ABSTRACT
A set of variable spraying system was designed based on TI's DM8168 cpu, and the cotton field video images were acquired via a webcam and sent to the image processor. The image processor would then give the weed position and variety after the analysis and recognition, pass to the DM8168 spraying equipment, and control the pesticide application of the spraying mechanism. In order to accurately distinguish the cotton from weeds, the deep learning model of Faster R-CNN convolutional network was introduced into the cotton weed image recognition, and a method of optimized structure, which was applicable to the cotton field weed recognition under complex background, was proposed. The test results show that the average target recognition accuracy of this method reaches 94.9%, the average time consumed by single-image recognition is 1.51 s, but it is shortened to 0.09 s after the acceleration through the GPU hardware. With a favorable defection effect on cotton weeds, the proposed method can provide a reference for the development of precise weeding.
- Niu Cong, Xu Liming, Ma Shuai, Application and Development of Variable Spray Technology[J]. Agricultural Equipment & Vehicle Engineering, Dec.2018,56(12):1-4Google Scholar
- Yin Dongfu, Chen Shuren, Mao Hanping, Weed control system for variable target spraying based on fuzzy control[J].Transactions of the Chinese Society for Agricultural Machinery,2011,42(4):179-183Google Scholar
- Bakhshipour A, Jafari A, Nassiri S M, Weed segmentation using texture features extracted from wavelet sub-images[J]. Biosystems Engineering, 2017, 157: 1-12.Google ScholarCross Ref
- Zhang Xiaolong, Xie Zhengchun, Zhang Niansheng, Weed recognition from pea seedling images and variables praying control system[J]. Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(11): 220-225,73.Google Scholar
- Li Xianfeng, Zhu Weixing, Ji Bin, Shape feature selection and weed recognition based on image processing and ant colony optimization[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(10): 178-182.Google Scholar
- Zheng Y, Zhu Q, Huang M, Maize and weed classification using color indices with support vector data description in outdoor fields[J]. Computers and Electronics in Agriculture, 2017, 141: 215-222.Google ScholarDigital Library
- Li Ying,Zhang Lifu,Yan Wei,et al. Weed identification using imaging spectrometer data[J]. Journal of Remote Sensing. 2013,17(4):855-862.Google Scholar
- Zhao Peng, Wei Xingzhu. Weed ༲ecognition in Agricultural Field Using Multiple Feature Fusions[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014,45(3):275-281.Google Scholar
- He Dongjian, Qiao Yongliang, Li Pan, Weed Recognition Based on SVM-DS Multi-feature Fusion[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013,44(2):182-187.Google Scholar
- Zhu Fengwu,Yang Jianjiao,Qi Ji.Study of field biological environment system based on genetic algorithm[J].Journal of Chinese Agricultural Mechanization,2016,37(12):157-161.Google Scholar
- Quan Longzhe, Xiao Yunhan,Wang Jianyu, Study on pattern recognition method of intelligent weeding equipment[J].Journal of Northeast Agricultural University, 2018, 49(9): 79-87. (in Chinese with English abstract)Google Scholar
- Wu Lanlan, Xu Kai, Xiong Lirong. Detecting weed in seedling rapeseed oil field based on visual-attention model[J]. Journal of Huazhong Agricultural University,2018,37( 2):96-102.Google Scholar
- Fu Longsheng, Feng Yali, Elkamil Tola, Image recognition method of multi-cluster kiwifruit in field based on convolutional neural networks[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(2): 205−211. (in Chinese with English abstract)Google Scholar
- Wang Can, Wu Xinhui, Li Zhiwei. Recognition of maize and weed based on multi-scale hierarchical features extracted by convolutional neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE),2018, 34(5): 144 − 151. (in Chinese with English abstract)Google Scholar
- Jiang Honghua, Wang Pengfei, Zhang Zhao, Fast Identification of Field Weeds Based on Deep Convolutional Network and Binary Hash Code[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018,49(11),30-38.Google Scholar
- Yin Dongfu, Chen Shuren, Pei Wenchao, Design of map-based indoor variable weed spraying system [J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2011, 27(4), 131-135.Google Scholar
- Yin Dongfu, Chen Shuren, Mao Hanping,et al. Weed Control System for Variable Target Spraying Based on Fuzzy Control[J]. Transactions of the Chinese Society for Agricultural Machinery, 2011,42(4),179-183.Google Scholar
- Wei Xinhua. Development of vehicular embedded information processing system for map-based precision farming[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013,29(6),142-145Google Scholar
- He Kaiming, Zhang Xiangyu, Ren Shaoqing, Deep Residual Learning for Image Recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016(C):770-778.Google Scholar
- T Lin,P Dollar,R Girshick, Feature Pyramid Networks for Object Detection[C]. IEEE Conference on Computer Vision and Pattern Recognition , Honolulu, Hawaii, USA ,2017(C): 936-944.Google Scholar
- He Kaiming, Gkioxari Georgia, Dollar Piotr, Mask R-CNN[C]. IEEE International Conference on Computer Vision, Venice, Italy,2017(C):2980-2988.Google Scholar
- Yang You, Igor Gitman, Boris Ginsburg. Large Batch Training of Convolutional Networks[J]. arXiv:1708.03888, 2017.Google Scholar
- Yang You, Zhao Zhang, Cho-Jui Hsieh, ImageNet Training in Minutes[J]. arXiv:1709.05011,2018.Google Scholar
- Chao Peng, Tete Xiao, Zeming Li, et,al. MegDet: A Large Mini-Batch Object Detector[C]. IEEE Conference on Computer Vision and Pattern Recognition, UTAH, USA, 2018(C): 6181-6189.Google Scholar
Recommendations
Identification of red and NIR spectral regions and vegetative indices for discrimination of cotton nitrogen stress and growth stage
Studies have demonstrated the value of spectral vegetation indices (VIs) based on red and near-infrared (NIR) spectral reflectance in agriculture. The objective of this research was to analyze the effects of central wavelengths and bandwidths of red and ...
Use of ground based hyperspectral remote sensing for detection of stress in cotton caused by leafhopper (Hemiptera: Cicadellidae)
Detection of crop stress is one of the major applications of hyperspectral remote sensing in agriculture. Many studies have demonstrated the capability of remote sensing techniques for detection of nutrient stress on cotton with only few on pest damage ...
Ground-based sensing system for weed mapping in cotton
A ground-based weed mapping system was developed to measure weed intensity and distribution in a cotton field. The weed mapping system includes WeedSeeker^(R) PhD600 sensor modules to indicate the presence of weeds between rows, a GPS receiver to ...
Comments