CN115509228A

CN115509228A - Target detection-based agricultural machinery obstacle avoidance method and device, agricultural machinery and storage medium

Info

Publication number: CN115509228A
Application number: CN202211179272.3A
Authority: CN
Inventors: 杨保健; 闫政; 曹云龙; 董中民
Original assignee: Wuyi University
Current assignee: Wuyi University
Priority date: 2022-09-27
Filing date: 2022-09-27
Publication date: 2022-12-23

Abstract

The invention provides an agricultural machinery obstacle avoidance method, an agricultural machinery obstacle avoidance device, an agricultural machinery and a storage medium based on target detection, wherein the method comprises the following steps: performing operation and controlling a camera to acquire a target image according to pre-planned initial path information; then, identifying a working area from the target image, and determining a target detection area according to the path area and the working area; then, performing target detection in a target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified, identifying a target obstacle avoidance object, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in a target image based on the preset obstacle avoidance algorithm; and controlling the driving device to avoid the obstacle according to the obstacle avoidance path information. According to the technical scheme of the embodiment, the interference of the operation equipment of the agricultural machinery on the target detection can be eliminated, the interference of crops can be eliminated according to the identification of the object to be identified, and the planning efficiency and the accuracy of the obstacle avoidance path of the agricultural machinery can be effectively improved.

Description

Agricultural machine obstacle avoidance method and device based on target detection, agricultural machine and storage medium

Technical Field

The invention belongs to the technical field of artificial intelligence, and particularly relates to an agricultural machinery obstacle avoidance method and device based on target detection, an agricultural machinery and a storage medium.

Background

With the development of information technology, the agricultural machinery intelligent navigation technology receives more and more attention, and the key technology for ensuring the operation safety and improving the operation efficiency, which is different from the traditional automatic navigation, becomes the agricultural machinery intelligent navigation. The common automatic navigation key technology of the agricultural machine comprises positioning and attitude measurement, path planning and motion control, but is different from the common automobile navigation, the operation environment of the agricultural machine is complex, such as a rice harvester, the operation environment is a farmland planted with crops and is not a recognizable open road, the obstacle avoidance is carried out through simple target detection, the obstacle avoidance is easily interfered by the crops and the operation equipment of the agricultural machine, and the obstacle avoidance efficiency of the agricultural machine is not high.

Disclosure of Invention

The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

The embodiment of the invention provides an agricultural machine obstacle avoidance method and device based on target detection, an agricultural machine and a storage medium, and the obstacle avoidance capability of the agricultural machine can be improved.

In a first aspect, an embodiment of the present invention provides an agricultural machinery obstacle avoidance method based on target detection, which is applied to a target agricultural machinery, where the target agricultural machinery includes a camera, a working device, and a driving device, and the method includes:

acquiring pre-planned initial path information, controlling the driving device to operate according to the initial path information, and starting the operation equipment to operate;

controlling the camera to collect a target image according to the initial path information, wherein the target image comprises a path area corresponding to a running path of the target agricultural machine;

identifying a working area from the target image, wherein the working area is an area where the working equipment is located in the target image;

determining a target detection area according to the path area and the operation area, wherein the target detection area and the operation area are not overlapped with each other;

performing target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified;

identifying a target obstacle avoidance object from the objects to be identified, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm;

and controlling the driving device to avoid the obstacle according to the obstacle avoiding path information.

In some embodiments, said identifying a job region from said target image comprises:

determining the equipment type of the target agricultural machine, and determining a reference image of the operation equipment according to the equipment type;

and identifying the working area from the target image according to the reference image.

In some embodiments, the identifying a target obstacle avoidance object from the objects to be identified includes:

extracting the features of the object to be recognized to obtain the features to be recognized;

determining the object type of the object to be identified according to the feature to be identified and a preset reference feature;

and determining the object to be identified with the object type as a target obstacle avoidance object.

In some embodiments, the determining, based on a preset obstacle avoidance algorithm, obstacle avoidance path information according to a position of the target obstacle avoidance object in the target image includes:

determining at least one selectable obstacle avoidance path according to the obstacle avoidance algorithm and the position of the target obstacle avoidance object in the target image;

determining a target obstacle avoidance path from at least one selectable obstacle avoidance path according to a preset rule;

and determining the obstacle avoidance path information according to the target obstacle avoidance path.

In some embodiments, the target agricultural machine further comprises a distance sensor, and the determining the obstacle avoidance path information according to the target obstacle avoidance path comprises:

controlling the distance sensor to carry out distance detection based on the position of the target obstacle object in the target image to obtain a target distance between the target agricultural machinery and the target obstacle object;

determining a scale of the target image according to the target distance, and determining the path length of the target obstacle avoidance path according to the scale;

and determining the obstacle avoidance path information according to the target obstacle avoidance path and the path length.

In some embodiments, the target agricultural machine is further configured with a GNSS, and the determining a target obstacle avoidance path from at least one of the alternative obstacle avoidance paths according to a preset rule includes:

determining a turning smoothness for each of the alternative obstacle avoidance paths from the GNSS;

and determining the target obstacle avoidance path from the selectable obstacle avoidance paths according to the preset rule and the turning smoothness.

In some embodiments, the controlling the driving device to avoid the obstacle according to the obstacle avoidance path information includes:

determining the moving pose information of the target agricultural machine on the target obstacle avoidance path according to the GNSS;

and controlling the driving device to avoid the obstacle according to the moving pose information and the obstacle avoiding path information.

In a second aspect, an embodiment of the present invention provides an agricultural machinery obstacle avoidance device based on target detection, including:

the starting unit is used for acquiring pre-planned initial path information, controlling the driving device to operate according to the initial path information and starting the operation equipment to operate;

the image acquisition unit is used for controlling the camera to acquire a target image according to the initial path information, wherein the target image comprises a path area corresponding to the running path of the target agricultural machine;

a working area identification unit, configured to identify a working area from the target image, where the working area is located in the target image;

a detection area determination unit configured to determine a target detection area according to the path area and the work area, wherein the target detection area and the work area do not overlap with each other;

the target detection unit is used for carrying out target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified;

the path planning unit is used for identifying a target obstacle avoidance object from the object to be identified, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm;

and the obstacle avoidance unit is used for controlling the driving device to avoid obstacles according to the obstacle avoidance path information.

In a third aspect, an embodiment of the present invention provides an agricultural machine, including: the present invention relates to a method for avoiding obstacles of an agricultural machine based on object detection, and more particularly, to a method for avoiding obstacles of an agricultural machine based on object detection.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, where the computer program is configured to execute the method for avoiding obstacles for an agricultural machine based on object detection according to the first aspect.

The embodiment of the invention comprises the following steps: acquiring pre-planned initial path information, controlling the driving device to operate according to the initial path information, and starting the operation equipment to operate; controlling the camera to collect a target image according to the initial path information, wherein the target image comprises a path area corresponding to a running path of the target agricultural machine; identifying a working area from the target image, wherein the working area is an area where the working equipment is located in the target image; determining a target detection area according to the path area and the operation area, wherein the target detection area and the operation area are not overlapped with each other; performing target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified; identifying a target obstacle avoidance object from the objects to be identified, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm; and controlling the driving device to avoid the obstacle according to the obstacle avoiding path information. According to the technical scheme of the embodiment, the interference of the operation equipment of the agricultural machine on the target detection can be eliminated, the interference of crops can be eliminated according to the identification of the object to be identified, and the planning efficiency and the accuracy of the obstacle avoidance path of the agricultural machine can be effectively improved.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

The accompanying drawings are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and do not constitute a limitation thereof.

Fig. 1 is a flowchart of an agricultural machinery obstacle avoidance method based on target detection according to an embodiment of the present invention;

FIG. 2 is a flow chart of identifying work areas provided by another embodiment of the present invention;

fig. 3 is a flowchart of determining a target obstacle avoidance object according to another embodiment of the present invention;

fig. 4 is a flowchart of determining obstacle avoidance path information according to another embodiment of the present invention;

fig. 5 is a flowchart of determining obstacle avoidance path information according to another embodiment of the present invention;

fig. 6 is a flowchart of determining a target obstacle avoidance path according to another embodiment of the present invention;

fig. 7 is a flow chart for performing obstacle avoidance according to another embodiment of the present invention;

fig. 8 is a structural diagram of an agricultural obstacle avoidance device based on object detection according to another embodiment of the invention;

fig. 9 is a device diagram of an agricultural machine provided by another embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms "first," "second," and the like in the description, in the claims, or in the drawings, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

The invention provides an agricultural machinery obstacle avoidance method, an agricultural machinery obstacle avoidance device, an agricultural machinery and a storage medium based on target detection, wherein the method comprises the following steps: acquiring pre-planned initial path information, controlling the driving device to operate according to the initial path information, and starting the operation equipment to operate; controlling the camera to collect a target image according to the initial path information, wherein the target image comprises a path area corresponding to the running path of the target agricultural machine; identifying a working area from the target image, wherein the working area is an area where the working equipment is located in the target image; determining a target detection area according to the path area and the operation area, wherein the target detection area and the operation area are not overlapped with each other; performing target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified; identifying a target obstacle avoidance object from the objects to be identified, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm; and controlling the driving device to avoid the obstacle according to the obstacle avoidance path information. According to the technical scheme of the embodiment, the interference of the operation equipment of the agricultural machine on the target detection can be eliminated, the interference of crops can be eliminated according to the identification of the object to be identified, and the planning efficiency and the accuracy of the obstacle avoidance path of the agricultural machine can be effectively improved.

As shown in fig. 1, fig. 1 is a flowchart of an agricultural machinery obstacle avoidance method based on target detection according to an embodiment of the present invention, the agricultural machinery obstacle avoidance method based on target detection is applied to a target agricultural machinery, the target agricultural machinery includes a camera, a working device and a driving device, and the method includes:

step S110, acquiring pre-planned initial path information, controlling a driving device to run according to the initial path information, and starting operation equipment to operate;

step S120, controlling a camera to collect a target image according to the initial path information, wherein the target image comprises a path area corresponding to the running path of the target agricultural machine;

step S130, identifying a working area from the target image, wherein the working area is an area where the working equipment is located in the target image;

step S140, determining a target detection area according to the path area and the operation area, wherein the target detection area and the operation area are not overlapped;

step S150, performing target detection in a target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified;

step S160, identifying a target obstacle avoidance object from the objects to be identified, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm;

and S170, controlling the driving device to avoid the obstacle according to the obstacle avoiding path information.

The target agricultural machine may be any agricultural machinery equipment capable of carrying an intelligent control device, such as a rice harvester; the camera can be monocular camera, also can be binocular camera, according to the actual demand select can. The working device is determined according to a specific agricultural machine, for example, for a rice harvester, the working device is a rice harvesting device arranged in front of the rice harvester, and this embodiment is not limited to this. The driving device may be a device that moves and turns under an electric control signal, and those skilled in the art know how to configure the driving device to respond to the determined obstacle avoidance path information.

It should be noted that the initial path information may be obtained according to a common path planning algorithm after the map information of the farmland is obtained and the range where the operation needs to be performed is determined, which is not described herein in detail.

After the initial path information is determined, the operation device may be directly started to perform operation, and when the operation device is in a dynamic state, the operation region is determined, so that the operation device can be prevented from being recognized as an obstacle by mistake, for example, an agricultural machine is ready to travel to the left side, but the operation device moves to the left side to perform operation, and if the operation device is not excluded, a conventional target detection algorithm may recognize that an obstacle exists in a travel route, trigger obstacle avoidance, and belong to false triggering of obstacle avoidance. Based on this, in this embodiment, it is necessary to determine the area to be moved according to the initial path information, control the camera to turn to the direction or the area for image acquisition, identify the work area in the acquired image, remove the work area from the path area, obtain the target detection area, ensure that no work equipment is included in the target detection area, and improve the accuracy of target detection.

It should be noted that the target detection algorithm may be selected according to actual requirements, for example, an a-algorithm, a threshold segmentation method, a background difference method, a frame difference method, an optical flow method, machine learning, and the like.

It should be noted that, because the farmland environment is complex and may include obstacles, crops, other agricultural machines and workers, after the object to be identified is obtained through the target detection algorithm, the target obstacle avoidance object may be determined through simple feature extraction and identification, only the obstacle is identified, and the accuracy of the obstacle avoidance algorithm is improved.

It should be noted that after the target obstacle is determined, an obstacle avoidance path may be calculated according to a common obstacle avoidance algorithm, for example, turning around in an initial running path to bypass the target obstacle, and the obstacle avoidance algorithm and the method for controlling the driving device to achieve obstacle avoidance according to the obstacle avoidance path information are well known to those skilled in the art, and are not described herein again.

In addition, in an embodiment, referring to fig. 2, the step S130 shown in fig. 1 further includes, but is not limited to, the following steps:

step S210, determining the equipment type of the target agricultural machine, and determining a reference image of the operation equipment according to the equipment type;

in step S220, a work area is identified from the target image based on the reference image.

It should be noted that, because there are many types of agricultural machines and different working devices of different agricultural machines, for example, the shapes, functions and installation positions of the working devices of the rice harvester and the picking machine are different, in order to ensure that the working devices can be accurately identified from the target image, the device type of the target agricultural machine can be determined first, which can be set in advance from the device parameters of the target agricultural machine, after the device type is determined, the reference image of the working device can be determined, and then the working area can be determined by image identification according to the reference image.

In addition, in an embodiment, referring to fig. 3, the step S160 shown in fig. 1 further includes, but is not limited to, the following steps:

step S310, performing feature extraction on an object to be recognized to obtain features to be recognized;

step S320, determining the object type of the object to be identified according to the feature to be identified and the preset reference feature;

and step S330, determining the object to be identified with the object type as the target obstacle avoidance object.

It should be noted that after the object to be recognized is determined, the feature to be recognized may be extracted by performing feature extraction on a common deep learning model, and the specific deep learning model and the feature may be selected according to actual requirements, which is not limited in this embodiment.

It is understood that in the case of deep learning model determination, obstacles in a farm field are generally known in advance, such as potholes, stones, plants, other agricultural machines, and the like in the farm field, so that a reference feature of each obstacle may be set during training of the deep learning model, and the object type of the object to be recognized may be determined by comparing the feature to be recognized with the reference feature or calculating similarity.

It should be noted that the object type of the object to be recognized may include an obstacle, a crop, an agricultural equipment, an operator, and the like, which is not limited in this embodiment. Since the present embodiment is to implement obstacle avoidance, the type of the object representing the obstacle may be determined as a target obstacle type, such as an obstacle, a depression in a farmland, and the like.

In addition, in an embodiment, referring to fig. 4, the step S160 shown in fig. 1 further includes, but is not limited to, the following steps:

step S410, determining at least one selectable obstacle avoidance path according to an obstacle avoidance algorithm and the position of a target obstacle avoidance object in a target image;

step S420, determining a target obstacle avoidance path from at least one selectable obstacle avoidance path according to a preset rule;

and step S430, determining obstacle avoidance path information according to the target obstacle avoidance path.

It should be noted that, a farmland is different from a driving road, the farmland does not have a specific driving limit, and when an obstacle is encountered, many obstacle avoidance paths that can be selected by an agricultural machine are flexible.

It should be noted that the preset rule may be selected according to actual requirements, for example, the path is shortest first, and the turning is minimum, which is not limited in this embodiment.

In addition, in an embodiment, the target agricultural machine further includes a distance sensor, and referring to fig. 5, the step S430 shown in fig. 4 further includes, but is not limited to, the following steps:

step S510, controlling a distance sensor to carry out distance detection based on the position of a target obstacle object in a target image to obtain a target distance between a target agricultural machine and the target obstacle object;

step S520, determining a scale of the target image according to the target distance, and determining the path length of the target obstacle avoidance path according to the scale;

and step S530, determining obstacle avoidance path information according to the target obstacle avoidance path and the path length.

It should be noted that the distance sensor may be a common infrared distance sensor, an ultrasonic distance sensor, or the like, and may be selected according to actual needs.

It is worth noting that after the target obstacle avoidance path needs to be determined, the distance that each path needs to travel can be further determined so as to achieve accurate control over the agricultural machinery, on the basis, since the image distance of the obstacle and the operation equipment in the target image is identifiable, a scale between the target image and the actual scene needs to be determined, on the basis, distance detection is carried out on the obstacle through a distance sensor, a basis can be provided for determining the scale, after the target distance is determined, the scale can be determined according to the ratio between the target distance and the distance in the image, and after the scale is determined, the length of each path of the target obstacle avoidance path is further determined, so that obstacle avoidance path information is generated.

In addition, in an embodiment, the target agricultural machine is further configured with a GNSS, and referring to fig. 6, the step S420 shown in fig. 4 further includes, but is not limited to, the following steps:

step S610, determining the turning smoothness of each selectable obstacle avoidance path according to the GNSS;

and S620, determining a target obstacle avoidance path from the selectable obstacle avoidance paths according to a preset rule and the turning smoothness.

It should be noted that most agricultural machines have large equipment size and difficult and complicated turning control, and therefore, after determining the selectable obstacle avoidance path, the path with the optimal turning smoothness can be determined as the target obstacle avoidance path.

It should be noted that after the optional obstacle avoidance path is determined, coordinates of each turning point may be determined through GNSS, so as to construct a curve, and a turning angle of the curve is determined, so as to determine a turning smoothness, for example, the turning angle required to be performed by the entire optional obstacle avoidance path remains unchanged, compared with the optional obstacle avoidance path that needs to frequently perform a change of the turning angle, the turning smoothness is higher, and is convenient for agricultural operation.

In addition, in an embodiment, referring to fig. 7, the step S170 shown in fig. 1 further includes, but is not limited to, the following steps:

step S710, determining the moving position and pose information of the target agricultural machine on the target obstacle avoidance path according to the GNSS;

and S720, controlling a driving device to avoid the obstacle according to the moving pose information and the obstacle avoiding path information.

It should be noted that after the target obstacle avoidance path is determined, the mobile pose information, for example, the pose to be controlled when turning is performed, needs to be determined, and different poses can be provided for the same curve to complete turning, so that each mobile target point can be determined according to the smoothness of the turning by the GNSS, and smooth turning in the obstacle avoidance process is realized.

In addition, referring to fig. 8, an embodiment of the present invention provides an agricultural machinery obstacle avoidance apparatus based on target detection, where the agricultural machinery obstacle avoidance apparatus 800 based on target detection includes

The starting unit 810 is configured to obtain pre-planned initial path information, control the driving device to operate according to the initial path information, and start the operation equipment to perform operation;

an image collecting unit 820, configured to control a camera to collect a target image according to the initial path information, where the target image includes a path area corresponding to a running path of the target agricultural machine;

a job region identification unit 830 configured to identify a job region from the target image, the job region being a region where the job device is located in the target image;

a detection area determination unit 840 configured to determine a target detection area according to the path area and the work area, where the target detection area and the work area do not overlap with each other;

a target detection unit 850, configured to perform target detection in a target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified;

the path planning unit 860 is configured to identify a target obstacle avoidance object from the objects to be identified, and determine obstacle avoidance path information according to a position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm;

and an obstacle avoidance unit 870 configured to control the driving device to avoid an obstacle according to the obstacle avoidance path information.

Additionally, referring to fig. 9, an embodiment of the present invention also provides an agricultural machine, the agricultural machine 900 including: a memory 910, a processor 920, and a computer program stored on the memory 910 and executable on the processor 920.

The processor 920 and the memory 910 may be connected by a bus or other means.

The non-transitory software program and instructions required for implementing the target detection-based obstacle avoidance method of the agricultural machinery of the above-mentioned embodiment are stored in the memory 910, and when being executed by the processor 920, the target detection-based obstacle avoidance method of the above-mentioned embodiment is executed, for example, the method steps S110 to S170 in fig. 1, the method steps S210 to S220 in fig. 2, the method steps S310 to S330 in fig. 3, the method steps S410 to S430 in fig. 4, the method steps S510 to S530 in fig. 5, the method steps S610 to S620 in fig. 6, and the method steps S710 to S720 in fig. 7, which are described above, are executed.

The above described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where the computer program is executed by a processor or a controller, for example, by a processor in the above-mentioned agricultural machinery embodiment, and the processor may be enabled to execute the method for avoiding an obstacle of an agricultural machinery based on target detection in the above-mentioned embodiment, for example, the method steps S110 to S170 in fig. 1, the method steps S210 to S220 in fig. 2, the method steps S310 to S330 in fig. 3, the method steps S410 to S430 in fig. 4, the method steps S510 to S530 in fig. 5, the method steps S610 to S620 in fig. 6, and the method steps S710 to S720 in fig. 7, which are described above, are executed. It will be understood by those of ordinary skill in the art that all or some of the steps, means, and/or steps of the methods disclosed above may be implemented as software, firmware, hardware, or any suitable combination thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable storage media, which may include computer storage media (or non-transitory storage media) and communication storage media (or transitory storage media). The term computer storage media includes volatile and nonvolatile, removable and non-removable storage media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other storage medium which can be used to store the desired information and which can be accessed by a computer. In addition, communication storage media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery storage media as is well known to those of ordinary skill in the art.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

While the preferred embodiments of the present invention have been described, the present invention is not limited to the above embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and such equivalent modifications or substitutions are to be included within the scope of the present invention defined by the appended claims.

Claims

1. An agricultural machinery obstacle avoidance method based on target detection is characterized by being applied to a target agricultural machinery, wherein the target agricultural machinery comprises a camera, operation equipment and a driving device, and the method comprises the following steps:

acquiring initial path information which is planned in advance, controlling the driving device to operate according to the initial path information, and starting the operation equipment to operate;

controlling the camera to collect a target image according to the initial path information, wherein the target image comprises a path area corresponding to the running path of the target agricultural machine;

2. The method as claimed in claim 1, wherein the step of identifying the operation area from the target image comprises:

and identifying the operation area from the target image according to the reference image.

3. The method as claimed in claim 1, wherein the identifying the target obstacle avoidance object from the objects to be identified includes:

4. The method as claimed in claim 1, wherein the determining of obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm includes:

5. The method as claimed in claim 4, wherein the target agricultural machine further comprises a distance sensor, and the determining the obstacle avoidance path information according to the target obstacle avoidance path comprises:

6. The method as claimed in claim 4, wherein the target agricultural machine is further equipped with a GNSS, and determining a target obstacle avoidance path from at least one of the selectable obstacle avoidance paths according to a preset rule comprises:

7. The method as claimed in claim 6, wherein the controlling the driving device to avoid the obstacle according to the obstacle avoidance path information comprises:

and controlling the driving device to avoid the obstacle according to the movement pose information and the obstacle avoidance path information.

8. The utility model provides an obstacle-avoiding device for agricultural machinery based on target detection, which is characterized in that includes:

the image acquisition unit is used for controlling the camera to acquire a target image according to the initial path information, wherein the target image comprises a path area corresponding to the running path of the target agricultural machinery;

a working area identification unit, configured to identify a working area from the target image, where the working area is located in the target image by the working device;

the path planning unit is used for identifying a target obstacle avoidance object from the objects to be identified, and determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image based on a preset obstacle avoidance algorithm;

and the obstacle avoidance unit is used for controlling the driving device to avoid the obstacle according to the obstacle avoidance path information.

9. An agricultural machine comprising: memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for avoiding obstacles of an agricultural machine based on object detection according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the method for obstacle avoidance of an agricultural machine based on object detection according to any one of claims 1 to 7.