Recognition of cotton growth period for precise spraying based on convolution neural network

Abstract Dynamic acquisition of crop morphology is beneficial to real-time variable decision of precise spraying operations in fields. However, the existing spraying quantity regulation has high tolerance on the statistical characteristics of regional morphology, so expensive LiDAR and ultrasonic radar can't make full use of their high accuracy, and can reduce decision speed because of too much detail of branches and leaves. Therefore, designing a novel recognition system embedded machine learning with low-cost monocular vision is more feasible, especially in China, where the agricultural implements are medium sizes and cost-sensitive. In addition, we found that the growth period of crops is an important reference index for guiding spraying. So, taking cotton as a case study, a cotton morphology acquisition by a single camera is established, and a cotton growth period recognition algorithm based on Convolution Neural Network (CNN) is proposed in this paper. Through the optimization process based on confusion matrix and recognition efficiency, an optimized CNN model structure is determined from 9 different model structures, and its reliability was verified by changing training sets and test sets many times based on the idea of k-fold test. The accuracy, precision, recall, F1-score and recognition speed of this CNN model are 93.27%, 95.39%, 94.31%, 94.76% and 71.46 ms per image, respectively. In addition, compared with the performance of VGG16 and AlexNet, the convolution neural network model proposed in this paper has better performance. Finally, in order to verify the reliability of the designed recognition system and the feasibility of the spray decision-making algorithm based on CNN, spraying deposition experiments were carried out with 3 different growth-periods of cotton. The experiments’ results validate that after the optimal spray parameters were applied at different growth periods respectively, the average optimum index in 3 growth periods was 42.29%, which was increased up to 62.24% than the operations without distinguishing growth periods.

[1]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[2]  Hai Tao,et al.  Review of deep convolution neural network in image classification , 2017, 2017 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET).

[3]  V. A. Gulhane Dr. A. A. Gurjar,et al.  Detection of Diseases on Cotton Leaves and its Possible Diagnosis , 2011 .

[4]  A. K. Misra,et al.  Detection of plant leaf diseases using image segmentation and soft computing techniques , 2017 .

[5]  Tomàs Pallejà,et al.  Real time canopy density estimation using ultrasonic envelope signals in the orchard and vineyard , 2015, Comput. Electron. Agric..

[6]  S. Askew,et al.  Cotton (Gossypium hirsutum) and Weed Response to Flumioxazin Applied Preplant and Postemergence Directed1 , 2002, Weed Technology.

[7]  Hui Liu,et al.  Comparison of Sick and Hokuyo UTM-30LX laser sensors in canopy detection for variable-rate sprayer , 2018 .

[8]  Tristan Perez,et al.  Mixtures of Lightweight Deep Convolutional Neural Networks: Applied to Agricultural Robotics , 2017, IEEE Robotics and Automation Letters.

[9]  José Carlos Martínez-Patiño,et al.  Optimization of ultrasound-assisted extraction of biomass from olive trees using response surface methodology. , 2019, Ultrasonics sonochemistry.

[10]  Saeid Minaei,et al.  Ultrasonic sensing of pistachio canopy for low-volume precision spraying , 2015, Comput. Electron. Agric..

[11]  N. Iqbal,et al.  Weed control through allelopathic crop water extracts and S-metolachlor in cotton , 2020 .

[12]  Henrik Skov Midtiby,et al.  Plant species classification using deep convolutional neural network , 2016 .

[13]  Hui Liu,et al.  EVALUATION OF A LASER SCANNING SENSOR IN DETECTION OF COMPLEX-SHAPED TARGETS FOR VARIABLE-RATE SPRAYER DEVELOPMENT , 2016 .

[14]  Yadong Liu,et al.  Computer vision technology in agricultural automation —A review , 2020 .

[15]  Alsayed Algergawy,et al.  A Deep Learning-based Approach for Banana Leaf Diseases Classification , 2017, BTW.

[16]  A. Akram,et al.  Combined application of Artificial Neural Networks and life cycle assessment in lentil farming in Iran , 2017 .

[17]  Jianlong Dai,et al.  Intensive cotton farming technologies in China: Achievements, challenges and countermeasures ☆ , 2014 .

[18]  Tony E Grift,et al.  Geometry-based mass grading of mango fruits using image processing. , 2017 .

[19]  Z. Sawan,et al.  Climatic variables: Evaporation, sunshine, relative humidity, soil and air temperature and its adverse effects on cotton production , 2017 .

[20]  Avinash C. Tyagi,et al.  Towards a Second Green Revolution , 2016 .

[21]  H. E. Ozkan,et al.  Development of a Variable-Rate Sprayer with Laser Scanning Sensor to Synchronize Spray Outputs to Tree Structures , 2012 .

[22]  Gonzalo Pajares,et al.  Automatic detection of curved and straight crop rows from images in maize fields , 2017 .

[23]  Hossein Pourghassem,et al.  Computer vision-based apple grading for golden delicious apples based on surface features , 2017 .

[24]  Tomàs Pallejà,et al.  Real time canopy density validation using ultrasonic envelope signals and point quadrat analysis , 2017, Comput. Electron. Agric..