Target object ranging system based on deep learning point cloud classification algorithm

Abstract

The invention discloses a target object distance measurement system based on a deep learning point cloud classification algorithm, and relates to the technical field of target distance measurement, and the system comprises a construction processing module which is used for carrying out the laser point cloud scanning of a target object in a current space, obtaining original point cloud data, and constructing a point cloud model; the identification processing module is used for identifying and classifying the original point cloud data by using the point cloud model, and the identification result comprises an electrified body, a grounding body and an insulator; and the calculation processing module is used for calculating the distance between each adjacent target object based on the spatial relationship expression of each target object in the point cloud model. According to the method, the spatial position information of the current operating personnel is obtained, and the relative distance between the current operating personnel and a ground body, an insulator, a wire, an electrified body and other target objects is calculated, so that whether the operating personnel meet the safety operation standard is judged. This helps to ensure a safe distance between the operator and the potential hazard.

Description

Technical Field

[0001] The present invention relates to the technical field of target distance measurement, and in particular to a target distance measurement system based on a deep learning point cloud classification algorithm. Background Art

[0002] Live working can eliminate defects in power transmission and transformation equipment in a timely manner, ensure reliable and continuous power supply to users, and is widely used in power grid operation and maintenance. Therefore, live working is indispensable in daily power grid maintenance operations.

[0003] Ensure that the safety distance between the human body and the charged object (or the connected object) is not less than the specified value. That is, ensuring that the safety distance between the human body and the charged object (or the connected object) is not less than the specified safety distance is one of the three major technical conditions for live working. However, in order to ensure the safety of live working, necessary tests should be carried out according to the needs of the work before the work, and various safety distances, cross-over distances and ground distances should be tested.

[0004] Therefore, decisions can be made based on the test results (distance measurement results) on whether live working can be carried out, what working methods to adopt and necessary safety measures, providing auxiliary decision-making basis for the implementation of live working. However, most distance measurement methods in the prior art are based on manual experience to visually measure the safe distance, or laser rangefinders are used to continuously and manually illuminate the surrounding environment and equipment for distance measurement. Such distance measurement methods are inaccurate and inefficient, and safety cannot be guaranteed. Summary of the invention

[0005] In view of the problems existing in the existing target object ranging based on deep learning point cloud classification algorithm, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is that the existing distance measurement method is inaccurate and inefficient, and the safety cannot be guaranteed.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a target object ranging system based on a deep learning point cloud classification algorithm, which includes:

[0009] Construct a processing module for performing laser point cloud scanning on the target object in the current space, obtaining raw point cloud data, and constructing a point cloud model;

[0010] An identification processing module, used to identify and classify the original point cloud data using the point cloud model, wherein the identification results include charged bodies, grounded bodies, and insulators;

[0011] The calculation processing module is used to calculate the distance between each adjacent target object based on the spatial relationship expression of each target object in the point cloud model.

[0012] As a preferred solution of the target distance measurement system based on deep learning point cloud classification algorithm described in the present invention, it also includes a dangerous area identification module;

[0013] The hazardous area identification module is used to:

[0014] When the current target object is identified as a charged object, the type of the current charged object is identified, and the database is called to match to obtain the voltage level safety distance information corresponding to the type of the current charged object;

[0015] According to the type of the current charged object and the corresponding voltage level safety distance information, taking all edge points of the current charged object as the center of the point cloud and the safety distance value recorded in the voltage level safety distance information as the radius, multiple bounding boxes of the target object are obtained by extending outward;

[0016] Finally, it is determined that the collective spatial range data corresponding to the current multiple bounding boxes is the dangerous area.

[0017] As a preferred solution of the target object ranging system based on the deep learning point cloud classification algorithm described in the present invention, it also includes a non-dangerous area identification module, which is used to determine that the spatial range data outside the collective spatial range data corresponding to the current multiple bounding boxes corresponding to the current target object is marked as the non-dangerous area of ​​the current target object.

[0018] As a preferred solution of the target object ranging system based on the deep learning point cloud classification algorithm of the present invention, it also includes a ground ranging module;

[0019] The ground ranging module is used for:

[0020] Identify the ground body corresponding to the original point cloud data;

[0021] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0022] Calculate the relative position distance between the current operator and the ground object or the grounding object based on the position information of the current operator in the point cloud model;

[0023] Recording the relative position distance as the actual distance between the operator and the ground;

[0024] Obtain the preset standard value of the operator's safety distance to the ground, compare the operator's actual distance to the ground with the standard value of the operator's safety distance to the ground to determine whether the current operator meets the safety operation standard.

[0025] As a preferred solution of the target object ranging system based on the deep learning point cloud classification algorithm of the present invention, it also includes a minimum combination gap processing module;

[0026] The minimum combined gap processing module is used for:

[0027] Identify the ground body corresponding to the original point cloud data;

[0028] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0029] Obtain the preset value of the minimum combined gap on the human body insulation ladder, compare the actual gap distance of the current insulation ladder with the value of the minimum combined gap on the human body insulation ladder, and determine whether the current insulation ladder meets the safety operation standards.

[0030] As a preferred solution of the target object distance measurement system based on the deep learning point cloud classification algorithm of the present invention, it further includes a wire distance measurement processing module;

[0031] The wire distance measurement processing module is used for:

[0032] Identify the wires corresponding to the original point cloud data;

[0033] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0034] Calculating the relative distance between the current operator and the adjacent wire based on the position information of the current operator in the point cloud model;

[0035] The relative position distance is recorded as the actual distance of the adjacent wire to the wire by the operator;

[0036] Obtain the preset standard value of the equipotential operator to the adjacent phase conductor, compare the actual distance of the adjacent conductor corresponding to the operator with the standard value of the equipotential operator to the adjacent phase conductor, and determine whether the current operator meets the safety operation standards.

[0037] As a preferred solution of the target object distance measurement system based on the deep learning point cloud classification algorithm of the present invention, it further includes a charged body distance measurement processing module;

[0038] The charged body distance measurement processing module is used for:

[0039] Identify the charged body corresponding to the original point cloud data;

[0040] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0041] Calculating the relative position distance between the current operator and the adjacent charged body based on the position information of the current operator in the point cloud model;

[0042] The relative position distance is recorded as the actual distance between the operator and the adjacent charged body;

[0043] Obtain the preset standard safety distance value between the human body and the charged object for the equipotential workers, compare the actual distance of the adjacent charged object corresponding to the worker with the standard safety distance value between the human body and the charged object for the equipotential workers, and determine whether the current worker meets the safety operation standards.

[0044] As a preferred solution of the target object distance measurement system based on the deep learning point cloud classification algorithm of the present invention, it also includes a path planning processing module;

[0045] The path planning processing module is used for:

[0046] Receive the location information of the target operation point set and sent by the current operator, and then obtain the location information of the current location point of the current operator;

[0047] The dangerous area of ​​the current target object is obtained, and a target planning path from the current position point of the current operator to the target operation point is planned to avoid the dangerous area of ​​the current target object.

[0048] In a second aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned target object ranging system based on deep learning point cloud classification algorithm is implemented.

[0049] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned target object ranging system based on deep learning point cloud classification algorithm is implemented.

[0050] The beneficial effects of the present invention are as follows: by obtaining the spatial position information of the current operator and calculating the relative position distance between the operator and the target objects such as the ground, insulators, wires, and charged objects, it is determined whether the operator meets the safety operation standards. This helps to ensure a safe distance between the operator and potential dangerous objects. After calculating the distances to adjacent target objects, the position information of the current position point of the current operator is obtained based on the position information of the target operation point set by the current operator, and the dangerous area of ​​the target operation point is determined. Then a safe path that avoids the dangerous area is planned to ensure that the operator can safely reach the target operation point. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0052] Figure 1 This is a structural diagram of the target ranging system based on the deep learning point cloud classification algorithm. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0057] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0058] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] Example 1

[0060] Reference Figure 1 , which is the first embodiment of the present invention, and provides a target distance measurement system based on a deep learning point cloud classification algorithm, comprising:

[0061] Construct a processing module for performing laser point cloud scanning on the target object in the current space, obtaining raw point cloud data, and constructing a point cloud model;

[0062] An identification processing module, used to identify and classify the original point cloud data using the point cloud model, wherein the identification results include charged bodies, grounded bodies, and insulators;

[0063] The calculation processing module is used to calculate the distance between each adjacent target object based on the spatial relationship expression of each target object in the point cloud model.

[0064] Also included is a hazardous area identification module;

[0065] The hazardous area identification module is used to:

[0066] When the current target object is identified as a charged object, the type of the current charged object is identified, and the database is called to match to obtain the voltage level safety distance information corresponding to the type of the current charged object;

[0067] According to the type of the current charged object and the corresponding voltage level safety distance information, taking all edge points of the current charged object as the center of the point cloud and the safety distance value recorded in the voltage level safety distance information as the radius, multiple bounding boxes of the target object are obtained by extending outward;

[0068] Finally, it is determined that the collective spatial range data corresponding to the current multiple bounding boxes is the dangerous area.

[0069] It also includes a non-dangerous area identification module, which is used to determine that the spatial range data outside the set spatial range data corresponding to the current multiple bounding boxes corresponding to the current target object is marked as the non-dangerous area of ​​the current target object.

[0070] It also includes a ground ranging module;

[0071] The ground ranging module is used for:

[0072] Identify the ground body corresponding to the original point cloud data;

[0073] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0074] Calculate the relative distance between the current operator and the ground object or the grounding object based on the position information of the current operator in the point cloud model;

[0075] Recording the relative position distance as the actual distance between the operator and the ground;

[0076] Obtain the preset standard value of the operator's safety distance to the ground, compare the operator's actual distance to the ground with the standard value of the operator's safety distance to the ground to determine whether the current operator meets the safety operation standard.

[0077] It also includes a minimum combined gap processing module;

[0078] The minimum combined gap processing module is used for:

[0079] Identify the ground body corresponding to the original point cloud data;

[0080] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0081] Calculate the relative position distance between the current operator and the "insulation ladder" in the insulator based on the position information of the current operator in the point cloud model;

[0082] When the relative position distance is 0, it is determined that the operator is detected using an "insulated ladder";

[0083] Based on the current position information of the "insulating ladder", "charged body" and "grounded body" in the point cloud model, the actual spacing distance between the "insulating ladder" and the "charged body" and "grounded body" is calculated respectively, and the sum of the two is the actual gap distance;

[0084] Obtain the preset value of the minimum combined gap on the human body insulation ladder, compare the actual gap distance of the current insulation ladder with the value of the minimum combined gap on the human body insulation ladder, and determine whether the current insulation ladder meets the safety operation standards.

[0085] Also included is a wire ranging processing module;

[0086] The wire distance measurement processing module is used for:

[0087] Identify the wires corresponding to the original point cloud data;

[0088] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0089] Calculating the relative distance between the current operator and the adjacent wire based on the position information of the current operator in the point cloud model;

[0090] The relative position distance is recorded as the actual distance of the adjacent wire to the wire by the operator;

[0091] Obtain the preset standard value of the equipotential operator to the adjacent phase conductor, compare the actual distance of the adjacent conductor corresponding to the operator with the standard value of the equipotential operator to the adjacent phase conductor, and determine whether the current operator meets the safety operation standards.

[0092] It also includes a charged body ranging processing module;

[0093] The charged body distance measurement processing module is used for:

[0094] Identify the charged body corresponding to the original point cloud data;

[0095] Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model;

[0096] Calculating the relative position distance between the current operator and the adjacent charged body based on the position information of the current operator in the point cloud model;

[0097] The relative position distance is recorded as the actual distance between the operator and the adjacent charged body;

[0098] Obtain the preset standard safety distance value between the human body and the charged object for the equipotential workers, compare the actual distance of the adjacent charged object corresponding to the worker with the standard safety distance value between the human body and the charged object for the equipotential workers, and determine whether the current worker meets the safety operation standards.

[0099] Also includes a path planning processing module;

[0100] The path planning processing module is used for:

[0101] Receive the location information of the target operation point set and sent by the current operator, and then obtain the location information of the current location point of the current operator;

[0102] The dangerous area of ​​the current target object is obtained, and a target planning path from the current position point of the current operator to the target operation point is planned to avoid the dangerous area of ​​the current target object.

[0103] In summary, by obtaining the spatial position information of the current operator and calculating the relative position distance between the operator and the target objects such as the ground, insulators, wires, and charged objects, it is determined whether the operator meets the safety operation standards. This helps to ensure a safe distance between the operator and potential dangerous objects. After calculating the distance to the adjacent target objects, the position information of the current position point of the current operator is obtained according to the position information of the target operation point set by the current operator, and the dangerous area of ​​the target operation point is determined. Then a safe path that avoids the dangerous area is planned to ensure that the operator can safely reach the target operation point.

[0104] Example 2

[0105] This embodiment provides a computer device, which is suitable for the case of a target object ranging system based on a deep learning point cloud classification algorithm, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the target object ranging system based on the deep learning point cloud classification algorithm proposed in the above embodiment.

[0106] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a method bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating method and a computer program. The internal memory provides an environment for the operation of the operating method and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0107] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements a target object ranging system based on a deep learning point cloud classification algorithm as proposed in the above embodiment.

[0108] The storage medium proposed in this embodiment and the data storage system proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A target distance measurement system based on deep learning point cloud classification algorithm, characterized by: include, Construct a processing module for performing laser point cloud scanning on the target object in the current space, obtaining raw point cloud data, and constructing a point cloud model; An identification processing module, used to identify and classify the original point cloud data using the point cloud model, wherein the identification results include charged bodies, grounded bodies, and insulators; The calculation processing module is used to calculate the distance between each adjacent target object based on the spatial relationship expression of each target object in the point cloud model.

2. The target object ranging system based on deep learning point cloud classification algorithm according to claim 1, characterized in that: Also included is a hazardous area identification module; The hazardous area identification module is used to: When the current target object is identified as a charged object, the type of the current charged object is identified, and the database is called to match to obtain the voltage level safety distance information corresponding to the type of the current charged object; According to the type of the current charged object and the corresponding voltage level safety distance information, taking all edge points of the current charged object as the center of the point cloud and the safety distance value recorded in the voltage level safety distance information as the radius, multiple bounding boxes of the target object are extended outward; Finally, it is determined that the collective spatial range data corresponding to the current multiple bounding boxes is the dangerous area.

3. The target object ranging system based on deep learning point cloud classification algorithm as claimed in claim 2, characterized in that: It also includes a non-dangerous area identification module, which is used to determine that the spatial range data outside the set spatial range data corresponding to the current multiple bounding boxes corresponding to the current target object is marked as the non-dangerous area of ​​the current target object.

4. The target distance measurement system based on deep learning point cloud classification algorithm according to claim 3, characterized in that: It also includes a ground ranging module; The ground ranging module is used for: Identify the ground body corresponding to the original point cloud data; Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model; Calculate the relative distance between the current operator and the ground object or the grounding object based on the position information of the current operator in the point cloud model; Recording the relative position distance as the actual distance between the operator and the ground; Obtain the preset standard value of the operator's safety distance to the ground, compare the operator's actual distance to the ground with the standard value of the operator's safety distance to the ground to determine whether the current operator meets the safety operation standard.

5. The target distance measurement system based on deep learning point cloud classification algorithm according to claim 4, characterized in that: It also includes a minimum combined gap processing module; The minimum combined gap processing module is used for: Identify the ground body corresponding to the original point cloud data; Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model; Obtain the preset value of the minimum combined gap on the human body insulation ladder, compare the actual gap distance of the current insulation ladder with the value of the minimum combined gap on the human body insulation ladder, and determine whether the current insulation ladder meets the safety operation standards.

6. The target distance measurement system based on deep learning point cloud classification algorithm according to claim 5, characterized in that: Also included is a wire ranging processing module; The wire distance measurement processing module is used for: Identify the wires corresponding to the original point cloud data; Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model; Calculating the relative distance between the current operator and the adjacent wire based on the position information of the current operator in the point cloud model; The relative position distance is recorded as the actual distance of the adjacent wire to the wire by the operator; Obtain the preset standard value of the equipotential operator to the adjacent phase conductor, compare the actual distance of the adjacent conductor corresponding to the operator with the standard value of the equipotential operator to the adjacent phase conductor, and determine whether the current operator meets the safety operation standards.

7. The target distance measurement system based on deep learning point cloud classification algorithm according to claim 6, characterized in that: It also includes a charged body ranging processing module; The charged body distance measurement processing module is used for: Identify the charged body corresponding to the original point cloud data; Acquire the spatial position information of the current operator, and perform coordinate transformation according to the spatial position information to obtain the position information of the current operator in the point cloud model; Calculating the relative position distance between the current operator and the adjacent charged body based on the position information of the current operator in the point cloud model; The relative position distance is recorded as the actual distance between the operator and the adjacent charged body; Obtain the preset standard safety distance value between the human body and the charged object for the equipotential workers, compare the actual distance of the adjacent charged object corresponding to the worker with the standard safety distance value between the human body and the charged object for the equipotential workers, and determine whether the current worker meets the safety operation standards.

8. The target distance measurement system based on deep learning point cloud classification algorithm according to claim 7, characterized in that: Also includes a path planning processing module; The path planning processing module is used for: Receive the location information of the target operation point set and sent by the current operator, and then obtain the location information of the current location point of the current operator; The dangerous area of ​​the current target object is obtained, and a target planning path from the current position point of the current operator to the target operation point is planned to avoid the dangerous area of ​​the current target object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the target object ranging system based on the deep learning point cloud classification algorithm according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the target object ranging system based on the deep learning point cloud classification algorithm described in any one of claims 1 to 8 is implemented.

Images