Evaluation of two deep learning-based approaches for detecting weeds growing in cabbage.

BACKGROUND: Machine vision-based precision weed management is a promising solution to substantially reduce herbicide input and weed control cost. The objective of this research was to compare two different deep learning-based approaches for detecting weeds in cabbage: (1) detecting weeds directly, and (2) detecting crops by generating the bounding boxes covering the crops and any green pixels outside the bounding boxes were deemed as weeds. RESULTS: The precision, recall, F1-score, mAP0.5, mAP0.5:0.95 of You Only Look Once (YOLO) v5 for detecting cabbage were 0.986, 0.979, 0.982, 0.995, and 0.851, respectively, while these metrics were 0.973, 0.985, 0.979, 0.993, and 0.906 for YOLOv8, respectively. However, none of these metrics exceeded 0.891 when detecting weeds. The reduced performances for directly detecting weeds could be attributed to the diverse weed species at varying densities and growth stages with different plant morphologies. A segmentation procedure demonstrated its effectiveness for extracting weeds outside the bounding boxes covering the crops, and thereby realizing effective indirect weed detection. CONCLUSION: The indirect weed detection approach demands less manpower as the need for constructing a large training dataset containing a variety of weed species is unnecessary. However, in a certain case, weeds are likely to remain undetected due to their growth in close proximity with crops and being situated within the predicted bounding boxes that encompass the crops. The models generated in this research can be used in conjunction with the machine vision subsystem of a smart sprayer or mechanical weeder. © 2024 Society of Chemical Industry.

Semi-supervised learning methods for weed detection in turf.

BACKGROUND: Accurate weed detection is a prerequisite for precise automatic precision herbicide application. Previous research has adopted the laborious and time-consuming approach of manually labeling and processing large image data sets to develop deep neural networks for weed detection. This research introduces a novel semi-supervised learning (SSL) approach for detecting weeds in turf. The performance of SSL was compared with that of ResNet50, a fully supervised learning (FSL) method, in detecting and differentiating sub-images containing weeds from those containing only turfgrass. RESULTS: Compared with ResNet50, the evaluated SSL methods, Π-model, Mean Teacher, and FixMatch, increased the classification accuracy by 2.8%, 0.7%, and 3.9%, respectively, when only 100 labeled images per class were utilized. FixMatch was the most efficient and reliable model, as it exhibited higher accuracy (≥0.9530) and F1 scores (≥0.951) with fewer labeled data (50 per class) in the validation and testing data sets than the other neural networks evaluated. CONCLUSION: These results reveal that the SSL deep neural networks are capable of being highly accurate while requiring fewer labeled training images, thus being more time- and labor-efficient than the FSL method. © 2024 Society of Chemical Industry.

[Effects of light intensities on growth,physiological characteristic and chemical composition of Viola yedoensis].

The study is aimed to investigate the effects of light intensities on growth,photosynthetic physiology,antioxidant systems and chemical composition of Viola yedoensis and provide cultivation references for V.yedoensis.Five groups of V.yedoensis were planted under five light intensities conditions,namely 100%,80%,50%,35%,5%of full sunlight,and then morphological index,growth,chlorophyll fluorescence parameters,photosynthetic parameters and antioxidant enzyme system indexes were measured during harvest.The results showed that there was no significant difference in the biomass of V.yedoensis among 35% -100%full sunlight,but the biomass of those were significantly higher than that in the 5%full sunlight treatment(P<0.05).The net photosynthetic rate,transpiration rate,stomatal conductance,intercellular CO_2 concentration and water use efficiency increased firstly and then decreased with the decrease of light intensity;F_m,F_v/F_mand Yield in 5% full sunlight treatment were significantly lower than those in the other four groups(P<0.05).The structure of chloroplast was normal under light intensity ranged from 50%to 100% full sunlight.The lamellar concentration of chloroplast matrix decreased and the starch granules decreased in 35% full sunlight treatment,and the margin of lamellar layer of chloroplast and substrate were blurred,and the starch granules were small and the number of starch granules decreased significantly under 5% full sunlight.MDA content in 5%full sunlight treatment was significantly higher than those in the other four groups(P<0.05).The total coumarin content and total flavonoid content decreased with the decrease of light intensity.In summary,the light in-tensity range suitable for the growth of V.yedoensis is wide(ranging from 35% to 100% full sunlight).The content of flavonoids and coumarins is positively correlated with light intensity.