Sugarcane Stem Node Recognition in Field by Deep Learning Combining Data Expansion

The rapid and accurate identification of sugarcane stem nodes in the complex natural environment is essential for the development of intelligent sugarcane harvesters. However, traditional sugarcane stem node recognition has been mainly based on image processing and recognition technology, where the recognition accuracy is low in a complex natural environment. In this paper, an object detection algorithm based on deep learning was proposed for sugarcane stem node recognition in a complex natural environment, and the robustness and generalisation ability of the algorithm were improved by the dataset expansion method to simulate different illumination conditions. The impact of the data expansion and lighting condition in different time periods on the results of sugarcane stem nodes detection was discussed, and the superiority of YOLO v4, which performed best in the experiment, was verified by comparing it with four different deep learning algorithms, namely Faster R-CNN, SSD300, RetinaNet and YOLO v3. The comparison results showed that the AP (average precision) of the sugarcane stem nodes detected by YOLO v4 was 95.17%, which was higher than that of the other four algorithms (78.87%, 88.98%, 90.88% and 92.69%, respectively). Meanwhile, the detection speed of the YOLO v4 method was 69 f/s and exceeded the requirement of a real-time detection speed of 30 f/s. The research shows that it is a feasible method for real-time detection of sugarcane stem nodes in a complex natural environment. This research provides visual technical support for the development of intelligent sugarcane harvesters.

Impact of N-fixing bacterium Nitrospirillum amazonense on quality and quantitative parameters of sugarcane under field condition

Sugarcane is the world’s largest crop by production quantity. In Brazil, the sugarcane cultivation requires 30-70% less nitrogen than in other countries, due to the biological nitrogen fixation. Nitrospirillum amazonense is an N-fixing bacterium that has proven to increase plant growth and yields of sugarcane in greenhouse experiments. However, studies on field conditions are very scarce. For these reasons, this study aimed to assess the impact of different doses of a pre-commercial product, Aprinza®, containing N. amazonense on quality and quantitative parameters of the cultivar RB867515 in field conditions. The plant height, number of internodes, stem yield and sugar yield were measured. The leaf nutrient content was analyzed 60, 90 and 180 days after planting and the plant nutrient content was analyzed after harvest. The inoculation of N. amazonense did not affect the leaf and the stem nutrient content positively. The stem yield was increased 27.5 tons ha-1 (20%) and the total recoverable sugar yield increased 4.6 tons ha-1 (25%), compared to the control, by using 1 liter of Aprinza® per hectare. Therefore, N. amazonense can increase sugarcane stem and sugar yields in sandy soils with low nitrogen application, reducing the environmental impacts of the sugarcane cultivation system.

Yield and biometry of fertilized sugar cane with organomineral fertilizer of sewage sludge and biostimulant

The dependence of mineral fertilizers, increasingly, has brought concern facing the increased demand and because it is a non-renewable mineral resource. The organic fertilization, exclusively, it is impractical in large scale, however, the combination of organic and mineral sources have already proved to be feasible, both from the point of view of nutrition of plants as well as in the aspect of recycling of urban and industrial waste by agriculture. This research had as objective to determine the efficiency of aorganomineral fertilizer formulated on the basis of sewage sludge in substitution of mineral fertilizer in the cultivation of sugar cane in environments with different levels of soil fertility. An experiment was conducted in greater soil fertility, in the Institute Federal Goiano– Campus, Morrinhos-GO, Brazil. The other, less soil fertility, was implanted in the ethanol industry Tijuco Valley, located in Rio do Peixe, district of Prata-MG, Brazil. The experimental design was randomized blocks in a factorial 5 x 2 +1 being five doses, with and without a biostimulant plus an additional with mineral fertilization, in four replications. The doses were in function of fertilization recommendation of planting and coverage for each environment, consisting of: 100 % of the mineral source and percentage 0; 60; 80; 100 and 120 % of organomineral fertilizer. We evaluated the productivity, tillering, diameter and height of stem in Prata-MG the different percentages of the fertilization of planting favored and increased productivity, height and stem diameter of sugar cane; the use of biostimulants not contributed to increase crop yield. In Morrinhos-GO, the different percentage of planting fertilization did not increase the productivity, tillering, height and diameter of the sugarcane stem; the use of biostimulants increases the productivity yield of sugarcane. Organomineral fertilizer based on biosolids is similar to fertilization with mineral fertilizer in environments.

Influence of Carbon - Nitrogen Supplements and pH on Growth of Sugarcane Stem rot Pathogen Fusarium Solani NVS671

Fusarium solani NVS671 identified from infected sugarcane stem of Co 671 as a new pathogen was subjected to various cultural conditions to understand its physiological profile. In continuation with our previous work, cultural analysis was carried out under in vitro condition by supplementing various carbon and nitrogen sources in Czapek-Dox agar (CDA). Under different hydrogen ion concentrations, it was found that the growth of Fusarium solaniNVS671 was less at pH 4 and pH 10 and could reach up to 5 cm after 7 days of incubation on Potato Dextrose Agar (PDA). It is observed that the pH around 7 to 8 was optimum for the growth of F. solani. Ten different nitrogenous (N) sources and nine different carbon sources were tested on CDA medium to know their effect on the mycelial growth rate and characteristics of the fungus. Among the N sources evaluated, ammonium chloride (7.96±0.11 cm) was found to be most efficient for mycelial growth promotion followed by ammonium nitrate (7.7±0.1 cm) and ammonium sulphate (7.3±0.1 cm). The most preferred carbon source recorded to promote best radial mycelial growth was starch (7.96±0.05 cm) and sucrose (7.93±0.05 cm). Capabilities of using different carbon and nitrogen sources and ability to grow at different pH levels may allow species to adapt to specific soil conditions.This study is important to understand the physiology and metabolite preference of F. solani.

Sugarcane stem nodes based on the maximum value points of the vertical projection function

ABSTRACT: In order to solve the problem that the stem nodes are difficult to identify in the process of sugarcane seed automatic cutting, a method of identifying the stem nodes of sugarcane based on the extreme points of vertical projection function is proposed in this paper. Firstly, in order to reduce the influence of light on image processing, the RGB color image is converted to HSI color image, and the S component image of the HSI color space is extracted as a research object. Then, the S component image is binarized by the Otsu method, the hole of the binary image is filled by morphology closing algorithm, and the sugarcane and the background are initially separated by the horizontal projection map of the binary image. Finally, the position of sugarcane stem is preliminarily determined by continuously taking the derivative of the vertical projection function of the binary image, and the sum of the local pixel value of the suspicious pixel column is compared to further determine the sugarcane stem node. The experimental results showed that the recognition rate of single stem node is 100%, and the standard deviation is less than 1.1 mm. The accuracy of simultaneous identification of double stem nodes is 98%, and the standard deviation is less than 1.7 mm. The accuracy of simultaneous identification of the three stem nodes is 95%, and the standard deviation is less than 2.2 mm. Compared with the other methods introduced in this paper, the proposed method has higher recognition and accuracy.