Local zoom system for agricultural pest detection and recognition

Shen, Benlan; Chang, Jun; Wu, Chan-Shuo; Jin, Yihan; Chen, Weilin; Song, Dalin; Mu, Yu

doi:10.1007/s00340-018-7089-4

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental set-up is built to validate the system's basic principle and is well used for the imaging of aphids on plant leaves. The results demonstrate that the system performs well for imaging of pests at different local magnifications [14]. Shuanglu Dai-2017 et.al, proposed a convolutional Riemannian texture with differential entropic active contours to distinguish the background regions and expose pest regions.…”

Section: Introductionmentioning

confidence: 88%

Pest Detection in Crop using Video and Image Processing

Chodey¹

2020

IJRASET

View full text Add to dashboard Cite

Detection of pests of various species is one of the compelling tasks in pest management involving detection and classification which is much more difficult than common object detection because of the apparent differences among pest species. Early diagnosis of pest is more essential to enhance the production of healthy crops as well as to diminish the economic loss. However, one major challenge is the difficulty in determining the physical, chemical, and biological changes in plants during the asymptomatic stages of an infection. To overcome these challenge, a huge count of traditional techniques were formulated. Many algorithms were introduced to detect the pests from leaves. Such techniques are not efficient for all the types of pest. To overcome the above said problem, this paper deals with pest detection, identification using segmentation and classification algorithms.

show abstract

Section: Introductionmentioning

confidence: 88%

Pest Detection in Crop using Video and Image Processing

Chodey¹

2020

IJRASET

View full text Add to dashboard Cite

show abstract

“…Based on the foveated magnifcation foveated imaging technology, we followed the methods of Shen et al 2018 [41] and used SRDA to build a 9× foveated-zoom snapshot hyperspectral imaging (LHSI) system for fruit pest monitoring. We achieved a 14-bands (460 nm-630 nm) using a 256 × 512-pixel foveated zoom hyperspectral imaging system, which has two imaging channels with the same image plane.…”

Section: Introductionmentioning

confidence: 99%

High Zoom Ratio Foveated Snapshot Hyperspectral Imaging for Fruit Pest Monitoring

Chang

et al. 2023

Journal of Spectroscopy

Self Cite

View full text Add to dashboard Cite

Snapshot hyperspectral imaging technology is increasingly used in agricultural product monitoring. In this study, we present a 9× local zoom snapshot hyperspectral imaging system. Using commercial spectral sensors with spectrally resolved detector arrays, we achieved snapshot hyperspectral imaging with 14 wavelength bands and a spectral bandwidth of 10–15 nm. An experimental demonstration was performed by acquiring spatial and spectral information about the fruit and Drosophila. The results show that the system can identify Drosophila and distinguish well between different types of fruits. The results of this study have great potential for online fruit classification and pest identification.

show abstract

“…The experiment results demonstrate that all of these metrics are better than those of a conventional refractive lens.In imaging system, magnification imaging and wide field of view (FOV) imaging are very important in order to get more information 1 . Applications that require magnification imaging and wide FOV imaging range from surveillance 2 and medicine 3-5 to artificial intelligence 6,7 . Since with just one focus in a conventional imaging system, it requires zoom to take magnified images and wide FOV images, which means magnified images and wide FOV images cannot be taken by the conventional zoom imaging systems simultaneously.…”

mentioning

confidence: 99%

Bifocal flat lens with different imaging characteristics for a dual-sensor imaging system

Zhou

Kuang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Wide field of view (FOV) images and magnified images can be taken simultaneously by dual-sensor imaging systems. Here, we propose an approach for creating a bifocal flat lens with different imaging characteristics of its two foci, which makes dual-sensor imaging systems more integrated and miniaturized. That is, two special parts of two different conventional ZP are extracted and then combine the two elements in a specific way. So that there are two foci with different characteristics along the optical axis, one is long focus with higher resolution, the other is short focus with long depth of focus (DOF). Under the proposed approach, a thin and light bifocal diffractive lens (BDL) with thickness of 0.6 μm is developed. The long and short focal lengths of the BDL are ~ 81 mm and ~ 27 mm, respectively, with a diameter of 6 mm. We experimentally demonstrate that the long focus of the BDL is capable of taking high-resolution magnified images, and its resolution is up to 21.90″. The short focus is able to take wide FOV with long DOF images, and two objects spread 2880 mm apart can be imaged clearly. The experiment results demonstrate that all of these metrics are better than those of a conventional refractive lens.

show abstract

Local zoom system for agricultural pest detection and recognition

Cited by 4 publications

References 19 publications

Pest Detection in Crop using Video and Image Processing

Pest Detection in Crop using Video and Image Processing

High Zoom Ratio Foveated Snapshot Hyperspectral Imaging for Fruit Pest Monitoring

Bifocal flat lens with different imaging characteristics for a dual-sensor imaging system

Contact Info

Product

Resources

About