Research on Automatic Counting Soybean Leaf Aphids System Based on Computer Vision Technology

Shen, Weizheng; Zhang, Changli; Chen, Zhan-Liang

doi:10.1109/icmlc.2007.4370408

Cited by 7 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Investigators are often required to traverse soybean fields to count aphids on plants, the low efficiency of scouting is the main reason for the low adoption rate of IPM. 14,65 At present, the efficient nondestructive pest monitoring methods include the use of technologies of computer vision, 66 remote sensing, 67,68 and digital imaging, 69,70 among others, and the development of a portable pest monitoring system based on a smart phone platform, which is particularly suitable for monitoring large commercial fields over time. Such a project would enable more widespread adoption of IPM.…”

Section: Discussionmentioning

confidence: 99%

Comparing the cost–benefit probability of management based on early‐stage and late‐stage economic thresholds with that of seed treatment of Aphis glycines

Tong-hua

Xing³

et al. 2022

Pest Management Science

View full text Add to dashboard Cite

Background The current integrated pest management (IPM) curative strategy for soybean aphid, Aphis glycines Matsumura (Hemiptera: Aphididae), relies on responsive spraying foliar insecticides during the R1–R5 soybean stage when aphid abundance reaches the economic threshold (ET) of 250 aphids plant−1 (traditional IPM). By analyzing the relationship between aphid abundance and yield loss before the R1 stage, we developed an early‐stage ET. We propose to spray foliar insecticides on plants colonized with aphids using the early‐stage ET as a trigger (improved IPM), together with seed treatment to manage A. glycines and delay them exceeding the ET of 250 aphids plant−1 in the late stage for whole‐field spraying (traditional IPM). Finally, we compared the cost–benefit probabilities of the three management approaches. Results The early‐stage ET over all potential yields, market prices, and control costs was 64 aphids plant−1, providing growers 7 days of preparation time to spray foliar insecticides before the economic injury level of 187 aphids plant−1 was reached. Improved IPM achieved the highest cost–benefit probabilities followed by traditional IPM, and the seed treatment achieved the lowest. However, in fields where the pressure from white grubs was high, the probability of achieving a positive net return with seed treatment was higher than that in other locations. Conclusion Improved IPM based on early‐stage ET of 64 aphids plant−1 was the most cost‐effective of all the three approaches. Neonicotinoid seed treatment can be applied as an insurance strategy to supplement A. glycines IPM in Liaoning, China. © 2022 Society of Chemical Industry.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparing the cost–benefit probability of management based on early‐stage and late‐stage economic thresholds with that of seed treatment of Aphis glycines

Tong-hua

Xing³

et al. 2022

Pest Management Science

View full text Add to dashboard Cite

show abstract

“…The method of L1 can increase its robustness. The OpenCV library is used to calculate TV-L1 optical flow field [18]. The steps are as follows.…”

Section: Transformation Layermentioning

confidence: 99%

Two-Stream Convolutional Neural Network for Video Action Recognition

2021

KSII TIIS

View full text Add to dashboard Cite

“…Automatic counting of objects in digital images is a subject that has received significant attention in the last 20 years, dealing with objects as varied as cells [1], bacteria [2], trees [3], fruit [4], pollen [5], insects [6], people [7], etc. However, to the author's knowledge there is only one method to automatically count nodules using digital images, which was proposed by Lira and Smith [8].…”

Section: Introductionmentioning

confidence: 99%

Method for Automatic Counting Root Nodules Using Digital Images

Barbedo

2012

2012 12th International Conference on Computational Science and Its Applications

View full text Add to dashboard Cite

This paper presents a method to automatically count nodules that are present in the roots of many legume plants, using digital images captured after the nodules have been removed from the roots. This problem poses a significant challenge due to a number of reasons: the size and shape of the nodules vary greatly, they may appear clustered, and their texture is not uniform. The proposed method exploits wellknown morphological operations to discriminate each nodule, making the counting process possible. Tests reveal a good correlation between automatic and manual counting.

show abstract

Research on Automatic Counting Soybean Leaf Aphids System Based on Computer Vision Technology

Cited by 7 publications

References 7 publications

Comparing the cost–benefit probability of management based on early‐stage and late‐stage economic thresholds with that of seed treatment of Aphis glycines

Comparing the cost–benefit probability of management based on early‐stage and late‐stage economic thresholds with that of seed treatment of Aphis glycines

Two-Stream Convolutional Neural Network for Video Action Recognition

Method for Automatic Counting Root Nodules Using Digital Images

Contact Info

Product

Resources

About