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

Abstract

The present invention provides an agricultural machinery obstacle avoidance method, device, agricultural machinery, and storage medium based on target detection. The method includes: performing operations and controlling a camera to collect a target image according to pre-planned initial path information; then, identifying an operation area from the target image, and determining a target detection area according to the path area and the operation area; then, based on a preset target detection algorithm, performing target detection in the target detection area to obtain multiple objects to be identified, and identifying a target obstacle avoidance object, and based on a preset obstacle avoidance algorithm, determining obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image; and controlling a driving device to avoid obstacles according to the obstacle avoidance path information. According to the technical solution of this embodiment, the interference of the agricultural machinery's operating equipment on target detection can be eliminated, and the interference of crops can be eliminated according to the identification of the object to be identified, which can effectively improve the planning efficiency and accuracy of the agricultural machinery obstacle avoidance path.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to an agricultural machinery obstacle avoidance method, device, agricultural machinery, and storage medium based on target detection. Background Art

[0002] With the development of information technology, agricultural machinery intelligent navigation technology has received more and more attention. Ensuring operational safety and improving operational efficiency have become key technologies that distinguish agricultural machinery intelligent navigation from traditional automatic navigation. Common agricultural machinery automatic navigation key technologies include positioning and attitude measurement, path planning, and motion control. However, unlike ordinary car navigation, agricultural machinery operates in a complex environment. For example, a rice harvester operates in a farmland planted with crops, not an identifiable open road. Obstacle avoidance through simple target detection is easily interfered by crops and the operating equipment of the agricultural machinery itself, and the obstacle avoidance efficiency of agricultural machinery is not high. Summary of the invention

[0003] 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.

[0004] The embodiments of the present invention provide an agricultural machinery obstacle avoidance method, device, agricultural machinery, and storage medium based on target detection, which can improve the obstacle avoidance capability of the agricultural machinery.

[0005] 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, wherein the target agricultural machinery includes a camera, an operating device, and a driving device, and the method includes:

[0006] Acquire pre-planned initial path information, control the operation of the driving device according to the initial path information, and start the operating equipment to perform the operation;

[0007] According to the initial path information, controlling the camera to collect a target image, wherein the target image includes a path area corresponding to the running path of the target agricultural machinery;

[0008] Identifying a working area from the target image, where the working area is the area where the working equipment is located in the target image;

[0009] Determining a target detection area according to the path area and the operation area, wherein the target detection area and the operation area do not overlap each other;

[0010] Based on a preset target detection algorithm, target detection is performed in the target detection area to obtain a plurality of objects to be identified;

[0011] Identify a target obstacle avoidance object from the objects to be identified, and determine 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;

[0012] The driving device is controlled to avoid obstacles according to the obstacle avoidance path information.

[0013] In some embodiments, identifying the working area from the target image includes:

[0014] Determining the equipment type of the target agricultural machinery, and determining a reference image of the operating equipment according to the equipment type;

[0015] The working area is identified from the target image according to the reference image.

[0016] In some embodiments, the step of identifying a target obstacle avoidance object from the objects to be identified includes:

[0017] Extracting features of the object to be identified to obtain features to be identified;

[0018] Determining the object type of the object to be identified according to the feature to be identified and a preset reference feature;

[0019] The object to be identified whose object type is a target obstacle type is determined as the target obstacle avoidance object.

[0020] In some embodiments, the determining of obstacle avoidance path information based on a preset obstacle avoidance algorithm according to the position of the target obstacle avoidance object in the target image includes:

[0021] Determine at least one optional obstacle avoidance path according to the obstacle avoidance algorithm and the position of the target obstacle avoidance object in the target image;

[0022] Determining a target obstacle avoidance path from at least one of the optional obstacle avoidance paths according to a preset rule;

[0023] The obstacle avoidance path information is determined according to the target obstacle avoidance path.

[0024] In some embodiments, the target agricultural machine further includes a distance sensor, and determining the obstacle avoidance path information according to the target obstacle avoidance path includes:

[0025] Based on the position of the target obstacle object in the target image, controlling the distance sensor to perform distance detection to obtain a target distance between the target agricultural machinery and the target obstacle object;

[0026] Determining a scale of the target image according to the target distance, and determining a path length of the target obstacle avoidance path according to the scale;

[0027] The obstacle avoidance path information is determined according to the target obstacle avoidance path and the path length.

[0028] In some embodiments, the target agricultural machine is further equipped with a GNSS, and determining the target obstacle avoidance path from at least one of the optional obstacle avoidance paths according to a preset rule includes:

[0029] Determining a turning smoothness of each of the optional obstacle avoidance paths according to the GNSS;

[0030] The target obstacle avoidance path is determined from the optional obstacle avoidance paths according to the preset rule and the turning smoothness.

[0031] In some embodiments, controlling the driving device to avoid obstacles according to the obstacle avoidance path information includes:

[0032] Determine the moving position information of the target agricultural machinery on the target obstacle avoidance path according to the GNSS;

[0033] The driving device is controlled to avoid obstacles according to the moving posture information and the obstacle avoidance path information.

[0034] In a second aspect, an embodiment of the present invention provides an agricultural machinery obstacle avoidance device based on target detection, comprising:

[0035] A starting unit, used to obtain pre-planned initial path information, control the operation of the driving device according to the initial path information, and start the operating equipment to perform the operation;

[0036] An image acquisition unit, configured to control the camera to acquire a target image according to the initial path information, wherein the target image includes a path area corresponding to the running path of the target agricultural machinery;

[0037] An operation area recognition unit, used to recognize an operation area from the target image, wherein the operation area is an area where the operation equipment is located in the target image;

[0038] a detection area determination unit, configured to determine a target detection area according to the path area and the operation area, wherein the target detection area and the operation area do not overlap with each other;

[0039] A target detection unit, configured to perform target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified;

[0040] A path planning unit, 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;

[0041] An obstacle avoidance unit is used to control the driving device to avoid obstacles according to the obstacle avoidance path information.

[0042] In a third aspect, an embodiment of the present invention provides an agricultural machinery, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the agricultural machinery obstacle avoidance method based on target detection as described in the first aspect is implemented.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is used to execute the agricultural machinery obstacle avoidance method based on target detection as described in the first aspect.

[0044] The embodiment of the present invention includes: obtaining pre-planned initial path information, controlling the driving device to operate according to the initial path information, and starting the operating equipment to operate; according to the initial path information, controlling the camera to collect the target image, the target image includes the path area corresponding to the operating path of the target agricultural machinery; identifying the operating area from the target image, the operating area is the area where the operating equipment is located in the target image; determining the target detection area according to the path area and the operating area, wherein the target detection area and the operating area do not overlap each other; based on a preset target detection algorithm, performing target detection in the target detection area to obtain multiple objects to be identified; identifying the target obstacle avoidance object from the objects to be identified, and based on a preset obstacle avoidance algorithm, determining the obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image; and controlling the driving device to avoid obstacles according to the obstacle avoidance path information. According to the technical solution of this embodiment, the interference of the operating equipment of the agricultural machinery on the target detection can be eliminated, and the interference of crops can be eliminated according to the identification of the objects to be identified, which can effectively improve the planning efficiency and accuracy of the obstacle avoidance path of the agricultural machinery.

[0045] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0047] Figure 1 is a flow chart of an agricultural machinery obstacle avoidance method based on target detection provided by an embodiment of the present invention;

[0048] Figure 2 is a flow chart of identifying an operation area provided by another embodiment of the present invention;

[0049] Figure 3 is a flowchart of determining a target obstacle avoidance object provided by another embodiment of the present invention;

[0050] Figure 4 is a flowchart of determining obstacle avoidance path information provided by another embodiment of the present invention;

[0051] Figure 5 is a flowchart of determining obstacle avoidance path information provided by another embodiment of the present invention;

[0052] Figure 6 is a flow chart of determining a target obstacle avoidance path provided by another embodiment of the present invention;

[0053] Figure 7 is a flowchart of performing obstacle avoidance provided by another embodiment of the present invention;

[0054] Figure 8 is a structural diagram of an agricultural machinery obstacle avoidance device based on target detection provided by another embodiment of the present invention;

[0055] Fig. 9 It is a device diagram of an agricultural machine provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "target" and the like in the specification, claims or the above drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0058] The present invention provides an agricultural machinery obstacle avoidance method, device, agricultural machinery, and storage medium based on target detection, the method comprising: obtaining pre-planned initial path information, controlling the operation of the driving device according to the initial path information, and starting the operating equipment to operate; controlling the camera to collect a target image according to the initial path information, the target image comprising a path area corresponding to the operating path of the target agricultural machinery; identifying an operating area from the target image, the operating area being an area where the operating equipment is located in the target image; determining a target detection area according to the path area and the operating area, wherein the target detection area and the operating area do not overlap 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 obstacles according to the obstacle avoidance path information. According to the technical solution of this embodiment, the interference of the operating equipment of the agricultural machinery on the target detection can be eliminated, and the interference of crops can be eliminated based on the identification of the object to be identified, which can effectively improve the planning efficiency and accuracy of the obstacle avoidance path of the agricultural machinery.

[0059] like Figure 1 As shown, Figure 1 The present invention provides 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, an operating device and a driving device, and the method includes:

[0060] Step S110, obtaining pre-planned initial path information, controlling the operation of the driving device according to the initial path information, and starting the operating equipment to perform the operation;

[0061] Step S120, controlling the camera to collect a target image according to the initial path information, where the target image includes a path area corresponding to the running path of the target agricultural machinery;

[0062] Step S130, identifying an operation area from the target image, where the operation area is the area where the operation equipment is located in the target image;

[0063] 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 do not overlap with each other;

[0064] Step S150, performing target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified;

[0065] 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;

[0066] Step S170, controlling the driving device to avoid obstacles according to the obstacle avoidance path information.

[0067] It should be noted that the target agricultural machinery can be any agricultural machinery equipment that can be equipped with an intelligent control device, such as a rice harvester, etc. The camera can be a monocular camera or a binocular camera, which can be selected according to actual needs. The operating equipment is determined according to the specific agricultural machinery. For example, for a rice harvester, the operating equipment is a rice harvesting device arranged in front of the rice harvester. This embodiment does not limit this. The drive device can be a device that realizes movement and steering under an electric control signal. Those skilled in the art are familiar with how to configure the drive device to respond to the determined obstacle avoidance path information.

[0068] It should be noted that the initial path information can be obtained according to a common path planning algorithm after obtaining the map information of the farmland and determining the scope of the operation to be performed, and will not be elaborated here.

[0069] It should be noted that after determining the initial path information, the operating equipment can be directly started to operate. Determining the operating area when the operating equipment is in motion can avoid mistakenly identifying the operating equipment as an obstacle. For example, the agricultural machinery is ready to move to the left, but the operating equipment moves to the left to operate. If the operating equipment is not excluded, the conventional target detection algorithm will identify the existence of obstacles in the travel path and trigger obstacle avoidance, which is a false triggering of obstacle avoidance. Based on this, this embodiment needs to determine the area to be moved according to the initial path information, and control the camera to turn to the direction or area for image acquisition, and identify the operating area in the acquired image, remove the operating area from the path area, and obtain the target detection area, ensuring that the target detection area does not include the operating equipment, thereby improving the accuracy of target detection.

[0070] It should be noted that the target detection algorithm can be selected according to actual needs, such as A* algorithm, threshold segmentation method, background difference method, frame difference method, optical flow method and machine learning method. Since the farmland environment is not a road with good recognition, the present embodiment can adopt the A* algorithm to reduce the impact of environmental complexity on the accuracy of target detection.

[0071] It should be noted that due to the complex farmland environment, which may include obstacles, crops, other agricultural machinery and workers, after obtaining the object to be identified through the target detection algorithm, the target obstacle avoidance object can be determined through simple feature extraction and recognition, and only the obstacles can be identified to improve the accuracy of the obstacle avoidance algorithm.

[0072] It should be noted that after determining the target obstacle, an obstacle avoidance path can be calculated based on a common obstacle avoidance algorithm, such as turning in the initial running path to bypass the target obstacle. The obstacle avoidance algorithm and the control of the drive device based on the obstacle avoidance path information to achieve obstacle avoidance are technologies well known to those skilled in the art and will not be elaborated here.

[0073] In addition, in one embodiment, referring to Figure 2 , Figure 1 The step S130 shown in FIG. 1 also includes but is not limited to the following steps:

[0074] Step S210, determining the equipment type of the target agricultural machinery, and determining a reference image of the operating equipment according to the equipment type;

[0075] Step S220: identifying the work area from the target image according to the reference image.

[0076] It should be noted that due to the large number of types of agricultural machinery, different agricultural machinery has different operating equipment. For example, the operating equipment of rice harvesters and pickers are different in shape, function and setting position. In order to ensure accurate identification of the operating equipment from the target image, the equipment type of the target agricultural machinery can be determined first. This can be determined from the equipment parameters of the target agricultural machinery or pre-set. After determining the equipment type, the reference image of the operating equipment can be determined, and then image recognition is performed based on the reference image to determine the operating area.

[0077] In addition, in one embodiment, referring to Figure 3 , Figure 1 The step S160 shown in FIG. 1 also includes but is not limited to the following steps:

[0078] Step S310, extracting features of the object to be identified to obtain features to be identified;

[0079] Step S320, determining the object type of the object to be identified according to the feature to be identified and the preset reference feature;

[0080] Step S330: determine the to-be-identified object whose object type is the target obstacle type as the target obstacle avoidance object.

[0081] It should be noted that after determining the object to be identified, the features to be identified can be extracted through common deep learning models. The specific deep learning model and feature selection can be selected according to actual needs, and this embodiment does not impose any restrictions on this.

[0082] It is understandable that when the deep learning model is determined, obstacles in the farmland are usually known in advance, such as potholes, stones, plants, other agricultural machinery, etc. in the farmland. Therefore, the reference features of each obstacle can be set during the training process of the deep learning model, and the object type of the object to be identified can be determined by comparing the features to be identified with the reference features or calculating the similarity.

[0083] It should be noted that the object type of the object to be identified may include obstacles, crops, agricultural machinery and equipment, operators, etc., which are not limited in this embodiment. Since this embodiment is to achieve obstacle avoidance, the object type representing the obstacle can be determined as the target obstacle type, such as obstacles, potholes in farmland, etc.

[0084] In addition, in one embodiment, referring to Figure 4 , Figure 1 The step S160 shown in FIG. 1 also includes but is not limited to the following steps:

[0085] Step S410, determining at least one optional obstacle avoidance path according to the obstacle avoidance algorithm and the position of the target obstacle avoidance object in the target image;

[0086] Step S420, determining a target obstacle avoidance path from at least one optional obstacle avoidance path according to a preset rule;

[0087] Step S430: Determine obstacle avoidance path information according to the target obstacle avoidance path.

[0088] It should be noted that farmland is different from driving roads. There are no clearly defined driving restrictions on farmland. When encountering obstacles, agricultural machinery has more flexible obstacle avoidance paths to choose from. This embodiment can generate multiple optional obstacle avoidance paths after determining the target obstacle object, and determine the target obstacle avoidance path according to preset rules, making the obstacle avoidance scheme more flexible.

[0089] It should be noted that the preset rules can be selected according to actual needs, such as the shortest path priority, the minimum turn principle, etc., and this embodiment does not make any restrictions on this.

[0090] In addition, in one embodiment, the target agricultural machine also includes a distance sensor, referring to Figure 5 , Figure 4 The step S430 shown in FIG. 4 also includes but is not limited to the following steps:

[0091] Step S510, based on the position of the target obstacle object in the target image, controlling the distance sensor to perform distance detection to obtain the target distance between the target agricultural machinery and the target obstacle object;

[0092] Step S520, determining the 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;

[0093] Step S530: Determine obstacle avoidance path information according to the target obstacle avoidance path and the path length.

[0094] It should be noted that the distance sensor can be a common infrared distance sensor, ultrasonic distance sensor, etc., which can be selected according to actual needs.

[0095] It is worth noting that after determining the target obstacle avoidance path, the distance required to travel for each section of the path can be further determined to achieve precise control of the agricultural machinery. Based on this, since the image distance of obstacles and working equipment in the target image is identifiable, it is necessary to determine the scale between the target image and the actual scene. Based on this, distance detection of obstacles through distance sensors can provide a basis for determining the scale. After determining the target distance, the scale can be determined based on the ratio between the target distance and the distance in the image, and after determining the scale, the length of each section of the target obstacle avoidance path is further determined to generate obstacle avoidance path information.

[0096] In addition, in one embodiment, the target agricultural machine is also equipped with a GNSS. Figure 6 , Figure 4 The step S420 shown in FIG. 4 also includes but is not limited to the following steps:

[0097] Step S610, determining the turning smoothness of each optional obstacle avoidance path according to GNSS;

[0098] Step S620: determining a target obstacle avoidance path from the optional obstacle avoidance paths according to preset rules and turning smoothness.

[0099] It should be noted that most agricultural machinery is large in size and the turning control is difficult and complicated. Therefore, after determining the optional obstacle avoidance path, the path with the best turning smoothness can be determined as the target obstacle avoidance path.

[0100] It should be noted that after determining the optional obstacle avoidance path, the coordinates of each turning point can be determined by GNSS to construct a curve, and the turning angle of the curve can be determined, and then the turning smoothness can be determined. For example, the turning angle required for the entire optional obstacle avoidance path remains unchanged. Compared with the optional obstacle avoidance path that requires frequent changes in turning angles, its turning smoothness is higher, which is convenient for agricultural machinery operation.

[0101] In addition, in one embodiment, referring to Figure 7 , Figure 1 The step S170 shown in FIG. 1 also includes but is not limited to the following steps:

[0102] Step S710, determining the moving position information of the target agricultural machine on the target obstacle avoidance path according to the GNSS;

[0103] Step S720: Control the driving device to avoid obstacles according to the moving posture information and the obstacle avoidance path information.

[0104] It should be noted that after determining the target obstacle avoidance path, it is also necessary to determine the mobile posture information, such as the posture that needs to be controlled when turning. For the same curve, different postures can be used to complete the turn. Therefore, each moving target point can be determined according to the turning smoothness based on GNSS, thereby achieving smooth turning during obstacle avoidance.

[0105] In addition, refer to Figure 8 The embodiment of the present invention provides an agricultural machinery obstacle avoidance device based on target detection, and the agricultural machinery obstacle avoidance device based on target detection 800 includes

[0106] The starting unit 810 is used to obtain the pre-planned initial path information, control the operation of the driving device according to the initial path information, and start the operation equipment to perform the operation;

[0107] The image acquisition unit 820 is used to control the camera to acquire a target image according to the initial path information, where the target image includes a path area corresponding to the running path of the target agricultural machinery;

[0108] The operation area identification unit 830 is used to identify the operation area from the target image, where the operation area is the area where the operation equipment is located in the target image;

[0109] A detection area determination unit 840, configured to determine a target detection area according to the path area and the operation area, wherein the target detection area and the operation area do not overlap with each other;

[0110] The target detection unit 850 is used to perform target detection in the target detection area based on a preset target detection algorithm to obtain multiple objects to be identified;

[0111] A path planning unit 860 is used to identify a target obstacle avoidance object from the objects to be identified, and determine 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;

[0112] The obstacle avoidance unit 870 is used to control the driving device to avoid obstacles according to the obstacle avoidance path information.

[0113] In addition, refer to Fig. 9 An embodiment of the present invention further provides an agricultural machine, the agricultural machine 900 comprising: a memory 910, a processor 920, and a computer program stored in the memory 910 and executable on the processor 920.

[0114] The processor 920 and the memory 910 may be connected via a bus or in other ways.

[0115] The non-transient software program and instructions required to implement the agricultural machinery obstacle avoidance method based on target detection in the above embodiment are stored in the memory 910. When executed by the processor 920, the agricultural machinery obstacle avoidance method based on target detection in the above embodiment is executed, for example, the above described Figure 1 Steps S110 to S170 of the method, Figure 2 Steps S210 to S220 of the method, Figure 3 Steps S310 to S330 of the method, Figure 4 Steps S410 to S430 of the method, Figure 5 Steps S510 to S530 of the method, Figure 6 Steps S610 to S620 of the method, Figure 7 Method steps S710 to S720.

[0116] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor or a controller, for example, by a processor in the above agricultural machinery embodiment, so that the above processor can execute the agricultural machinery obstacle avoidance method based on target detection in the above embodiment, for example, execute the above described Figure 1 Steps S110 to S170 of the method, Figure 2 Steps S210 to S220 of the method, Figure 3 Steps S310 to S330 of the method, Figure 4 Steps S410 to S430 of the method, Figure 5 Steps S510 to S530 of the method, Figure 6 Steps S610 to S620 of the method, Figure 7Method steps S710 to S720 in the method. It will be appreciated by those skilled in the art that all or some of the steps and devices in the method disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or a non-transitory storage medium) and a communication storage medium (or a temporary storage medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable storage media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other storage medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication storage media generally contain 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 may include any information delivery storage media.

[0118] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0119] It should be understood that the present application is not limited to the precise structures that have been 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 present application is limited only by the appended claims.

[0120] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. An agricultural machinery obstacle avoidance method based on target detection, characterized in that: Applied to a target agricultural machine, the target agricultural machine includes a camera, an operating device, and a driving device, and the method includes: Acquire pre-planned initial path information, control the operation of the driving device according to the initial path information, and start the operating equipment to perform the operation; According to the initial path information, controlling the camera to collect a target image, wherein the target image includes a path area corresponding to the running path of the target agricultural machinery; Identifying a working area from the target image, where the working area is the 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 do not overlap each other; Based on a preset target detection algorithm, target detection is performed in the target detection area to obtain a plurality of objects to be identified; Identify a target obstacle avoidance object from the objects to be identified, and determine 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; The driving device is controlled to avoid obstacles according to the obstacle avoidance path information.

2. The agricultural machinery obstacle avoidance method based on target detection according to claim 1, characterized in that: The step of identifying the working area from the target image comprises: Determining the equipment type of the target agricultural machinery, and determining a reference image of the operating equipment according to the equipment type; The working area is identified from the target image according to the reference image.

3. The agricultural machinery obstacle avoidance method based on target detection according to claim 1, characterized in that: The step of identifying a target obstacle avoidance object from the to-be-identified object comprises: Extracting features of the object to be identified to obtain features to be identified; Determining the object type of the object to be identified according to the feature to be identified and a preset reference feature; The object to be identified whose object type is a target obstacle type is determined as the target obstacle avoidance object.

4. The agricultural machinery obstacle avoidance method based on target detection according to claim 1, characterized in that: The obstacle avoidance algorithm based on a preset obstacle avoidance algorithm determines the obstacle avoidance path information according to the position of the target obstacle avoidance object in the target image, including: Determine at least one optional 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 of the optional obstacle avoidance paths according to a preset rule; The obstacle avoidance path information is determined according to the target obstacle avoidance path.

5. The agricultural machinery obstacle avoidance method based on target detection according to claim 4 is characterized in that: The target agricultural machine also includes a distance sensor, and determining the obstacle avoidance path information according to the target obstacle avoidance path includes: Based on the position of the target obstacle avoidance object in the target image, controlling the distance sensor to perform distance detection to obtain a target distance between the target agricultural machinery and the target obstacle avoidance object; Determining a scale of the target image according to the target distance, and determining a path length of the target obstacle avoidance path according to the scale; The obstacle avoidance path information is determined according to the target obstacle avoidance path and the path length.

6. The agricultural machinery obstacle avoidance method based on target detection according to claim 4, characterized in that: The target agricultural machine is also equipped with a GNSS, and determining the target obstacle avoidance path from at least one of the optional obstacle avoidance paths according to a preset rule includes: Determining a turning smoothness of each of the optional obstacle avoidance paths according to the GNSS; The target obstacle avoidance path is determined from the optional obstacle avoidance paths according to the preset rule and the turning smoothness.

7. The agricultural machinery obstacle avoidance method based on target detection according to claim 6, characterized in that: The controlling the driving device to avoid obstacles according to the obstacle avoidance path information comprises: Determine the moving position information of the target agricultural machinery on the target obstacle avoidance path according to the GNSS; The driving device is controlled to avoid obstacles according to the moving posture information and the obstacle avoidance path information.

8. An agricultural machinery obstacle avoidance device based on target detection, characterized in that: include: A starting unit, used to obtain pre-planned initial path information, control the operation of the driving device according to the initial path information, and start the operating equipment to perform the operation; An image acquisition unit, configured to control a camera to acquire a target image according to the initial path information, wherein the target image includes a path area corresponding to the running path of the target agricultural machinery; An operation area recognition unit, used to recognize an operation area from the target image, wherein the operation area is an area where the operation equipment 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 operation area, wherein the target detection area and the operation area do not overlap with each other; A target detection unit, configured to perform target detection in the target detection area based on a preset target detection algorithm to obtain a plurality of objects to be identified; A path planning unit, 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; An obstacle avoidance unit is used to control the driving device to avoid obstacles according to the obstacle avoidance path information.

9. An agricultural machine comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the agricultural machinery obstacle avoidance method based on target detection as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: The computer program is used to execute the agricultural machinery obstacle avoidance method based on target detection as described in any one of claims 1 to 7.

Images