CN115079182A - Method, apparatus, device, medium, and program product for determining packing state - Google Patents
Method, apparatus, device, medium, and program product for determining packing state Download PDFInfo
- Publication number
- CN115079182A CN115079182A CN202210497826.8A CN202210497826A CN115079182A CN 115079182 A CN115079182 A CN 115079182A CN 202210497826 A CN202210497826 A CN 202210497826A CN 115079182 A CN115079182 A CN 115079182A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- plane
- container
- trailer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/04—Systems determining the presence of a target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
Landscapes
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The present application provides a method, an apparatus, a device, a medium, and a program product for determining a packing state, the method including: after first point cloud data acquired by a first radar installed at the top of a tractor of a container truck and second point cloud data acquired by a second radar installed at the tail of a trailer of the container truck are acquired, target point cloud data are determined from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and structural parameters of the trailer, and when the point cloud number of the target point cloud data is larger than the preset point cloud number, a first plane of a container close to the tractor and a second plane of the container close to the tail of the trailer are obtained according to the target point cloud data, so that the position of the container is determined according to the first plane and the second plane. In the technical scheme, the container state is determined through the target point cloud data, and the accuracy of detecting the container state is effectively improved.
Description
Technical Field
The present application relates to the field of vehicle technologies, and in particular, to a method, an apparatus, a device, a medium, and a program product for determining a package status.
Background
Along with the gradual development of port intellectuality, more and more wharf operations can all be realized through intelligent container truck, and the effectual efficiency and the security that have promoted the wharf operation have reduced the human cost.
At present, an intelligent container truck consists of a tractor and a trailer, and the state of a container on the trailer needs to be accurately sensed in real time in the operation process so as to fulfill the aims of completing the wharf operation process and guaranteeing the operation safety. In the prior art, the real-time and accurate sensing of the container state on the trailer is mainly to acquire the container state on the trailer according to data of a container placement area of the trailer, which is acquired in real time by a detection device (such as a laser radar installed on a tractor or an ultrasonic wave or a pressure sensor installed on the trailer) installed on an intelligent truck.
However, when two containers exist on the trailer, the front box can shield the rear box, so that the prior art cannot accurately judge whether the rear box or the loading position of the rear box is arranged through the detection equipment, and the operation scene supported by the intelligent container truck is limited.
Disclosure of Invention
The application provides a method, a device, equipment, a medium and a program product for determining a packing state, which are used for solving the problem that whether a rear box or a loading position of the rear box is arranged cannot be accurately judged through detection equipment in the prior art, and the operation scene supported by an intelligent card concentrator is limited.
In a first aspect, an embodiment of the present application provides a method for determining a boxing state, including:
acquiring first point cloud data acquired by a first radar arranged at the top of a tractor of a collection card and second point cloud data acquired by a second radar arranged at the tail of a trailer of the collection card;
determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer, wherein the target point cloud data is point cloud data of an area for placing a container in the trailer;
when the point cloud number of the target point cloud data is larger than the preset point cloud number, obtaining a first plane of a container close to the tractor and a second plane of the container close to the tail of the trailer according to the target point cloud data;
determining a packing state including at least one of a loading position of the container, a number of the containers, and a packing type of the container according to the first plane and the second plane.
In a possible design of the first aspect, the determining, according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, target point cloud data from the first point cloud data and the second point cloud data includes:
converting the first point cloud data from a coordinate system of the first radar to a vehicle front coordinate system, and converting the second point cloud data from a coordinate system of the second radar to the vehicle front coordinate system to obtain initial point cloud data, wherein the vehicle front coordinate system is a coordinate system of the container truck;
determining the ROI of the container according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer;
determining initial point cloud data in the ROI as the target point cloud data.
Optionally, when the point cloud number of the target point cloud data is greater than a preset point cloud number, according to the target point cloud data, a first plane of the container close to the tractor and a second plane of the container close to the trailer tail are obtained, which includes:
when the point cloud number of the target point cloud data is larger than the preset point cloud number, deleting points, in the target point cloud data, of which the included angle between a normal vector and the X axis of the vehicle front coordinate system is larger than or equal to a preset angle, and acquiring third point cloud data;
extracting the first plane and the second plane from the third point cloud data using a RANSAC method.
Optionally, the extracting the first plane and the second plane from the third point cloud data by using a RANSAC method includes:
extracting a first initial plane from the third point cloud data by using a RANSAC method;
deleting points, with a distance smaller than a preset distance from the first initial plane, in the third point cloud data to obtain fourth point cloud data;
extracting a second initial plane from the fourth point cloud data by using a RANSAC method;
calculating a first intersection point of the first initial plane and the X axis of the vehicle front coordinate system and a second intersection point of the second initial plane and the X axis of the vehicle front coordinate system;
and determining the initial plane corresponding to the intersection point with the minimum coordinate absolute value as the first plane, and determining the initial plane corresponding to the intersection point with the maximum coordinate absolute value as the second plane.
In another possible design of the first aspect, the determining the position of the container according to the first plane and the second plane includes:
converting the first plane and the second plane into a trailer coordinate system according to the structural parameters of the trailer, and acquiring the first plane after coordinate conversion and the second plane after coordinate conversion;
and determining the boxing state according to the first plane after the coordinates are converted and the second plane after the coordinates are converted.
In yet another possible design of the first aspect, after determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, the method further includes:
and when the point cloud number of the target point cloud data is less than or equal to the preset point cloud number, determining that the container is not loaded on the trailer.
In a second aspect, an embodiment of the present application provides an apparatus for determining a package status, including:
the acquisition module is used for acquiring first point cloud data acquired by a first radar arranged at the top of a tractor of the container truck and second point cloud data acquired by a second radar arranged at the tail of a trailer of the container truck;
the processing module is used for determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer, wherein the target point cloud data is point cloud data of an area for placing a container in the trailer;
the processing module is further used for obtaining a first plane of the container close to the tractor and a second plane of the container close to the tail of the trailer according to the target point cloud data when the point cloud number of the target point cloud data is larger than the preset point cloud number;
the processing module is further configured to determine a packing status according to the first plane and the second plane, where the packing status includes at least one of a loading position of the container, a number of the containers, and a type of the container.
In a possible design of the second aspect, the processing module is specifically configured to:
converting the first point cloud data from a coordinate system of the first radar to a vehicle front coordinate system, and converting the second point cloud data from a coordinate system of the second radar to the vehicle front coordinate system to obtain initial point cloud data, wherein the vehicle front coordinate system is a coordinate system of the container truck;
determining the ROI of the container according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer;
determining initial point cloud data in the ROI as the target point cloud data.
Optionally, the processing module is specifically configured to:
when the point cloud number of the target point cloud data is larger than the preset point cloud number, deleting points, in the target point cloud data, of which the included angle between a normal vector and the X axis of the vehicle front coordinate system is larger than or equal to a preset angle, and acquiring third point cloud data;
extracting the first plane and the second plane from the third point cloud data using a RANSAC method.
Optionally, the processing module is specifically configured to:
extracting a first initial plane from the third point cloud data by using a RANSAC method;
deleting points, with a distance smaller than a preset distance from the first initial plane, in the third point cloud data to obtain fourth point cloud data;
extracting a second initial plane from the fourth point cloud data by using a RANSAC method;
calculating a first intersection point of the first initial plane and the X axis of the vehicle front coordinate system and a second intersection point of the second initial plane and the X axis of the vehicle front coordinate system;
and determining the initial plane corresponding to the intersection point with the minimum coordinate absolute value as the first plane, and determining the initial plane corresponding to the intersection point with the maximum coordinate absolute value as the second plane.
In another possible design of the second aspect, the processing module is specifically configured to:
converting the first plane and the second plane into a trailer coordinate system according to the structural parameters of the trailer, and acquiring the first plane after coordinate conversion and the second plane after coordinate conversion;
and determining the boxing state according to the first plane after the coordinates are converted and the second plane after the coordinates are converted.
In a possible design of the second aspect, after determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, the processing module is further configured to:
and when the point cloud number of the target point cloud data is less than or equal to the preset point cloud number, determining that the container is not loaded on the trailer.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory and computer program instructions stored on the memory and executable on the processor for implementing the method of the first aspect and each possible design when the processor executes the computer program instructions.
In a fourth aspect, embodiments of the present application may provide a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the method provided by the first aspect and each possible design.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a computer program that, when executed by a processor, is configured to implement the method provided by the first aspect and each possible design.
The method, apparatus, device, medium, and program product for determining a bin packing state provided in an embodiment of the present application, in the method: after first point cloud data acquired by a first radar installed at the top of a tractor of a container truck and second point cloud data acquired by a second radar installed at the tail of a trailer of the container truck are acquired, target point cloud data are determined from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and structural parameters of the trailer, and when the point cloud number of the target point cloud data is larger than the preset point cloud number, a first plane of a container close to the tractor and a second plane of the container close to the tail of the trailer are obtained according to the target point cloud data, so that the container loading state is determined according to the first plane and the second plane. Wherein the packing state includes at least one of a loading position of the container, a number of the containers, and a box type of the container. In the technical scheme, the target point cloud data of the area for placing the container in the trailer is determined from the first point cloud data and the second point cloud data, so that the position of the container is determined according to the target point cloud data, and the accuracy of detecting the state of the container is effectively improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic view of an application scenario of a method for determining a boxing state according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a first embodiment of a method for determining a boxing state according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a second embodiment of a method for determining a boxing state according to an embodiment of the present application;
fig. 4 is a schematic flowchart of a third embodiment of a method for determining a boxing state according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a device for determining a boxing state provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. The drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the disclosed concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The intelligent container truck is composed of a tractor and a trailer, and generally needs to accurately sense the container loading state on the trailer of a self-vehicle (namely the container truck) in real time in the operation process so as to complete the operation flow or ensure the operation safety.
In the prior art, the real-time accurate sensing of the container state on the trailer can be realized by the following modes:
(1) the data of the container area can be placed on the trailer which is collected in real time through the laser radar installed at the top of the tractor, and the container state on the trailer is obtained according to the data. However, the method cannot judge whether the rear box exists or not when the front box is shielded, and further cannot acquire the position of the rear box.
(2) On the basis of the above method, the sensor support can be heightened to make the laser radar higher than the container, so as to acquire the container state on the trailer. However, this method poses a great challenge to the stability of the stent, and has poor safety and high cost.
(3) The status of the container on the trailer is tracked by ultrasonic waves, pressure sensors mounted on the trailer, or based on external information (e.g., job instructions). However, the method can only judge whether the rear box exists or not, cannot well give the position of the rear box, is easily limited by an operation scene, and has high dependency on the operation scene.
In summary, the prior art can handle big case operation scene, but can not be fine handle small case operation scene, when having two containers on the trailer, because the back box can be sheltered from to the front box, leads to the state that can't accurately acquire the back box through check out test set, has the relatively poor problem of the degree of accuracy of the container state that detects.
Therefore, according to the method for determining the packing state provided by the application, the first radar is installed at the top of the tractor of the container truck, the second radar is installed at the tail of the trailer of the container truck, the first radar and the second radar can scan to obtain target point cloud data of an area, used for placing a container, in the trailer, so that a first plane, close to the tractor, of the container and a second plane, close to the tail of the trailer, of the container are obtained according to the target point cloud data, and the position of the container is obtained according to the first plane and the second plane through analysis. When two containers exist on the trailer, the first plane is the plane of the front box close to the tractor, and the second plane is the plane of the rear box close to the trailer tail, so that the container packing state is accurately acquired according to the first plane and the second plane, and the accuracy of the detected container state is improved.
For example, the method for determining the boxing state provided by the embodiment of the present application may be applied to an application scenario diagram shown in fig. 1. Fig. 1 is a schematic view of an application scenario of the method for determining a boxing state according to an embodiment of the present application, so as to solve the above technical problem. As shown in fig. 1, the application scenario may include: tractor 11, trailer 12, radar 13, radar 14, and electronics 15.
Wherein, the tractor 11 is used for controlling the trailer 12 to move, the trailer 12 is used for placing containers, the tractor 11 and the trailer 12 form a truck, and the truck in fig. 1 is a front view of the truck.
In this embodiment, the radar 13 is mounted on the head of the tractor 11 and the radar 14 is mounted on the tail of the trailer 12. The electronic device 15 may acquire the first point cloud data acquired by the radar 13 and may also acquire the second point cloud data acquired by the radar 14, and execute program codes of a method for determining a packing state, thereby determining the packing state of the trailer 12.
It should be understood that the electronic device may be a controller in a card collection, or may be a terminal device independent from the card collection, such as a mobile phone, a tablet computer, a notebook computer, etc. of a dispatcher, or may be a server, and the embodiment of the present application does not specifically limit the type of the electronic device. It may be determined as the case may be, whether the electronic device is specifically a controller, a terminal device, or a server in a card concentrator.
The technical solution of the present application will be described in detail below with reference to specific examples.
It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
Fig. 2 is a schematic flowchart of a first embodiment of a method for determining a boxing state according to an embodiment of the present application. As shown in fig. 2, the method for determining the packing status may include the steps of:
s201, acquiring first point cloud data acquired by a first radar installed at the top of a tractor of the collecting card and second point cloud data acquired by a second radar installed at the tail of a trailer of the collecting card.
Optionally, the first radar may be installed at the top of the tractor horizontally or vertically, and similarly, the second radar may be installed at the tail of the trailer horizontally or vertically, and the installation manner of the first radar and the second radar is not limited in the embodiment of the present application. The first radar is used for acquiring first point cloud data and sending the first point cloud data to the electronic equipment, and similarly, the second radar is used for acquiring second point cloud data and sending the second point cloud data to the electronic equipment. For the electronic device, first point cloud data sent by a first radar and second point cloud data sent by a second radar are received.
Optionally, the radar (i.e., the first radar and/or the second radar) may collect the point cloud data in real time, and may also collect the point cloud data according to a preset frequency, for example, the preset frequency may be 1 time per second, 2 times per second, 3 times per second, and the like, and may also collect the point cloud data when the truck body is straightened, and the point cloud data may be determined according to an actual situation, which is not limited in the embodiment of the present application.
Wherein the first radar may scan a plane of a container loaded on the trailer near the tractor and the second radar may scan a plane of a container loaded on the trailer near the trailer tail. Optionally, the containers may be the same or different containers.
Alternatively, the radar may be a multi-line laser radar, such as a 16-line mechanical laser radar, or may be another radar capable of acquiring point cloud data, which is not particularly limited.
Optionally, the radar and the electronic device may be connected by wireless communication or by physical lines.
S202, determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer.
The target point cloud data is point cloud data of an area for placing the container in the trailer.
It should be understood that the zones may or may not be loaded with containers. That is, when a container is loaded in the trailer, the target point cloud data is point cloud data of the container and point cloud data of a trailer part, and when no container is loaded in the trailer, the target point cloud data is point cloud data of the trailer part for placing a container area.
In the embodiment Of the application, the first point cloud data and the second point cloud data comprise point cloud data Of an area in the trailer for placing the container and point cloud data Of other areas Of the trailer, so that the first point cloud data and the second point cloud data can be respectively converted into a vehicle front coordinate system to obtain initial point cloud data, a Region Of Interest (ROI) Of the container is determined according to the pose Of the first radar, the pose Of the second radar and the structural parameters Of the trailer, the ROI is the area in the trailer for placing the container, and the initial point cloud data in the ROI is determined as target point cloud data.
The ROI refers to a region needing to be processed and is delineated in a square frame, circle, ellipse, irregular polygon and other modes, and by determining the ROI, point cloud data in the ROI region can be analyzed and processed in a targeted mode, so that subsequent processing time and processing resources are reduced, and processing accuracy is improved.
Alternatively, the structural parameters of the trailer may be the size, shape, height, etc. of the trailer.
For specific implementation of this step, reference may be made to the following description in the embodiment shown in fig. 3, which is not described herein again.
And S203, when the point cloud number of the target point cloud data is larger than the preset point cloud number, obtaining a first plane of the container close to the tractor and a second plane of the container close to the tail of the trailer according to the target point cloud data.
Optionally, the number of the preset point clouds may be 50, 60, 70, and the like, and may be determined according to actual situations, which is not specifically limited in the embodiment of the present application.
In an implementation manner, a point in the target point cloud data, where an included angle between a normal vector and an X-axis of a vehicle front coordinate system is greater than or equal to a preset angle, may be deleted, to obtain third point cloud data, and a Random Sample Consensus (RANSAC) method is used to extract the first plane and the second plane from the third point cloud data, so as to improve accuracy and efficiency of extracting the first plane and the second plane.
For example, the preset angle may be 10 degrees, 12 degrees, 14 degrees, and the like, and may be determined according to actual situations, which is not specifically limited in the embodiment of the present application.
For specific implementation of extracting the first plane and the second plane from the third point cloud data by using the RANSAC method, reference may be made to the following description in the embodiment shown in fig. 4, and details are not repeated here.
And S204, determining the boxing state according to the first plane and the second plane.
Wherein the packing state includes at least one of a loading position of the container, a number of the containers, and a box type of the container.
In a possible implementation manner, the first plane and the second plane may be converted to a trailer coordinate system according to the structural parameters of the trailer, and the first plane after the coordinates are converted and the second plane after the coordinates are converted are obtained. And then, determining the position of the container according to the first plane after the coordinate conversion and the second plane after the coordinate conversion, so that the loading position of the rear box can still be accurately obtained under the condition that the front box is shielded.
The trailer coordinate system refers to a coordinate system where the trailer is located, the origin of the coordinate system can be the position closest to the tractor in an area for placing a container in the trailer, the X axis is parallel to the ground and extends backwards along the tail of the trailer in the positive direction, the Y axis is parallel to the ground and extends outwards in the positive direction perpendicular to the X axis, and the Z axis is perpendicular to the ground and extends away from the ground in the positive direction. Optionally, the position closest to the tractor in the area for placing the container in the trailer may be obtained through real-time detection, a card collecting structure drawing or measurement calculation, which is not specifically limited in this application.
The X coordinate of the first plane after the coordinate conversion may be used as a first distance, the X coordinate of the second plane after the coordinate conversion may be used as a second distance, and the position of the container may be determined according to the first distance and the second distance.
Optionally, the box type of the container may also be determined according to the first distance and the second distance. The container type of the container comprises a large container, a middle container and small containers, wherein the trailer can be used for placing one large container, or one middle container, or at most two small containers, the small container close to the tractor is a front container, and the small container close to the tail part of the trailer is a rear container.
For example, determining the number and the type of the container based on the first distance and the second distance may include the following:
(1) and when the first distance is greater than the front box position threshold value and the difference value between the first distance and the second distance is less than or equal to the small box length threshold value, determining that the front box exists in the position of the container.
Illustratively, the headbox position threshold is related to the truck operating environment and trailer configuration, and is typically less than half a canister length, for example, the headbox position threshold may be 3 meters at a container terminal. It should be understood that the front box position threshold may also be other values, which are not specifically limited by the embodiment of the present application.
Illustratively, the small box length threshold may be a length smaller than that of the standard small box, wherein the length of the standard small box may be 6.058 meters, for example, the small box length threshold may be a length of 3 meters to 5 meters, such as 3 meters, 4 meters, 5 meters, etc., which is not limited in this application. When the small box length threshold value is smaller than the length of the standard small box, the robustness of calculation can be effectively improved.
(2) And when the first distance is greater than the front box position threshold value and the difference value between the first distance and the second distance is greater than the large box length threshold value, the front box and the rear box or the large box are positioned in the container. Since the standard 40-inch large box is 12.192 meters long and the standard 45-inch large box is 13.716 meters long, the large box length threshold may be a value between 9 meters and 11 meters, such as 9 meters, 10 meters, 11 meters, etc., which is not specifically limited in this application.
(3) And when the first distance is greater than or equal to the rear box position threshold value, the position of the container is the storage rear box. Wherein, the rear box position threshold and the front box position threshold may have the following relationship: the rear box position threshold + 6.058.
(4) And when the first distance is greater than the front box position threshold value and the first distance is less than the rear box position threshold value, the position of the container is the existence of the middle box.
In this step, the box type and position of each container may be determined by a first plane and a second plane, for example, it may be determined that a middle box is loaded in the trailer 2 meters from the origin of the trailer coordinate system, or that two small boxes are loaded in the trailer, the first plane of the front box being 1.5 meters from the origin of the trailer coordinate system, the second plane of the rear box being 6 meters from the origin of the trailer coordinate system, etc.
According to the method for determining the packing state, after first point cloud data acquired by a first radar installed at the top of a tractor of a container truck and second point cloud data acquired by a second radar installed at the tail of a trailer of the container truck are acquired, target point cloud data are determined from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and structural parameters of the trailer, and when the point cloud number of the target point cloud data is larger than the preset point cloud number, a first plane of a container close to the tractor and a second plane of the container close to the tail of the trailer are obtained according to the target point cloud data, so that the packing state is determined according to the first plane and the second plane. In the technical scheme, the target point cloud data of the area for placing the container in the trailer is determined from the first point cloud data and the second point cloud data, so that the container loading state is determined according to the target point cloud data, and the accuracy of detecting the container loading state is effectively improved. In the method, only the first radar needs to be installed at the top of the tractor, the second radar needs to be installed at the tail of the trailer, the radars do not need to be heightened, the problem that the support is too high and is easy to collide or the problem of radar shaking caused by infirm is avoided, and the safety and the stability of the detection process are guaranteed.
Optionally, on the basis of any one of the above embodiments, fig. 3 is a schematic flow diagram of a second embodiment of the method for determining a boxing state provided in the embodiment of the present application. As shown in fig. 3, S202 may be implemented by:
s301, converting the first point cloud data from a coordinate system where the first radar is located to a vehicle front coordinate system, and converting the second point cloud data from a coordinate system where the second radar is located to the vehicle front coordinate system to obtain initial point cloud data.
Wherein, the front coordinate system is the coordinate system of the container truck.
The coordinate systems of the radar and the container truck are different, the coordinate system of the radar is determined by the position and the attitude of the radar, and after the radar is installed, the coordinate system of the radar is uniquely determined. The vehicle front coordinate system is typically a right hand coordinate system defined in terms of the hub location, and may have an origin at which the center of the forward-most end of the vehicle head is located, an X axis parallel to the ground and extending forward along the front of the hub head, a Y axis parallel to the ground and extending outward in a forward direction perpendicular to the X axis, and a Z axis perpendicular to the ground and extending forward away from the ground.
S302, determining the ROI of the container according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer.
The radar has a wide acquisition range, and the acquired point cloud comprises point cloud data of an area for placing a container in the trailer and point cloud data of other areas of the trailer. Therefore, the ROI of the container can be obtained through division according to the pose of the first radar, the position of the second radar and the structural parameters of the trailer, the ROI is an area for placing the container in the trailer, and the ROI can better reflect the space range of the container.
It should be understood that the following principles need to be satisfied when determining the RoI:
(1) ensuring that the RoI can cover the position range where the container can appear;
(2) the possible inclusion of miscellaneous points on non-container objects is minimized.
Wherein, the coordinate range of the ROI is the maximum value and the minimum value of the ROI on the X, Y, Z axis of the plantago coordinate system.
For example, the maximum value (max _ X) of the X-axis may be the position closest to the tractor in the area of the trailer for placing the container, and the minimum value (min _ X) of the X-axis may have the following relationship with max _ X: min _ x-trailer length, the maximum value on the Z-axis (max _ Z) may be trailer height plus a preset height, and the minimum value on the Z-axis (min _ Z) may be trailer height.
The position, the trailer length and the trailer height of the area, which is used for placing the container, of the trailer and is closest to the tractor can be obtained through real-time detection, a card collecting structure drawing or measurement calculation.
For example, the preset height may be determined according to the height of the container, such as 2 meters. It should be understood that the preset height may be other heights, and the embodiment of the present application is not particularly limited thereto.
And S303, determining the initial point cloud data in the ROI as target point cloud data.
In the embodiment of the application, the first point cloud data are converted from a coordinate system where the first radar is located to a coordinate system in front of a vehicle, the second point cloud data are converted from the coordinate system where the second radar is located to the coordinate system in front of the vehicle, initial point cloud data are obtained, the ROI of the container is determined according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer, and therefore the initial point cloud data in the ROI are determined to be target point cloud data. In the technical scheme, redundant point cloud data in the first point cloud data and the second point cloud data are removed, so that target point cloud data of the ROI are obtained, and the efficiency and the precision of subsequent processing are effectively improved.
Optionally, on the basis of any one of the above embodiments, fig. 4 is a schematic flow chart of a third embodiment of the method for determining a boxing state provided in the embodiment of the present application. As shown in fig. 4, extracting the first plane and the second plane from the third point cloud data using the RANSAC method in S203 may be implemented by:
s401, extracting a first initial plane from the third point cloud data by using a RANSAC method.
Wherein, the interior point threshold value when using RANSAC method can be 0.2 meter.
S402, deleting the points, with the distance from the first initial plane being smaller than the preset distance, in the third point cloud data, and obtaining fourth point cloud data.
The preset distance may be 0.5 m, 0.6 m, 0.7 m, and the like, which may be limited by actual conditions, and this is not specifically limited in the embodiment of the present application.
And deleting redundant point cloud data in the third point cloud data through a preset distance, so that the efficiency and the accuracy of subsequent processing are improved.
And S403, extracting a second initial plane from the fourth point cloud data by using a RANSAC method.
Wherein, the interior point threshold value when using RANSAC method can be 0.2 meter.
S404, calculating a first intersection point of the first initial plane and the X axis of the vehicle front coordinate system and a second intersection point of the second initial plane and the X axis of the vehicle front coordinate system.
S405, determining the initial plane corresponding to the intersection point with the minimum coordinate absolute value as a first plane, and determining the initial plane corresponding to the intersection point with the maximum coordinate absolute value as a second plane.
In the above-described embodiment, the first plane and the second plane are extracted from the third point cloud data by the RANSAC method, so that the accuracy of extracting the first plane and the second plane is improved, and the accuracy of the bin state determined from the first plane and the second plane is further improved.
Optionally, in some embodiments, after determining the target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, the method for determining the bin packing state may further include the following steps:
and when the point cloud number of the target point cloud data is less than or equal to the preset point cloud number, determining that the container is not loaded on the trailer.
That is, when the point cloud number of the target point cloud data is less than or equal to the preset point cloud number, it is indicated that only the point cloud data of the trailer part is included in the target point cloud data, and the point cloud data of the container is not included.
According to the technical scheme, whether the container is loaded in the trailer or not is judged according to the point cloud number of the target point cloud data, so that the accuracy of determining the position of the container is improved.
The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
Fig. 5 is a schematic structural diagram of a device for determining a boxing state according to an embodiment of the present application. As shown in fig. 5, the device for determining the packing state includes:
the acquisition module 51 is used for acquiring first point cloud data acquired by a first radar installed at the top of a tractor of the truck and second point cloud data acquired by a second radar installed at the tail of a trailer of the truck;
the processing module 52 is configured to determine target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, where the target point cloud data is point cloud data of an area in the trailer where the container is placed;
the processing module 52 is further configured to, when the point cloud number of the target point cloud data is greater than the preset point cloud number, obtain a first plane of the container near the tractor and a second plane of the container near the trailer tail according to the target point cloud data;
the processing module 52 is further configured to determine a packing status according to the first plane and the second plane, wherein the packing status includes at least one of a loading position of the container, a number of the containers, and a type of the container.
In one possible design of this embodiment of the present application, the processing module 52 is specifically configured to:
converting the first point cloud data from a coordinate system of a first radar to a vehicle front coordinate system, and converting the second point cloud data from a coordinate system of a second radar to a vehicle front coordinate system to obtain initial point cloud data, wherein the vehicle front coordinate system is a coordinate system of a container truck;
determining an ROI (region of interest) of the container according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer;
the initial point cloud data in the ROI is determined as target point cloud data.
Optionally, the processing module 52 is specifically configured to:
when the point cloud number of the target point cloud data is larger than the preset point cloud number, deleting points of which the included angle between the normal vector in the target point cloud data and the X axis of the vehicle front coordinate system is larger than or equal to the preset angle, and acquiring third point cloud data;
the first plane and the second plane are extracted from the third point cloud data using the RANSAC method.
Optionally, the processing module 52 is specifically configured to:
extracting a first initial plane from the third point cloud data by using a RANSAC method;
deleting points, with a distance smaller than a preset distance from the first initial plane, in the third point cloud data to obtain fourth point cloud data;
extracting a second initial plane from the fourth point cloud data by using a RANSAC method;
calculating a first intersection point of the first initial plane and the X axis of the vehicle front coordinate system and a second intersection point of the second initial plane and the X axis of the vehicle front coordinate system;
and determining the initial plane corresponding to the intersection point with the minimum coordinate absolute value as a first plane, and determining the initial plane corresponding to the intersection point with the maximum coordinate absolute value as a second plane.
In another possible design of the embodiment of the present application, the processing module 52 is specifically configured to:
converting the first plane and the second plane into a trailer coordinate system according to the structural parameters of the trailer, and acquiring the first plane after coordinate conversion and the second plane after coordinate conversion;
and determining the boxing state according to the first plane after the coordinates are converted and the second plane after the coordinates are converted.
In another possible design of the embodiment of the present application, after determining the target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, the processing module 52 is further configured to:
and when the point cloud number of the target point cloud data is less than or equal to the preset point cloud number, determining that the container is not loaded on the trailer.
The device for determining the boxing state provided by the embodiment of the application can be used for executing the method for determining the boxing state in any embodiment, and the implementation principle and the technical effect are similar, and are not described herein again.
It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element here may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device 15 may include: a processor 61, a memory 62 and computer program instructions stored on the memory 62 and executable on the processor 61, the processor 61 implementing the method of determining a bin state provided by any of the previous embodiments when executing the computer program instructions.
Alternatively, the above devices of the electronic device 15 may be connected by a system bus.
The memory 62 may be a separate memory unit or a memory unit integrated into the processor. The number of processors is one or more.
Optionally, the electronic device 15 may also include interfaces to interact with other devices.
It should be understood that the Processor 61 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor, or in a combination of the hardware and software modules in the processor.
The system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The memory may include a Random Access Memory (RAM) and may also include a non-volatile memory (NVM), such as at least one disk memory.
All or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The aforementioned program may be stored in a readable memory. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state disk, magnetic tape (magnetic tape), floppy disk (optical disc), and any combination thereof.
The electronic device provided in the embodiment of the present application may be configured to execute the method for determining a boxing state provided in any method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
Embodiments of the present application provide a computer-readable storage medium, in which computer instructions are stored, and when the computer instructions are executed on a computer, the computer is caused to execute the method for determining a bin state.
The computer readable storage medium may be any type of volatile or non-volatile storage device or combination thereof, such as static random access memory, electrically erasable programmable read only memory, magnetic storage, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
Alternatively, a readable storage medium may be coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Embodiments of the present application further provide a computer program product, which includes a computer program stored in a computer-readable storage medium, from which the computer program can be read by at least one processor, and the at least one processor can implement the method for determining the bin state.
It will be understood that the present disclosure 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 present disclosure is limited only by the appended claims.
Claims (10)
1. A method for determining a packaging status, comprising:
acquiring first point cloud data acquired by a first radar arranged at the top of a tractor of a collection card and second point cloud data acquired by a second radar arranged at the tail of a trailer of the collection card;
determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer, wherein the target point cloud data is point cloud data of an area for placing a container in the trailer;
when the point cloud number of the target point cloud data is larger than the preset point cloud number, obtaining a first plane of a container close to the tractor and a second plane of the container close to the tail of the trailer according to the target point cloud data;
determining a packing state according to the first plane and the second plane, wherein the packing state comprises at least one of the loading position of the container, the number of the containers and the packing type of the container.
2. The method of claim 1, wherein determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer comprises:
converting the first point cloud data from a coordinate system of the first radar to a vehicle front coordinate system, and converting the second point cloud data from the coordinate system of the second radar to the vehicle front coordinate system to obtain initial point cloud data, wherein the vehicle front coordinate system is a coordinate system of the container truck;
determining an ROI (region of interest) of the container according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer;
determining initial point cloud data in the ROI as the target point cloud data.
3. The method according to claim 2, wherein when the point cloud number of the target point cloud data is greater than a preset point cloud number, obtaining a first plane of a container close to the tractor and a second plane of the container close to the trailer tail according to the target point cloud data comprises:
when the point cloud number of the target point cloud data is larger than the preset point cloud number, deleting points, in the target point cloud data, of which the included angle between a normal vector and the X axis of the vehicle front coordinate system is larger than or equal to a preset angle, and acquiring third point cloud data;
and extracting the first plane and the second plane from the third point cloud data by using a random sample consensus (RANSAC) method.
4. The method of claim 3, wherein the extracting the first plane and the second plane from the third point cloud data using a RANSAC method comprises:
extracting a first initial plane from the third point cloud data by using a RANSAC method;
deleting points, with a distance smaller than a preset distance from the first initial plane, in the third point cloud data to obtain fourth point cloud data;
extracting a second initial plane from the fourth point cloud data by using a RANSAC method;
calculating a first intersection point of the first initial plane and the X axis of the vehicle front coordinate system and a second intersection point of the second initial plane and the X axis of the vehicle front coordinate system;
and determining the initial plane corresponding to the intersection point with the minimum coordinate absolute value as the first plane, and determining the initial plane corresponding to the intersection point with the maximum coordinate absolute value as the second plane.
5. The method of claim 1, wherein said determining the location of the container from the first plane and the second plane comprises:
converting the first plane and the second plane into a trailer coordinate system according to the structural parameters of the trailer, and acquiring the first plane after coordinate conversion and the second plane after coordinate conversion;
and determining the boxing state according to the first plane after the coordinates are converted and the second plane after the coordinates are converted.
6. The method of any one of claims 1 to 5, wherein after determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar, and the structural parameters of the trailer, the method further comprises:
and when the point cloud number of the target point cloud data is less than or equal to the preset point cloud number, determining that the container is not loaded on the trailer.
7. An apparatus for determining a container state, comprising:
the acquisition module is used for acquiring first point cloud data acquired by a first radar arranged at the top of a tractor of the container truck and second point cloud data acquired by a second radar arranged at the tail of a trailer of the container truck;
the processing module is used for determining target point cloud data from the first point cloud data and the second point cloud data according to the pose of the first radar, the pose of the second radar and the structural parameters of the trailer, wherein the target point cloud data is point cloud data of an area for placing a container in the trailer;
the processing module is further used for obtaining a first plane of the container close to the tractor and a second plane of the container close to the tail of the trailer according to the target point cloud data when the point cloud number of the target point cloud data is larger than the preset point cloud number;
the processing module is further configured to determine a packing status according to the first plane and the second plane, where the packing status includes at least one of a loading position of the container, a number of the containers, and a type of the container.
8. An electronic device, comprising: processor, memory and computer program instructions stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program instructions, is adapted to carry out the method of determining a bin state according to any of claims 1 to 6.
9. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of determining a bin state of any one of claims 1 to 6 when executed by a processor.
10. A computer program product comprising a computer program for implementing a method of determining a bin status according to any one of claims 1 to 6 when the computer program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210497826.8A CN115079182A (en) | 2022-05-06 | 2022-05-06 | Method, apparatus, device, medium, and program product for determining packing state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210497826.8A CN115079182A (en) | 2022-05-06 | 2022-05-06 | Method, apparatus, device, medium, and program product for determining packing state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115079182A true CN115079182A (en) | 2022-09-20 |
Family
ID=83248169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210497826.8A Pending CN115079182A (en) | 2022-05-06 | 2022-05-06 | Method, apparatus, device, medium, and program product for determining packing state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115079182A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024104192A1 (en) * | 2022-11-16 | 2024-05-23 | 上海西井科技股份有限公司 | Point cloud-based lifting appliance secondary anchoring method, system and device, and storage medium |
-
2022
- 2022-05-06 CN CN202210497826.8A patent/CN115079182A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024104192A1 (en) * | 2022-11-16 | 2024-05-23 | 上海西井科技股份有限公司 | Point cloud-based lifting appliance secondary anchoring method, system and device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109188438B (en) | Yaw angle determination method, device, equipment and medium | |
| CN113376654B (en) | Method and device for detecting anti-smashing of integrated card based on three-dimensional laser and computer equipment | |
| WO2022142628A1 (en) | Point cloud data processing method and device | |
| CN112513679B (en) | Target identification method and device | |
| CN109190573A (en) | A kind of ground detection method, apparatus, electronic equipment, vehicle and storage medium | |
| CN112560800A (en) | Road edge detection method, device and storage medium | |
| CN109828250B (en) | Radar calibration method, calibration device and terminal equipment | |
| CN114677410A (en) | Obstacle ranging method, mobile robot, equipment and medium | |
| CN115079182A (en) | Method, apparatus, device, medium, and program product for determining packing state | |
| CN112465908B (en) | Object positioning method, device, terminal equipment and storage medium | |
| CN112799091A (en) | Algorithm evaluation method, device and storage medium | |
| WO2023179718A1 (en) | Point cloud processing method and apparatus for lidar, and device and storage medium | |
| CN113247769A (en) | Truck positioning method, positioning system thereof and shore bridge | |
| US12046008B2 (en) | Pose calibration method, robot and computer readable storage medium | |
| CN112036274A (en) | Driving region detection method and device, electronic equipment and storage medium | |
| CN114219770A (en) | Ground detection method, ground detection device, electronic equipment and storage medium | |
| CN115728734A (en) | Laser radar shielding detection method and device, storage medium and laser radar | |
| CN117890878A (en) | Filtering method and device for two-dimensional laser point cloud, electronic equipment and storage medium | |
| CN117496515A (en) | Point cloud data labeling method, storage medium and electronic equipment | |
| CN110542422B (en) | Robot positioning method, device, robot and storage medium | |
| CN111868562B (en) | Object detection device, vehicle, object detection method, and computer-readable recording medium | |
| CN115457506A (en) | Target detection method, device and storage medium | |
| CN113345023B (en) | Box positioning method and device, medium and electronic equipment | |
| CN116002529A (en) | Alignment method, system, equipment and storage medium based on lifting equipment characteristics | |
| EP4361958A1 (en) | Ground point cloud segmentation method and apparatus, and autonomous vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |