WOS Indexed (2023)
clarivate analytics

AMA, Agricultural Mechanization in Asia, Africa and Latin America

AMA, Agricultural Mechanization in Asia, Africa and Latin America (AMA) (issn: 00845841) is a peer reviewed journal first published online after indexing scopus in 1982. AMA is published by Farm Machinery Industrial Research Corp and Shin-Norinsha Co. AMA publishes every subjects of general engineering and agricultural engineering. Azerbaijan Medical Journal Gongcheng Kexue Yu Jishu/Advanced Engineering Science Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery Interventional Pulmonology Zhenkong Kexue yu Jishu Xuebao/Journal of Vacuum Science and Technology Wuhan Ligong Daxue Xuebao (Jiaotong Kexue Yu Gongcheng Ban)/Journal of Wuhan University of Technology (Transportation Science and Engineering) Zhonghua yi shi za zhi (Beijing, China : 1980)

Submission Deadline
29 Mar 2023 (Vol - 54 , Issue- 04 )
Upcoming Publication
31 Mar 2023 (Vol - 54 , Issue 03 )

Aim and Scope :

AMA, Agricultural Mechanization in Asia, Africa and Latin America

AMA, Agricultural Mechanization in Asia, Africa and Latin America (ISSN: 00845841) is a peer-reviewed journal. The journal covers Agricultural and Biological Sciences and all sort of engineering topic. the journal's scopes are in the following fields but not limited to:

Agricultural and Biological Sciences
Electrical Engineering and Telecommunication
Electronic Engineering
Computer Science & Engineering
Civil and architectural engineering
Mechanical and Materials Engineering

Method to Recognize Litchi Fruit by Improved YOLOv3

Paper ID- AMA-20-12-2021-10970

High-accuracy recognition of litchi fruits is the key to yield estimation. To solve the problem of low detection rates of dense, small targets in orchard scenes, this paper proposes an improved YOLOv3 method for litchi fruit recognition. The litchi fruit target anchor frames in the dataset are re-clustered to obtain nine predefined anchor frames. The prediction scale of the network is adjusted, a 160 × 160 feature prediction scale is added to improve the detection of small targets, and the feature prediction scale for large-target detection in YOLOv3 is removed to simplify the network model. A dense connection module is added to the feature-extraction network to enhance the feature propagation capability and improve network performance. To train and test the litchi fruit dataset, immature (young fruit and expansion stage) and mature stages were constructed in an orchard scene, and 227018 labels were generated using LabelImg software. The F1 score and mean accuracy precision (mAP) were used to evaluate the network model, and the proposed method was experimentally compared with YOLOv3 for litchi images. The experiments showed that the recognition effect was significantly improved using the proposed model, with F1 and mAP of 0.851 and 88.9%, respectively, on the full dataset, which are better than YOLOv3 by 0.238 and 31.1 percentage points, respectively. Therefore, the method has a good effect for dense litchi fruit recognition in orchard scenarios and provides technical support for litchi yield estimation.

Design and field experiment of self-propelled Chinese little greens harvester

Paper ID- AMA-20-12-2021-10968

Aiming at the problems of difficult harvesting, low efficiency and high labor intensity of Chinese little greens, a self-propelled Chinese little greens harvester is designed. The bidirectional electric drive reciprocating cutter device is adopted to effectively improve the cutting efficiency and cutting quality. The motion cutting diagram of double-action cutter under different cutting speed ratio is drawn, which shows that the best cutting speed ratio to reduce the area of heavy cutting area and missing cutting area is k = 1.7, which could effectively reduce the phenomenon of heavy cutting and missing cutting. The inclined vertical flexible and orderly clamping conveying device is adopted to control the conveying speed at 1.2 ~ 1.5 times of the walking speed of machine to ensure the smooth conveying process and avoid congestion. The angle between the conveyor and the horizontal ground is controlled at 10 ° ~ 20 °. The field experiment shows that the performance of the harvest is good. The average time of harvesting Chinese little greens per 100 m2 is 57.17 seconds and the average loss rate is 6.475%. The research results could provide reference and theoretical basis for the development of other leafy vegetable harvesting machinery technology.

Path tracking and obstacle avoidance planning of tracked robot based on model predictive control

Paper ID- AMA-19-12-2021-10967

In order to ensure the stable and safe driving of tracked robots in complex farmland environment, this paper proposes a path tracking and obstacle avoidance planning method for tracked robots based on model predictive control. According to the kinematics analysis method, the kinematic model in the form of state equation of the tracked robot is established. Considering the influence of the unavoidable system uncertainty and external disturbance on path tracking accuracy, the path tracking control layer based on MPC theory is designed with control input as constraint. Then, the point-mass model is used to describe the movement of the tracked robot in the work area, so as to reduce the amount of calculation in the path re-planning layer. The obstacle avoidance function is selected according to the proportion of penalty function and the velocity of tracked robot. The complete MPC controller for path tracking and obstacle avoidance planning of tracked robot is established through the combination of path tracking control layer and path re-planning layer. The final results and analysis show that the method proposed in this paper can achieve smooth avoidance of obstacles and improve the path tracking control accuracy of tracked robots.

Uneven illumination enhancement method of straw mushroom image in mushroom house

Paper ID- AMA-19-12-2021-10966

The growth monitoring of edible mushroom based on machine vision is an important part of the production and management of industrial edible mushroom. In order to solve the problem of serious uneven illumination of straw mushroom image in closed and no light straw mushroom room environment, this paper establishes the gray level calculation formula of mushroom bed image under multiple LED light sources, and construct a reasonable mask background image used to enhance the straw mushroom image. The processed image result showed the average, deviation and range of gray scale of mushroom image decreased by 58.2%, 65.81% and 45.28% respectively, the mean, deviation and range of background gray decreased by 97.8 %, 81.69 % and 61.02 % respectively. Compared with Multi-Scale Retinex and Homomorphic Filtering, the algorithm in this paper performs better in concentrating of gray distribution and increasing the image gray level difference of straw mushroom and culture material, which is helpful for the subsequent segmentation and recognition of the mushroom image.

Rice Lodging Analyse Based on Gray Level Co-occurrence Matrix

Paper ID- AMA-16-12-2021-10964

Rice lodging refers to the phenomenon that rice crops growing upright are skewed and even the whole plant falls to the ground due to the influence of external forces. When the paddy field that has fallen down is harvested mechanically, it is necessary to adjust the harvesting direction, the height of the header and other factors according to the specific lodging situation. In the rice field image taken from the driving perspective of the harvester, the texture feature of the rice field image in the harvest area will rise or fall rapidly and shake greatly due to the lodging of part of the rice. In this paper, the gray level co-occurrence matrix analysis method and MATLAB simulation tools are used to analyze the texture characteristics of the four main factors of Angular Second Moment, Correlation, Inverse Different Moment and Contrast in the image of the area to be harvested from the driving perspective of the harvester. It provides a basis for determining the texture feature parameter criterion when using the neural network to detect the lodging situation of rice.