阅读说明：本技术 一种ai应用于农作物倒伏检测的方法 (Method for detecting lodging of crops by AI ) 是由 朱亮 韩民乐 于 2021-08-06 设计创作，主要内容包括：本发明公开了一种AI应用于农作物倒伏检测的方法,包括以下步骤：S1、收割前的准备工作：S11、将收割机移动至农田边；S12、判断收割机行进路线是否准确,若收割机行进路线准确,则完成对收割机位置的调整,转至S14,S13、若收割机行进路线不准确,调整收割机的位置,再调整收割机的朝向,转至S12。本发明中,在实际收割时,可以对农作物的状态进行实时的检测,从而给控制端反馈控制信息,并且使用AI可以的满足对不同地区农作物的倒伏的不同状态进行检测,具有更好的泛化性,通过AI方案对农作物倒伏进行检测,从而给控制端信息来控制收割机割台的高度,进而可以实现更高效的进行农作物收割的功能。(The invention discloses a method for detecting lodging of crops by AI, comprising the following steps: s1, preparation before harvesting: s11, moving the harvester to the side of a farmland; s12, judging whether the advancing route of the harvester is accurate, if the advancing route of the harvester is accurate, adjusting the position of the harvester, turning to S14 and S13, if the advancing route of the harvester is inaccurate, adjusting the position of the harvester, adjusting the orientation of the harvester, and turning to S12. According to the invention, during actual harvesting, the state of crops can be detected in real time, so that control information is fed back to the control end, the AI can be used for detecting different lodging states of the crops in different regions, the better generalization performance is achieved, the lodging of the crops is detected through the AI scheme, so that the height of the header of the harvester is controlled through the information of the control end, and the function of more efficiently harvesting the crops can be realized.)

1. A method for detecting lodging of crops by AI is characterized in that: the method comprises the following steps:

s1, preparation before harvesting:

s11, moving the harvester to the side of a farmland;

s12, judging whether the advancing route of the harvester is accurate, if so, completing the adjustment of the position of the harvester, and turning to S14;

s13, if the advancing route of the harvester is not accurate, adjusting the position of the harvester, adjusting the orientation of the harvester, and turning to S12;

s14, installing a camera at the front end of glass in the cab, shooting a current picture by using the camera, and transmitting the picture to a display module:

s15, judging whether the camera position is accurately installed, if the camera position is properly installed, automatically recording the current position of the camera, recording the current position as an initial position, completing the adjustment of the camera position, and turning to S2;

s16, if the position is not accurately installed, adjusting the position of the camera, adjusting the angle of the camera, and turning to S15;

s2, normal harvesting stage:

s21, reading data in real time by the camera, processing the video data by the preprocessing module, importing the processed data into a detection/segmentation model, and reasoning the data by the detection/segmentation model;

s21, judging whether the inference times are more than n times, if so, turning to S22, and if not, turning to S23;

s22, whether the inference result needs to be displayed or not, if the inference result needs to be displayed, turning to S23, judging whether the operation exists within T seconds or not, if the operation exists, turning to S23, if the operation does not exist within T seconds, controlling a signal transmission controller, and turning to S24;

s23, transmitting the inference result to the display module, judging whether to transmit the data, if so, turning to S24, if not, turning to S3, and after the adjustment is finished, turning to S24;

s24, inputting the inference result into a control end, the control end carries out lifting or descending operation on the header according to the received signal,

s3, adjusting:

s31, detecting a lodging area;

s32, adjusting the angle of the camera, and judging whether the lodging area can be still detected;

s32, if the lodging region can still be detected, turning to S32, and if the lodging region cannot be detected, determining the lodging area;

s33, judging whether the lodging area is larger than P square meters or not, if so, adjusting the advancing route of the harvester, and if not, not adjusting the advancing route of the harvester and restoring the camera to the initial position;

s4, harvesting the lodging area, judging whether the lodging degree of crops needs manual supporting, if so, turning to S5 after manual supporting, and if not, directly turning to S5;

and S5, determining the lodging direction of the crop, adjusting the position of the harvester according to the lodging direction, and starting harvesting the lodging area.

2. The method for detecting lodging of crops by AI according to claim 1, wherein: the step S21 can be modified according to actual conditions.

3. The method for detecting lodging of crops by AI according to claim 1, wherein: t in the step S22 can be changed according to actual conditions.

4. The method for detecting lodging of crops by AI according to claim 1, wherein: p in the step S33 can be changed according to actual conditions.

5. The method for detecting lodging of crops by AI according to claim 1, wherein: the judgment in the step S4 as to whether or not manual assistance is needed may be performed by the pictures displayed by the display module, or may be performed manually after the situation is known on site.

6. The method for detecting lodging of crops by AI according to claim 1, wherein: the crop lodging direction in the step S5 is based on the majority of crop lodging directions.

7. The method for detecting lodging of crops by AI according to claim 1, wherein: the data model in said step S21 adds header areas.

8. The method for detecting lodging of crops by AI according to claim 1, wherein: the data processing mode in step S21 processes the data using both detection and segmentation.

Technical Field

The invention relates to the technical field of AI, in particular to a method for applying AI to crop lodging detection.

Background

Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence, a field of research that includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. Since the birth of artificial intelligence, theories and technologies become mature day by day, and application fields are expanded continuously, so that science and technology products brought by the artificial intelligence in the future can be assumed to be 'containers' of human intelligence. The artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is not human intelligence, but can think like a human, and can also exceed human intelligence.

At present, the development of agricultural technology is different day by day, the application popularity of large-scale agricultural harvesters is very high, when agricultural crops are harvested, due to the influence of weather factors, the phenomena such as lodging and the like occur when the crops are mature, no matter the operation is carried out by a driver or a professional driver, the height of the header needs to be controlled in real time, the quality of the harvested crops is prevented from being reduced, and the great energy of the driver is consumed, so that a method for applying AI (artificial intelligence) to crop lodging detection is provided, and the problems are solved.

Disclosure of Invention

The invention aims to provide a method for detecting lodging of crops by AI, so as to solve the problems in the background technology.

In order to achieve the purpose, the invention provides the following technical scheme: a method for detecting lodging of crops by AI comprises the following steps:

s1, preparation before harvesting:

s11, moving the harvester to the side of a farmland;

s12, judging whether the advancing route of the harvester is accurate, if so, completing the adjustment of the position of the harvester, and turning to S14;

s13, if the advancing route of the harvester is not accurate, adjusting the position of the harvester, adjusting the orientation of the harvester, and turning to S12;

s14, installing a camera at the front end of glass in the cab, shooting a current picture by using the camera, and transmitting the picture to a display module:

s15, judging whether the camera position is accurately installed, if the camera position is properly installed, automatically recording the current position of the camera, recording the current position as an initial position, completing the adjustment of the camera position, and turning to S2;

s16, if the position is not accurately installed, adjusting the position of the camera, adjusting the angle of the camera, and turning to S15;

s2, normal harvesting stage:

s21, reading data in real time by the camera, processing the video data by the preprocessing module, importing the processed data into a detection/segmentation model, and reasoning the data by the detection/segmentation model;

s21, judging whether the inference times are more than n times, if so, turning to S22, and if not, turning to S23;

s22, whether the inference result needs to be displayed or not, if the inference result needs to be displayed, turning to S23, judging whether the operation exists within T seconds or not, if the operation exists, turning to S23, if the operation does not exist within T seconds, controlling a signal transmission controller, and turning to S24;

s23, transmitting the inference result to the display module, judging whether to transmit the data, if so, turning to S24, if not, turning to S3, and after the adjustment is finished, turning to S24;

s24, inputting the inference result into a control end, the control end carries out lifting or descending operation on the header according to the received signal,

s3, adjusting:

s31, detecting a lodging area;

s32, adjusting the angle of the camera, and judging whether the lodging area can be still detected;

s32, if the lodging region can still be detected, turning to S32, and if the lodging region cannot be detected, determining the lodging area;

s33, judging whether the lodging area is larger than P square meters or not, if so, adjusting the advancing route of the harvester, and if not, not adjusting the advancing route of the harvester and restoring the camera to the initial position;

s4, harvesting the lodging area, judging whether the lodging degree of crops needs manual supporting, if so, turning to S5 after manual supporting, and if not, directly turning to S5;

and S5, determining the lodging direction of the crop, adjusting the position of the harvester according to the lodging direction, and starting harvesting the lodging area.

Preferably, n in the step S21 may be changed according to actual situations.

Preferably, T in step S22 may be changed according to actual situations.

Preferably, P in step S33 may be modified according to actual situations.

Preferably, the judgment in step S4 as to whether or not manual assistance is needed may be performed by a picture displayed by the display module, or may be performed after the situation is known manually on site.

Preferably, the crop lodging direction in the step S5 is based on a majority of crop lodging directions.

Preferably, the header area is added to the data model in step S21, which has the advantage of taking the header as a fixed reference object to thereby cut the header into an effective range, thereby improving the inference efficiency of the model and reducing the interference in the actual working scene.

Preferably, the data processing mode in step S21 processes the data by using both detection and division.

Compared with the prior art, the invention has the beneficial effects that:

1. in the invention, the state of the crops can be detected in real time, so that control information is fed back to the control end;

2. in the invention, the AI can be used for detecting different lodging states of crops in different areas, so that the method has better generalization;

3. according to the invention, the crop lodging is detected through the AI scheme, so that the height of the header of the harvester is controlled by giving information to the control end, and the function of harvesting crops more efficiently can be realized.

According to the invention, during actual harvesting, the state of crops can be detected in real time, so that control information is fed back to the control end, the AI can be used for detecting different lodging states of the crops in different regions, the better generalization performance is achieved, the lodging of the crops is detected through the AI scheme, so that the height of the header of the harvester is controlled through the information of the control end, and the function of more efficiently harvesting the crops can be realized.

Drawings

FIG. 1 is a flow chart of the present invention for adjusting the position of a harvester;

FIG. 2 is a flow chart of adjusting the position of a camera according to the present invention;

FIG. 3 is a flow chart of the present invention for controlling the height of a header of a harvester;

FIG. 4 is a flow chart of detecting the area of a lodging region in the present invention;

FIG. 5 is a flow chart of determining the degree of lodging in the present invention;

FIG. 6 is a schematic view of the field of view of the camera of the present invention;

FIG. 7 is a diagram of a marked image from the perspective of a camera according to the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "connected," and the like are to be construed broadly, such as "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

Example one

Referring to fig. 1 to 7, an embodiment of the present invention includes: a method for detecting lodging of crops by AI comprises the following steps:

s1, preparation before harvesting:

s11, moving the harvester to the side of a farmland;

s12, judging whether the advancing route of the harvester is accurate, if so, completing the adjustment of the position of the harvester, and turning to S14;

s13, if the advancing route of the harvester is not accurate, adjusting the position of the harvester, adjusting the orientation of the harvester, and turning to S12;

s14, installing a camera at the front end of glass in the cab, shooting a current picture by using the camera, and transmitting the picture to a display module:

s15, judging whether the camera position is accurately installed, if the camera position is properly installed, automatically recording the current position of the camera, recording the current position as an initial position, completing the adjustment of the camera position, and turning to S2;

s16, if the position is not accurately installed, adjusting the position of the camera, adjusting the angle of the camera, and turning to S15;

s2, normal harvesting stage:

s21, reading data in real time by the camera, processing the video data by the preprocessing module, importing the processed data into a detection/segmentation model, and reasoning the data by the detection/segmentation model;

s21, judging whether the inference times are more than n times, if so, turning to S22, and if not, turning to S23;

s22, whether the inference result needs to be displayed or not, if the inference result needs to be displayed, turning to S23, judging whether the operation exists within T seconds or not, if the operation exists, turning to S23, if the operation does not exist within T seconds, controlling a signal transmission controller, and turning to S24;

s23, transmitting the inference result to the display module, judging whether to transmit the data, if so, turning to S24, if not, turning to S3, and after the adjustment is finished, turning to S24;

s24, inputting the inference result into a control end, the control end carries out lifting or descending operation on the header according to the received signal,

s3, adjusting:

s31, detecting a lodging area;

s32, adjusting the angle of the camera, and judging whether the lodging area can be still detected;

s32, if the lodging region can still be detected, turning to S32, and if the lodging region cannot be detected, determining the lodging area;

s33, judging whether the lodging area is larger than P square meters or not, if so, adjusting the advancing route of the harvester, and if not, not adjusting the advancing route of the harvester and restoring the camera to the initial position;

s4, harvesting the lodging area, judging whether the lodging degree of crops needs manual supporting, if so, turning to S5 after manual supporting, and if not, directly turning to S5;

and S5, determining the lodging direction of the crop, adjusting the position of the harvester according to the lodging direction, and starting harvesting the lodging area.

Example two

Referring to fig. 1 to 7, an embodiment of the present invention includes: a method for detecting lodging of crops by AI comprises the following steps:

s1, preparation before harvesting:

s11, moving the harvester to the side of a farmland;

s12, judging whether the advancing route of the harvester is accurate, if so, completing the adjustment of the position of the harvester, and turning to S14;

s13, if the advancing route of the harvester is not accurate, adjusting the position of the harvester, adjusting the orientation of the harvester, and turning to S12;

s14, installing a camera at the front end of glass in the cab, shooting a current picture by using the camera, and transmitting the picture to a display module:

s15, judging whether the camera position is accurately installed, if the camera position is properly installed, automatically recording the current position of the camera, recording the current position as an initial position, completing the adjustment of the camera position, and turning to S2;

s16, if the position is not accurately installed, adjusting the position of the camera, adjusting the angle of the camera, and turning to S15;

s2, normal harvesting stage:

s21, the camera reads data in real time, the preprocessing module processes the video data, the processed data are led into a detection/segmentation model, the detection/segmentation model infers the data, the data model adds a header area, and the method has the advantages that the header is used as a fixed reference object so as to obtain an effective range for header harvesting, so that the inference efficiency of the model is improved, the interference in an actual working scene is reduced, and the data processing mode processes the data in two modes of detection and segmentation;

s21, judging whether the inference times is more than n times, if so, turning to S22, and if not, turning to S23, wherein n can be changed according to the actual situation;

s22, whether the inference result needs to be displayed or not, if the inference result needs to be displayed, turning to S23, judging whether an operation exists within T seconds or not, if the operation exists, turning to S23, if the operation does not exist within T seconds, changing T according to the actual situation, controlling a signal transmission controller, and turning to S24;

s23, transmitting the inference result to the display module, judging whether to transmit the data, if so, turning to S24, if not, turning to S3, and after the adjustment is finished, turning to S24;

s24, inputting the inference result into a control end, the control end carries out lifting or descending operation on the header according to the received signal,

s3, adjusting:

s31, detecting a lodging area;

s32, adjusting the angle of the camera, and judging whether the lodging area can be still detected;

s32, if the lodging region can still be detected, turning to S32, and if the lodging region cannot be detected, determining the lodging area;

s33, judging whether the lodging area is larger than P square meters or not, if so, adjusting the advancing route of the harvester, if not, not adjusting the advancing route of the harvester, and if not, changing P according to the actual condition to restore the camera to the initial position;

s4, harvesting the lodging area, judging the lodging degree of crops, judging whether manual supporting is needed, judging through pictures displayed by a display module, or judging after understanding the situation on site manually, if manual supporting is needed, turning to S5, and if manual supporting is not needed, directly turning to S5;

and S5, determining the lodging direction of the crops, wherein the lodging direction of the crops is based on the lodging direction of most crops, and adjusting the position of the harvester according to the lodging direction to harvest the lodging area.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.