Robotic harvesting offers a solution to reducing labor costs, optimizing harvest scheduling, enabling selective harvesting, and increasing operation efficiency. These attributes allow the users of robotic harvesters to maximize production efficiency and profits. This article reviews automated fruit harvesting systems of sweet pepper, tomato, apple and kiwifruit as an example to demonstrate the recent advances in intelligent automatic harvesting robots in horticulture.

Kernel smut, caused by Tilletia horrida, is a disease characterized by the replacement of rice grains with black sooty masses of teliospores or chlamydospores. Kernel smut differs from rice false smut, caused by Ustilaginoidea virens, in the color of chlamydospores. False smut is characterized by globose, velvety spore balls ranging from orangish yellow to greenish black in color. Both kernel smut and false smut have been persistent but are considered minor diseases in many countries since they were discovered in the late 1870s to the 1980s due to their sporadic outbreaks and limited economic impacts. In recent years, however, kernel smut and false smut have emerged as two of the most economically important diseases in rice, including organic rice, in many countries, especially in the United States. The increased use of susceptible rice cultivars, especially hybrids, excessive use of nitrogen fertilizer, and short crop rotations have resulted in an increase in kernel smut and false smut, causing significant losses in grain yield and quality. In this article, we provide a review of the distribution and economic importance of kernel smut; our current understanding of the taxonomy, biology, and epidemiology of kernel smut; and the genomics of the kernel smut fungus as compared with false smut and its causal agent. We also provide an update on the current management strategies of pathogen exclusion, cultivar resistance, fungicides, biological control, and cultural practices for kernel smut and false smut of rice.

Bacterial panicle blight (BPB) is present in more than 18 countries and has become a global disease in rice. BPB is highly destructive and can cause significant losses of up to 75% in yield and milling quality. BPB is caused by Burkholderia glumae or B. gladioli, with the former being the primary cause of the disease. Outbreaks of BPB are triggered by conditions of high temperatures in combination with high relative humidity at heading. The disease cycle starts with primary infections from infected seed, soil, and irrigation water, and subsequent secondary infections result from rain splash and panicle contact. Limited management options are available for control of BPB. There are only several cultivars including hybrids with partial resistance available currently. Twelve quantitative trait loci (QTLs) associated with the partial resistance have been identified. Oxolinic acid is an effective antibacterial compound for control of BPB in Japan, but it is not labeled for use on rice in the USA and many other countries. Sustainable control of BPB relies on integrated use of available management strategies of exclusion, genetic resistance, chemical control, biocontrol, and cultural practice. Developing and use of resistant cultivars is the best strategy to minimize the damage caused by BPB and maximize rice production in the long term.

Cercospora janseana is the causal agent of narrow brown leaf spot, one of the major diseases of rice in the United States. In vitro studies were conducted to evaluate various plant-based agar media in comparison with potato dextrose agar (PDA) for their effects on radial growth and sporulation of C. janseana. The agar media were evaluated individually with the following plant-extract ingredients: fresh rice leaves, dried rice leaves, dried rice stems, dried rice roots, dried rice hulls, dried rice straw, rice bran, dried sorghum leaves, and dried barnyard grass leaves. Plant-based extracts obtained from 25, 50, 100, or 200 g/liter (plant material/water) were tested either alone or in combination with 10 and 20% clarified V8 juice. PDA served as the control medium. Media with 10 and 20% V8 juice were also included for comparison. Media were inoculated with a disc of 1-week-old actively growing C. janseana at the center of Petri plates and incubated at 28°C with a 12/12-h (light/dark) cycle for 2 weeks. Radial growth was measured at 7 and 14 days after inoculation (DAI), whereas sporulation was measured at 14 DAI. Radial growth and sporulation differed among various media and their amendment concentrations. Media with extracts of fresh rice leaves, dried rice leaves, dried rice stems, dried barnyard grass leaves, and clarified V8 juice enhanced radial growth compared with the PDA control. Of all the agar media evaluated, fresh rice leaf extract amendment at 25 g/liter with no V8 supplementation consistently supported the greatest radial growth, and 10% V8-only medium resulted in greater sporulation of C. janseana than other media evaluated.

Sheath blight (ShB), caused by Rhizoctonia solani AG1-I, is one of the most important diseases in rice worldwide. The symptoms of ShB primarily develop on leaf sheaths and leaf blades. Hyperspectral remote sensing technology has the potential of rapid, efficient and accurate detection and monitoring of the occurrence and development of rice ShB and other crop diseases. This study evaluated the spectral responses of leaf blade fractions with different development stages of ShB symptoms to construct the spectral feature library of rice ShB based on “three-edge” parameters and narrow-band vegetation indices to identify the disease on the leaves. The spectral curves of leaf blade lesions have significant changes in the blue edge, green peak, yellow edge, red valley, red edge and near-infrared regions. The variables of the normalized index between green peak amplitude and red valley amplitude (Rg − Ro)/(Rg + Ro), the normalized index between the yellow edge area and blue edge area (SDy − SDb)/(SDy + SDb), the ratio index of green peak amplitude and red valley amplitude (Rg/Ro) and the nitrogen reflectance index (NRI) had high relevance to the disease. At the leaf scale, the importance weights of all attributes decreased with the effect of non-infected areas in a leaf by the ReliefF algorithm, with Rg/Ro being the indicator having the highest importance weight. Estimation rate of 95.5% was achieved in the decision tree classifier with the parameter of Rg/Ro. In addition, it was found that the variety degree of absorptive valley, reflection peak and reflecting steep slope was different in the blue edge, green and red edge regions, although there were similar spectral curve shapes between leaf sheath lesions and leaf blade lesions. The significant difference characteristic was the ratio index of the red edge area and green peak area (SDr/SDg) between them. These results can provide the basis for the development of a specific sensor or sensors system for detecting the ShB disease in rice.

Lodging is one of the major issues that seriously affects wheat quality and yield. To obtain timely and accurate wheat lodging information and identify the potential factors leading to lodged wheat in wheat breeding programs, we proposed a lodging-detecting model coupled with unmanned aerial vehicle (UAV) image features of wheat at multiple plant growth stages. The UAV was used to collect canopy images and ground lodging area information at five wheat growth stages. The PSPNet model was improved by combining the convolutional LSTM (ConvLSTM) timing model, inserting the convolutional attention module (CBAM) and the Tversky loss function. The effect of the improved PSPNet network model in monitoring wheat lodging under different image sizes and different growth stages was investigated. The experimental results show that (1) the improved Lstm_PSPNet model was more effective in lodging prediction, and the precision reached 0.952; (2) choosing an appropriate image size could improve the segmentation accuracy, with the optimal image size in this study being 468 × 468; and (3) the model of Lstm_PSPNet improved its segmentation accuracy sequentially from early flowering to late maturity, and the three evaluation metrics increased sequentially from 0.932 to 0.952 for precision, from 0.912 to 0.940 for recall, and from 0.922 to 0.950 for F1-Score, with good extraction at mid and late reproductive stages. Therefore, the lodging information extraction model proposed in this study can make full use of temporal sequence features to improve image segmentation accuracy and effectively extract lodging areas at different growth stages. The model can provide more comprehensive reference and technical support for monitoring the lodging of wheat crops at different growth stages.