an overview of current phenotyping technologies and the ongoing integration of artificial intelligence into plant phenotyping. Lastly, the limitations of the current approaches/methods and future directions are discussed.
A vision-based weed control robot for agricultural field application requires robust vegetation segmentation. The output of vegetation segmentation is the fundamental element in the subsequent process of weed and crop discrimination as well as weed control. There are two challenging issues for robust vegetation segmentation under agricultural field conditions: (1) to overcome strongly varying natural illumination; (2) to avoid the influence of shadows under direct sunlight conditions. A way to resolve the issue of varying natural illumination is to use high dynamic range (HDR) camera technology. HDR cameras, however, do not resolve the shadow issue. In many cases, shadows tend to be classified during the segmentation as part of the foreground, i.e., vegetation regions. This study proposes an algorithm for ground shadow detection and removal, which is based on color space conversion and a multilevel threshold, and assesses the advantage of using this algorithm in vegetation segmentation under natural illumination conditions in an agricultural field. Applying shadow removal improved the performance of vegetation segmentation with an average improvement of 20, 4.4, and 13.5% in precision, specificity and modified accuracy, respectively. The average processing time for vegetation segmentation with shadow removal was 0.46 s, which is acceptable for real-time application (<1 s required). The proposed ground shadow detection and removal method enhances the performance of vegetation segmentation under natural illumination conditions in the field and is feasible for real-time field applications.
In greenhouses, plant growth is directly influenced by internal environmental conditions, and therefore requires continuous management and proper environmental control. Inadequate environmental conditions make plants vulnerable to pests and diseases, lower yields, and cause impaired growth and development. Previous studies have explored the combination of greenhouse actuator control history with internal and external environmental data to enhance prediction accuracy, using deep learning-based models such as RNNs and LSTMs. In recent years, transformer-based models and RNN-based models have shown good performance in various domains. However, their applications for time-series forecasting in a greenhouse environment remain unexplored. Therefore, the objective of this study was to evaluate the prediction performance of temperature, relative humidity (RH), and CO2 concentration in a greenhouse after 1 and 3 h, using a transformer-based model (Autoformer), variants of two RNN models (LSTM and SegRNN), and a simple linear model (DLinear). The performance of these four models was compared to assess whether the latest state-of-the-art (SOTA) models, Autoformer and SegRNN, are as effective as DLinear and LSTM in predicting greenhouse environments. The analysis was based on four external climate data samples, three internal data samples, and six actuator data samples. Overall, DLinear and SegRNN consistently outperformed Autoformer and LSTM. Both DLinear and SegRNN performed well in general, but were not as strong in predicting CO2 concentration. SegRNN outperformed DLinear in CO2 predictions, while showing similar performance in temperature and RH prediction. The results of this study do not provide a definitive conclusion that transformer-based models, such as Autoformer, are inferior to linear-based models like DLinear or certain RNN-based models like SegRNN in predicting time series for greenhouse environments.
Panax ginseng has been used as a traditional medicine to strengthen human health for centuries. Over the last decade, significant agronomical progress has been made in the development of elite ginseng cultivars, increasing their production and quality. However, as one of the significant environmental factors, heat stress remains a challenge and poses a significant threat to ginseng plants’ growth and sustainable production. This study was conducted to investigate the phenotype of ginseng leaves under heat stress using hyperspectral imaging (HSI). A visible/near-infrared (Vis/NIR) and short-wave infrared (SWIR) HSI system were used to acquire hyperspectral images for normal and heat stress-exposed plants, showing their susceptibility (Chunpoong) and resistibility (Sunmyoung and Sunil). The acquired hyperspectral images were analyzed using the partial least squares-discriminant analysis (PLS-DA) technique, combining the variable importance in projection and successive projection algorithm methods. The correlation of each group was verified using linear discriminant analysis. The developed models showed 12 bands over 79.2% accuracy in Vis/NIR and 18 bands with over 98.9% accuracy at SWIR in validation data. The constructed beta-coefficient allowed the observation of the key wavebands and peaks linked to the chlorophyll, nitrogen, fatty acid, sugar and protein content regions, which differentiated normal and stressed plants. This result shows that the HSI with the PLS-DA technique significantly differentiated between the heat-stressed susceptibility and resistibility of ginseng plants with high accuracy.