CN114399550A - Automobile saddle extraction method and system based on three-dimensional laser scanning - Google Patents
Automobile saddle extraction method and system based on three-dimensional laser scanning Download PDFInfo
- Publication number
- CN114399550A CN114399550A CN202210056734.6A CN202210056734A CN114399550A CN 114399550 A CN114399550 A CN 114399550A CN 202210056734 A CN202210056734 A CN 202210056734A CN 114399550 A CN114399550 A CN 114399550A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- vehicle
- cloud data
- saddle
- target
- 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.)
- Granted
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 40
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 76
- 239000010959 steel Substances 0.000 claims abstract description 76
- 238000011068 loading method Methods 0.000 claims abstract description 16
- 238000012163 sequencing technique Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides an automobile saddle extraction method and an automobile saddle extraction system based on three-dimensional laser scanning, which comprise the following steps: carrying out three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data; segmenting the vehicle point cloud data to obtain vehicle body point cloud data; projecting the vehicle body point cloud data to obtain four projected corner coordinates; extracting the point cloud of the vehicle bottom plane, and cutting the vehicle bottom plane according to the point cloud of the vehicle bottom plane; cutting off the plane point cloud of the side plate of the automobile body according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data; projecting the target point cloud data, and extracting a straight line in the current projection; and sequencing the extracted straight lines, and pairing the sequenced straight lines in pairs under a preset constraint condition to generate a projection straight line of the saddle. According to the invention, the automobile saddle piece is automatically identified and extracted, so that the unmanned steel coil loading can be completed, and the saddle does not need to be pre-calibrated, so that the target saddle can be accurately extracted.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to an automobile saddle extraction method and an automobile saddle extraction system based on three-dimensional laser scanning.
Background
Heavy-duty warehouse logistics transport vehicle types are numerous, and there are single base plane trailer, the many base plane trailer of height board, van-type trailer etc. commonly, and each type of heavy-duty warehouse logistics transport vehicle can place the saddle temporarily at the vehicle bottom plane usually when carrying out the coil of strip transportation, then utilizes these saddles to fix the coil of strip. Common saddle models include two-piece, four-piece, six-piece, etc., and each type of saddle can be abstracted as a saddle including two saddle planes on the left and right. At present, steel coils of a heavy-duty warehouse are loaded in a manual mode and an automatic loading method based on pre-calibration. The manual mode needs the driver and cooperates the handling of carrying out the coil of strip with the ground commander usually and places the operation, has to observe positioning error great, and staff's safety guarantee hangs down the key problem. The pre-calibration automatic loading mode needs to calibrate coordinates of a saddle on each vehicle in advance, record the relative position of the saddle, then detect the actual coordinates of the whole vehicle, and calculate the actual coordinates of the saddle based on the actual coordinates of the vehicle and the pre-recorded relative position of the saddle. The pre-calibration automatic loading mode has the following defects: 1) due to the large diameter difference of the materials, the accurate calculation of the Z coordinate of the target position of the loaded steel coil cannot be realized; 2) the trailer is replaced by a trailer hook or a logistics transport company is used for replacing a vehicle, the tedious calibration needs to be carried out again, or the safety risk exists; 3) the product outgoing logistics of the finished product warehouse are usually non-fixed vehicles, complicated calibration needs to be carried out for each delivery, and the calibration result has no subsequent utilization value.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention provides a method and a system for extracting a saddle of a vehicle based on three-dimensional laser scanning, which are used for solving the problems in the prior art when loading a steel coil.
To achieve the above and other related objects, the present invention provides a method for extracting a saddle of a vehicle based on three-dimensional laser scanning, comprising the steps of:
carrying out three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data of the target vehicle;
segmenting the vehicle point cloud data to obtain vehicle body point cloud data of the target vehicle;
projecting the vehicle body point cloud data along the parallel surface of the bottom surface of the vehicle body of the target vehicle, and acquiring four projected corner point coordinates;
extracting vehicle bottom plane point clouds from the vehicle body point cloud data, and cutting off a vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data;
projecting the target point cloud data along the midperpendicular of the target vehicle parking direction, and extracting a straight line in the current projection;
sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under a preset constraint condition to generate projection straight lines of one or more saddles; wherein the preset constraint condition comprises: an angle constraint and a distance constraint.
Optionally, the method further comprises: segmenting the point cloud data for the one or more saddles from the target point cloud data according to projected straight lines of the one or more saddles.
Optionally, the method further comprises: after the target point cloud data is projected along the middle vertical line of the target vehicle parking direction, extracting a curve from the corresponding projection to be used as a projection line of a steel coil; and segmenting the point cloud data of the steel coil from the target point cloud data according to the projection line of the steel coil.
Optionally, the method further comprises: establishing a reference coordinate system by taking the ground as a plane where an x axis and a y axis are located and taking an axis vertical to the ground as a z axis;
acquiring an included angle alpha between the central axis of the target vehicle in the parking direction and the x axis;
after the bottom plane of the car is cut off, the projected four angular point coordinates are rotated around the z axis by an angle alpha and are parallel to the x axis, the point cloud of the plane of the side plate of the car body is cut off through straight-through filtering, and the residual point cloud data only containing the steel coil point cloud and the saddle point cloud is used as target point cloud data.
Optionally, the target vehicle comprises at least: a vehicle loaded with a coil and a saddle at the same time, a vehicle for loading a coil and having a saddle already present, a vehicle for loading a coil and having no saddle present.
Optionally, the target vehicle is located within a target area; the target area includes at least: and (4) parking areas when the vehicle loads and unloads the steel coil.
Optionally, the saddle comprises at least one of: two-piece type saddle, four-piece type saddle, six-piece type saddle.
The invention also provides an automobile saddle extraction system based on three-dimensional laser scanning, which comprises:
the scanning module is used for carrying out three-dimensional laser scanning on a target vehicle to generate vehicle point cloud data of the target vehicle;
the segmentation module is used for segmenting the vehicle point cloud data to generate vehicle body point cloud data of the target vehicle;
the first projection module is used for projecting the vehicle body point cloud data along a parallel plane of the bottom surface of the vehicle body of the target vehicle;
the cutting module is used for extracting vehicle bottom plane point clouds from the vehicle body point cloud data and cutting the vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to four angular point coordinates in the projection output by the first projection module, and taking the remaining point cloud data as target point cloud data;
the second projection module is used for projecting the target point cloud data along the midperpendicular of the parking direction of the target vehicle;
a saddle projection extraction module used for extracting straight lines from the projection output by the second projection module, sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under the preset constraint condition to generate one or more saddle projection straight lines; wherein the preset constraint condition comprises: an angle constraint and a distance constraint.
Optionally, the system further comprises a saddle point cloud extraction module for segmenting the point cloud data of the one or more saddles from the target point cloud data according to projected straight lines of the one or more saddles.
Optionally, the system further comprises: the steel coil projection extraction module is used for extracting a curve from the projection output by the second projection module as a projection line of the steel coil;
and the steel coil point cloud extraction module is used for segmenting the point cloud data of the steel coil from the target point cloud data according to the projection line of the steel coil.
As described above, the invention provides an automobile saddle extraction method and system based on three-dimensional laser scanning, which has the following beneficial effects:
firstly, carrying out three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data of the target vehicle; then, the vehicle point cloud data are segmented, and vehicle body point cloud data of the target vehicle are obtained; projecting the vehicle body point cloud data along the parallel surface of the bottom surface of the vehicle body of the target vehicle, and acquiring four projected corner point coordinates; extracting vehicle bottom plane point clouds from the vehicle body point cloud data, and cutting off a vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data; projecting the target point cloud data along the middle vertical line of the target vehicle parking direction, and extracting a straight line in the current projection; finally, sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under the preset constraint condition to generate the projection straight lines of one or more saddles; wherein the preset constraint condition comprises: an angle constraint and a distance constraint. According to the invention, the automobile saddle piece is automatically identified and extracted by utilizing the projection straight line of the saddle, so that the steel coil unmanned loading operation can be completed, and the saddle does not need to be pre-calibrated, so that the saddle parameters can be accurately calculated and the target saddle can be extracted, and the requirements of an intelligent storage system on the quick, reliable and safe delivery of transportation vehicles of various non-standardized automobile types and composite saddles are met.
Drawings
FIG. 1 is a schematic flow chart of a three-dimensional laser scanning-based automobile saddle piece extraction method provided by an embodiment;
FIG. 2 is a schematic flow chart of a three-dimensional laser scanning-based automobile saddle piece extraction method according to another embodiment;
FIG. 3 is a schematic diagram illustrating the location and orientation of a laser scanner and a target vehicle in a reference coordinate system according to an embodiment;
FIG. 4 is a schematic diagram illustrating a relationship between four corner points in a point cloud ground projection of a vehicle body and an included angle between a central axis of the vehicle and an x-axis in a reference coordinate system according to an embodiment;
FIG. 5 is a schematic view of a projection line of saddle point cloud data and steel coil point cloud data along a vertical plane in a vehicle body direction according to an embodiment;
FIG. 6 is a schematic hardware structure diagram of a three-dimensional laser scanning-based automobile saddle piece extraction system provided by an embodiment.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Referring to fig. 1, the present embodiment provides a method for extracting a vehicle saddle based on three-dimensional laser scanning, which includes the following steps:
s100, carrying out three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data of the target vehicle. The target vehicles in this embodiment include, but are not limited to, vehicles that are loaded with steel coils and saddles at the same time, vehicles that are used to load steel coils and have saddles present, vehicles that are used to load steel coils and have no saddles present. Wherein the target vehicle is located within the target area; the target area in this embodiment includes, but is not limited to, a parking area when the vehicle is handling a steel coil. As an example, the present embodiment may perform three-dimensional laser scanning on vehicles in a designated area based on a 3D scanner correctly installed in a logistics transportation scene, and then use the acquired 3D point cloud data as vehicle point cloud data of a corresponding vehicle. Specifically, the designated area may refer to a parking space defined in the storage area for loading and unloading the vehicle when the steel coil is loaded and unloaded and a margin area thereof, and the collected point cloud data in the area may be point cloud data including the steel coil transportation vehicle collected after the vehicle is parked when the steel coil is unloaded from the storage.
And S200, segmenting the vehicle point cloud data to obtain the vehicle body point cloud data of the target vehicle. In this embodiment, the manner of segmenting the vehicle point cloud data may adopt the prior art, and this embodiment is not described again.
And S300, projecting the vehicle body point cloud data along the parallel surface of the bottom surface of the vehicle body of the target vehicle, and acquiring four projected corner point coordinates. As an example, the present embodiment projects the obtained vehicle body point cloud to the ground plane, extracts the outer contour of the projection plane, and identifies and calculates coordinates (x) of four corner points of the outer contourA，yA)、(xB，yB)、(xC，yC)、(xD，yD) And an included angle alpha between the parking central axis of the vehicle and the x axis.
S400, extracting vehicle bottom plane point clouds from the vehicle body point cloud data, and cutting off a vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; and after the vehicle bottom plane is cut off, cutting off the vehicle body side plate plane point cloud according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data. As an example, in the embodiment, the ground is taken as a plane where an x axis and a y axis are located, and an axis perpendicular to the ground is taken as a z axis, so as to establish a reference coordinate system; acquiring an included angle alpha between the central axis of the target vehicle in the parking direction and the x axis; after the bottom plane of the car is cut off, the projected four angular point coordinates are rotated around the z axis by an angle alpha and are parallel to the x axis, the point cloud of the plane of the side plate of the car body is cut off through straight-through filtering, and the residual point cloud data only containing the steel coil point cloud and the saddle point cloud is used as target point cloud data.
S500, projecting the target point cloud data along the midperpendicular of the parking direction of the target vehicle, and extracting a straight line in the current projection. As an example, in the present embodiment, target point cloud data (which may include two, four, six, and other types of saddle pieces and steel coils of various sizes) are projected along the vehicle parking direction vehicle bottom perpendicular (saddle piece plane is converted into a straight line, and steel coils are converted into circular arcs), a straight line in the projection is extracted, and a straight line model parameter is calculated, so that feature extraction of "plane-projection-straight line" of each type of saddle piece is realized. In this embodiment, before projecting the target point cloud data along the midperpendicular of the parking direction of the target vehicle, the method further includes reversely rotating the target point cloud by an angle α, then restoring the target point cloud to the original position, and then projecting to extract a straight line in the current projection.
S600, sequencing the extracted straight lines according to the parking direction of the target vehicle, pairing the sequenced straight lines in pairs under a preset constraint condition, and generating projection straight lines of one or more saddles; wherein the preset constraint condition comprises: an angle constraint and a distance constraint.
According to the above, in an exemplary embodiment, the method further includes: segmenting the point cloud data for the one or more saddles from the target point cloud data according to projected straight lines of the one or more saddles. By way of example, the saddle in the present embodiment includes, but is not limited to, a two-piece saddle, a four-piece saddle, a six-piece saddle, and the like.
According to the above, in an exemplary embodiment, the method further includes: after the target point cloud data is projected along the middle vertical line of the target vehicle parking direction, extracting a curve from the corresponding projection to be used as a projection line of a steel coil; and segmenting the point cloud data of the steel coil from the target point cloud data according to the projection line of the steel coil.
In another exemplary embodiment, the present embodiment provides a car saddle recognition and extraction method based on three-dimensional laser scanning, including the following steps:
s1, extracting the vehicle body, obtaining a plane model of a local head top plate of all logistics vehicles by applying a three-dimensional point cloud planarization quick search method, and segmenting the head area to further realize segmentation and extraction of vehicle body point cloud data;
s2, positioning the vehicle body, and calculating coordinates of four corner points after the projection of the bottom surface of the vehicle body according to the vehicle body point cloud obtained in the step S1;
s3, saddle and steel coil point clouds are obtained, vehicle bottom plane point clouds are extracted according to vehicle body point cloud data obtained in the step S1, bottom plane model parameters are calculated, a vehicle bottom plane is cut off, and vehicle body side plate plane point clouds are cut off according to four coordinate values obtained in the step S2;
and S4, extracting saddle piece projection straight lines, projecting the point clouds (possibly comprising two-piece, four-piece, six-piece and other types of saddle pieces and steel coils with various sizes) obtained in the step S3 along the vehicle parking direction vehicle bottom vertical plane (converting saddle piece planes into straight lines, converting steel coils into circular arcs), extracting straight lines in projection, and calculating straight line model parameters to realize the feature extraction of 'plane-projection-straight lines' of various types of saddle pieces.
S5, aligning all the obtained saddle piece projection straight lines along the parking direction coordinate axis according to the straight line model characteristic parameters of the saddle pieces obtained in the step S4, and pairing the saddle piece projection straight lines pairwise under the included angle threshold value constraint and the distance threshold value constraint to form a left straight line and a right straight line of each saddle projection;
and S6, segmenting each saddle point cloud according to the saddle projection straight line parameters obtained in the step S5.
Specifically, the present embodiment is based on 3D point cloud data acquired by a 3D scanner correctly installed in a scene for a specified area. The specified area refers to a parking space and an allowance area thereof which are defined in the storage area and used for loading and unloading the steel coil, and the collected point cloud data in the area is the point cloud data which is collected after the steel coil is parked when the steel coil is discharged from the storage and contains the steel coil transportation vehicle. The position relation between the 3D scanner and the steel coil out-of-storage vehicle and the field coordinate direction are shown in figure 3, and the vehicle stops along the x axis. The flow chart of the saddle extraction method in the embodiment is shown in fig. 2, and comprises the following steps:
ST1, based on the parking space threshold value and the bottom height direct filtering, extracting the vehicle point cloud data and removing the abnormal noise points. If no qualified vehicle exists in the parking space, prompting a vehicle abnormal code; if the vehicle exists in the parking space, a three-dimensional point cloud planarization quick search method is used for obtaining a plane model of a local head top plate of the logistics vehicle, and head data are intercepted according to the parameters of the head plane, so that vehicle body point cloud is obtained.
ST2, as shown in FIG. 4, projecting the obtained vehicle body point cloud to the ground plane, extracting the outer contour of the projection plane, identifying and calculating the coordinates (x) of the four corner points of the outer contourA，yA)、(xB，yB)、(xC，yC)、(xD，yD) And an included angle alpha between the parking central axis of the vehicle and the x axis.
ST3, iteratively identifying and extracting the bottom plate plane in the vehicle body data for multiple times according to threshold parameters such as the width of the vehicle body bottom plate plane, and cutting vehicle body side plate point cloud data in the vehicle body (four pieces of front, back, left and right) point cloud data by direct filtering after rotating the alpha angle around the z axis and being parallel to the x axis according to the four angular point coordinates of the vehicle body positioning, wherein the residual point cloud only comprises a steel coil and saddle point cloud.
ST4, the point cloud data which only contains the saddle and the steel coil and is obtained in ST3 is projected on the vertical plane of the vehicle bottom plate plane along the vehicle parking direction, as shown in figure 5, the saddle sheet plane is converted into a straight line, the steel coil is converted into an arc, the straight line in the projection is extracted based on a straight line fast search method, the straight line parameters (central coordinates (x, y, z), the slope k, a linear equation and the like) are obtained, the straight line is sequenced according to x coordinate values by representing the central coordinates (x, y, z) of the straight line, and the straight line is pairwise paired into a projection straight line where the saddle is located under the slope threshold value constraint and the distance threshold value constraint.
And ST5, performing straight-through filtering on the data which is obtained by ST3 and only comprises the steel coil and the saddle point cloud on the x axis according to the range of the x coordinate value of the projection straight line of the two saddle pieces of each saddle, which is obtained by matching in ST4, and finally extracting the saddle point cloud of the whole vehicle.
In summary, the invention provides a method for extracting an automobile saddle based on three-dimensional laser scanning, which includes the steps of firstly, performing three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data of the target vehicle; then, the vehicle point cloud data are segmented, and vehicle body point cloud data of the target vehicle are obtained; projecting the vehicle body point cloud data along the parallel surface of the bottom surface of the vehicle body of the target vehicle, and acquiring four projected corner point coordinates; extracting vehicle bottom plane point clouds from the vehicle body point cloud data, and cutting off a vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data; projecting the target point cloud data along the middle vertical line of the target vehicle parking direction, and extracting a straight line in the current projection; finally, sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under the preset constraint condition to generate the projection straight lines of one or more saddles; wherein the preset constraint condition comprises: an angle constraint and a distance constraint. According to the method, the automobile saddle sheet is automatically identified and extracted by utilizing the projection straight line of the saddle, so that the unmanned loading operation of the steel coil can be finished, the saddle does not need to be pre-calibrated, the saddle parameters can be accurately calculated, the target saddle can be extracted, and the requirements of an intelligent storage system on the rapid, reliable and safe delivery of transportation vehicles of various non-standardized automobile types and composite saddles are met.
As shown in fig. 6, the invention also provides a car saddle extracting system based on three-dimensional laser scanning, which comprises:
the scanning module M10 is configured to perform three-dimensional laser scanning on a target vehicle, and generate vehicle point cloud data of the target vehicle. The target vehicles in this embodiment include, but are not limited to, vehicles that are loaded with steel coils and saddles at the same time, vehicles that are used to load steel coils and have saddles present, vehicles that are used to load steel coils and have no saddles present. Wherein the target vehicle is located within the target area; the target area in this embodiment includes, but is not limited to, a parking area when the vehicle is handling a steel coil. As an example, the present embodiment may perform three-dimensional laser scanning on vehicles in a designated area based on a 3D scanner correctly installed in a logistics transportation scene, and then use the acquired 3D point cloud data as vehicle point cloud data of a corresponding vehicle. Specifically, the designated area may refer to a parking space defined in the storage area for loading and unloading the vehicle when the steel coil is loaded and unloaded and a margin area thereof, and the collected point cloud data in the area may be point cloud data including the steel coil transportation vehicle collected after the vehicle is parked when the steel coil is unloaded from the storage.
And the segmentation module M20 is used for segmenting the vehicle point cloud data to generate the vehicle body point cloud data of the target vehicle. In this embodiment, the manner of segmenting the vehicle point cloud data may adopt the prior art, and this embodiment is not described again.
A first projection module 30 for projecting the vehicle body point cloud data along a parallel plane of the bottom surface of the vehicle body of the target vehicle; as an example, the present embodiment projects the obtained vehicle body point cloud to the ground plane, extracts the outer contour of the projection plane, and identifies and calculates coordinates (x) of four corner points of the outer contourA，yA)、(xB，yB)、(xC，yC)、(xD，yD) And an included angle alpha between the parking central axis of the vehicle and the x axis.
The removing module M40 is used for extracting vehicle bottom plane point clouds from the vehicle body point cloud data and removing the vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; and after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to the four angular point coordinates in the projection output by the first projection module, and taking the remaining point cloud data as target point cloud data. As an example, in the embodiment, the ground is taken as a plane where an x axis and a y axis are located, and an axis perpendicular to the ground is taken as a z axis, so as to establish a reference coordinate system; acquiring an included angle alpha between the central axis of the target vehicle in the parking direction and the x axis; after the bottom plane of the car is cut off, the projected four angular point coordinates are rotated around the z axis by an angle alpha and are parallel to the x axis, the point cloud of the plane of the side plate of the car body is cut off through straight-through filtering, and the residual point cloud data only containing the steel coil point cloud and the saddle point cloud is used as target point cloud data.
And the second projection module M50 is used for projecting the target point cloud data along the midperpendicular of the parking direction of the target vehicle. As an example, in the present embodiment, target point cloud data (which may include two, four, six, and other types of saddle pieces and steel coils of various sizes) are projected along the vehicle parking direction vehicle bottom perpendicular (saddle piece plane is converted into a straight line, and steel coils are converted into circular arcs), a straight line in the projection is extracted, and a straight line model parameter is calculated, so that feature extraction of "plane-projection-straight line" of each type of saddle piece is realized. In this embodiment, before projecting the target point cloud data along the midperpendicular of the parking direction of the target vehicle, the method further includes reversely rotating the target point cloud by an angle α, then restoring the target point cloud to the original position, and then projecting to extract a straight line in the current projection.
A saddle projection extraction module M60, configured to extract straight lines from the projection output by the second projection module, sort the extracted straight lines according to the parking direction of the target vehicle, and pair every two sorted straight lines under a preset constraint condition to generate one or more saddle projection straight lines; wherein the preset constraint condition comprises: an angle constraint and a distance constraint.
In accordance with the above, in an exemplary embodiment, the system further comprises a saddle point cloud extraction module M70 for segmenting the point cloud data of the one or more saddles from the target point cloud data according to projected straight lines of the one or more saddles.
In accordance with the above, in an exemplary embodiment, the system further comprises: the steel coil projection extraction module M80 is used for extracting a curve from the projection output by the second projection module as a projection line of the steel coil;
and the steel coil point cloud extraction module M90 is used for dividing the point cloud data of the steel coil from the target point cloud data according to the projection line of the steel coil.
In another exemplary embodiment, the present embodiment provides a three-dimensional laser scanning based car saddle recognition extraction system based on 3D point cloud data acquired by a 3D scanner correctly installed in a scene for a specified area. The specified area refers to a parking space and an allowance area thereof which are defined in the storage area and used for loading and unloading the steel coil, and the collected point cloud data in the area is the point cloud data which is collected after the steel coil is parked when the steel coil is discharged from the storage and contains the steel coil transportation vehicle. The position relation between the 3D scanner and the steel coil out-of-storage vehicle and the field coordinate direction are shown in figure 3, and the vehicle stops along the x axis. The saddle extraction system in this embodiment specifically performs the following steps:
ST1, based on the parking space threshold value and the bottom height direct filtering, extracting the vehicle point cloud data and removing the abnormal noise points. If no qualified vehicle exists in the parking space, prompting a vehicle abnormal code; if the vehicle exists in the parking space, a three-dimensional point cloud planarization quick search method is used for obtaining a plane model of a local head top plate of the logistics vehicle, and head data are intercepted according to the parameters of the head plane, so that vehicle body point cloud is obtained.
ST2, as shown in FIG. 4, projecting the obtained vehicle body point cloud to the ground plane, extracting the outer contour of the projection plane, identifying and calculating the coordinates (x) of the four corner points of the outer contourA，yA)、(xB，yB)、(xC，yC)、(xD，yD) And an included angle alpha between the parking central axis of the vehicle and the x axis.
ST3, iteratively identifying and extracting the bottom plate plane in the vehicle body data for multiple times according to threshold parameters such as the width of the vehicle body bottom plate plane, and cutting vehicle body side plate point cloud data in the vehicle body (four pieces of front, back, left and right) point cloud data by direct filtering after rotating the alpha angle around the z axis and being parallel to the x axis according to the four angular point coordinates of the vehicle body positioning, wherein the residual point cloud only comprises a steel coil and saddle point cloud.
ST4, the point cloud data which only contains the saddle and the steel coil and is obtained in ST3 is projected on the vertical plane of the vehicle bottom plate plane along the vehicle parking direction, as shown in figure 5, the saddle sheet plane is converted into a straight line, the steel coil is converted into an arc, the straight line in the projection is extracted based on a straight line fast search method, the straight line parameters (central coordinates (x, y, z), the slope k, a linear equation and the like) are obtained, the straight line is sequenced according to x coordinate values by representing the central coordinates (x, y, z) of the straight line, and the straight line is pairwise paired into a projection straight line where the saddle is located under the slope threshold value constraint and the distance threshold value constraint.
And ST5, performing straight-through filtering on the data which is obtained by ST3 and only comprises the steel coil and the saddle point cloud on the x axis according to the range of the x coordinate value of the projection straight line of the two saddle pieces of each saddle, which is obtained by matching in ST4, and finally extracting the saddle point cloud of the whole vehicle.
In summary, the invention provides an automobile saddle extraction system based on three-dimensional laser scanning, which includes the steps of firstly, performing three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data of the target vehicle; then, the vehicle point cloud data are segmented, and vehicle body point cloud data of the target vehicle are obtained; projecting the vehicle body point cloud data along the parallel surface of the bottom surface of the vehicle body of the target vehicle, and acquiring four projected corner point coordinates; extracting vehicle bottom plane point clouds from the vehicle body point cloud data, and cutting off a vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data; projecting the target point cloud data along the middle vertical line of the target vehicle parking direction, and extracting a straight line in the current projection; finally, sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under the preset constraint condition to generate the projection straight lines of one or more saddles; wherein the preset constraint condition comprises: an angle constraint and a distance constraint. This system comes to carry out automatic identification to the automobile saddle piece through the projection straight line that utilizes the saddle and draws, not only can accomplish the coil of strip unmanned loading operation, also need not to mark in advance the saddle to can accurately calculate the saddle parameter and extract the target saddle, satisfy the intelligent storage system to the haulage vehicle of all kinds of non-standardized motorcycle types and combined type saddle quick, reliable, the demand of safe delivery. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A car saddle extraction method based on three-dimensional laser scanning is characterized by comprising the following steps:
carrying out three-dimensional laser scanning on a target vehicle to obtain vehicle point cloud data of the target vehicle;
segmenting the vehicle point cloud data to obtain vehicle body point cloud data of the target vehicle;
projecting the vehicle body point cloud data along the parallel surface of the bottom surface of the vehicle body of the target vehicle, and acquiring four projected corner point coordinates;
extracting vehicle bottom plane point clouds from the vehicle body point cloud data, and cutting off a vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to the projected four angular point coordinates, and taking the remaining point cloud data as target point cloud data;
projecting the target point cloud data along the midperpendicular of the target vehicle parking direction, and extracting a straight line in the current projection;
sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under a preset constraint condition to generate projection straight lines of one or more saddles; wherein the preset constraint condition comprises: an angle constraint and a distance constraint.
2. The three-dimensional laser scanning based automobile saddle extraction method according to claim 1, further comprising: segmenting the point cloud data for the one or more saddles from the target point cloud data according to projected straight lines of the one or more saddles.
3. The three-dimensional laser scanning based automobile saddle extraction method according to claim 1, further comprising:
after the target point cloud data is projected along the middle vertical line of the target vehicle parking direction, extracting a curve from the corresponding projection to be used as a projection line of a steel coil;
and segmenting the point cloud data of the steel coil from the target point cloud data according to the projection line of the steel coil.
4. The three-dimensional laser scanning based automobile saddle extraction method according to claim 1, further comprising:
establishing a reference coordinate system by taking the ground as a plane where an x axis and a y axis are located and taking an axis vertical to the ground as a z axis;
acquiring an included angle alpha between the central axis of the target vehicle in the parking direction and the x axis;
after the bottom plane of the car is cut off, the projected four angular point coordinates are rotated around the z axis by an angle alpha and are parallel to the x axis, the point cloud of the plane of the side plate of the car body is cut off through straight-through filtering, and the residual point cloud data only containing the steel coil point cloud and the saddle point cloud is used as target point cloud data.
5. The method for three-dimensional laser scanning based saddle extraction for automobiles according to claim 1, characterized in that said target vehicle comprises at least: a vehicle loaded with a coil and a saddle at the same time, a vehicle for loading a coil and having a saddle already present, a vehicle for loading a coil and having no saddle present.
6. The method for extracting automobile saddles based on three-dimensional laser scanning according to claim 1 or 5, characterized in that said target vehicle is located within a target area; the target area includes at least: and (4) parking areas when the vehicle loads and unloads the steel coil.
7. The method of claim 1 or 2, wherein the saddle comprises at least one of: two-piece type saddle, four-piece type saddle, six-piece type saddle.
8. A car saddle extraction system based on three-dimensional laser scanning, characterized in that, the system includes:
the scanning module is used for carrying out three-dimensional laser scanning on a target vehicle to generate vehicle point cloud data of the target vehicle;
the segmentation module is used for segmenting the vehicle point cloud data to generate vehicle body point cloud data of the target vehicle;
the first projection module is used for projecting the vehicle body point cloud data along a parallel plane of the bottom surface of the vehicle body of the target vehicle;
the cutting module is used for extracting vehicle bottom plane point clouds from the vehicle body point cloud data and cutting the vehicle bottom plane of the target vehicle according to the vehicle bottom plane point clouds; after the vehicle bottom plane is cut off, cutting off vehicle body side plate plane point clouds according to four angular point coordinates in the projection output by the first projection module, and taking the remaining point cloud data as target point cloud data;
the second projection module is used for projecting the target point cloud data along the midperpendicular of the parking direction of the target vehicle;
a saddle projection extraction module used for extracting straight lines from the projection output by the second projection module, sequencing the extracted straight lines according to the parking direction of the target vehicle, and pairing the sequenced straight lines in pairs under the preset constraint condition to generate one or more saddle projection straight lines; wherein the preset constraint condition comprises: an angle constraint and a distance constraint.
9. The three-dimensional laser scanning based automobile saddle extraction system according to claim 8, further comprising a saddle point cloud extraction module for segmenting point cloud data of the one or more saddles from the target point cloud data according to projected straight lines of the one or more saddles.
10. The three-dimensional laser scanning based automobile saddle extraction system according to claim 8, further comprising:
the steel coil projection extraction module is used for extracting a curve from the projection output by the second projection module as a projection line of the steel coil;
and the steel coil point cloud extraction module is used for segmenting the point cloud data of the steel coil from the target point cloud data according to the projection line of the steel coil.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210056734.6A CN114399550B (en) | 2022-01-18 | 2022-01-18 | Three-dimensional laser scanning-based automobile saddle extraction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210056734.6A CN114399550B (en) | 2022-01-18 | 2022-01-18 | Three-dimensional laser scanning-based automobile saddle extraction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114399550A true CN114399550A (en) | 2022-04-26 |
| CN114399550B CN114399550B (en) | 2024-06-07 |
Family
ID=81231375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210056734.6A Active CN114399550B (en) | 2022-01-18 | 2022-01-18 | Three-dimensional laser scanning-based automobile saddle extraction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114399550B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117784169A (en) * | 2024-02-27 | 2024-03-29 | 唐山港集团股份有限公司 | 3D point cloud-based steel coil contour measurement method, equipment and medium |
Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090134555A1 (en) * | 2004-07-27 | 2009-05-28 | Edw. C. Levy Co. | Steel Coil Cutting Apparatus and Method |
| CN106056659A (en) * | 2016-05-27 | 2016-10-26 | 山东科技大学 | Building corner space position automatic extraction method in vehicle laser scanning point cloud |
| CN106327044A (en) * | 2015-06-30 | 2017-01-11 | 宝山钢铁股份有限公司 | Device and method for automatically identifying and positioning vehicle-mounted steel coils and vehicle saddles |
| CN106371104A (en) * | 2016-08-16 | 2017-02-01 | 长春理工大学 | Vehicle targets recognizing method and anti-collision device using multi-line point cloud data machine learning |
| US20180225538A1 (en) * | 2015-08-04 | 2018-08-09 | Universite Grenoble Alpes | Device and method for automatically detecting a surgical tool on an image provided by a medical imaging system |
| US20180284230A1 (en) * | 2017-03-28 | 2018-10-04 | Honda Motor Co., Ltd. | Method for detecting edge of object by laser ranging device |
| CN108932475A (en) * | 2018-05-31 | 2018-12-04 | 中国科学院西安光学精密机械研究所 | A kind of Three-dimensional target recognition system and method based on laser radar and monocular vision |
| CN108985254A (en) * | 2018-08-01 | 2018-12-11 | 上海主线科技有限公司 | A kind of band based on laser hangs tag vehicle tracking |
| CN109484975A (en) * | 2018-11-06 | 2019-03-19 | 北京首钢自动化信息技术有限公司 | A kind of vehicle saddle Scan orientation method |
| CN109814850A (en) * | 2017-11-20 | 2019-05-28 | 上海宝信软件股份有限公司 | The intelligent warehouse compartment recommender system and method for rule-based engine and geometry optimization |
| US20190235062A1 (en) * | 2017-08-23 | 2019-08-01 | Tencent Technology (Shenzhen) Company Limited | Method, device, and storage medium for laser scanning device calibration |
| CN110728753A (en) * | 2019-10-09 | 2020-01-24 | 湖南大学 | Target point cloud 3D bounding box fitting method based on linear fitting |
| CN110766731A (en) * | 2019-10-21 | 2020-02-07 | 武汉中海庭数据技术有限公司 | Method and device for automatically registering panoramic image and point cloud and storage medium |
| CN110853134A (en) * | 2019-10-25 | 2020-02-28 | 西安交通大学 | Method for calculating contact state of assembly matching surface containing geometric errors |
| CN111243010A (en) * | 2018-11-12 | 2020-06-05 | 中冶京诚工程技术有限公司 | Intelligent steel coil vehicle loading system and method for crown block image recognition |
| CN111308987A (en) * | 2020-02-21 | 2020-06-19 | 西安理工大学 | Automatic uncoiling control system of uncoiler based on image processing and detection method |
| CN111578893A (en) * | 2020-05-29 | 2020-08-25 | 苏州挚途科技有限公司 | Method for identifying included angle between tractor and trailer |
| WO2020168742A1 (en) * | 2019-02-20 | 2020-08-27 | 苏州风图智能科技有限公司 | Method and device for vehicle body positioning |
| CN111680542A (en) * | 2020-04-17 | 2020-09-18 | 东南大学 | Steel coil point cloud identification and classification method based on multi-scale feature extraction and Pointernet neural network |
| US20200339210A1 (en) * | 2018-04-27 | 2020-10-29 | FUELL Inc. | Electric saddle type vehicle |
| CN111899291A (en) * | 2020-08-05 | 2020-11-06 | 深圳市数字城市工程研究中心 | Automatic registration method for coarse-to-fine urban point cloud based on multi-source dimension decomposition |
| CN112183455A (en) * | 2020-10-16 | 2021-01-05 | 飞马智科信息技术股份有限公司 | Method for improving identification efficiency based on steel point cloud information |
| US20210001845A1 (en) * | 2018-03-28 | 2021-01-07 | Honda Motor Co., Ltd. | Object detection system for saddle-type vehicle, and saddle-type vehicle |
| CN112257707A (en) * | 2020-10-22 | 2021-01-22 | 宝钢湛江钢铁有限公司 | Automatic identification structure and method for tail of steel coil and ID of steel coil |
| CN112389437A (en) * | 2021-01-21 | 2021-02-23 | 北京主线科技有限公司 | Device and method for measuring and calculating included angle between head and trailer of automatic driving truck |
| CN112777257A (en) * | 2021-01-29 | 2021-05-11 | 佛山市诚德新材料有限公司 | Steel coil over-span transportation system |
| CN112906128A (en) * | 2021-01-18 | 2021-06-04 | 上海交通大学 | Vehicle modeling method, equipment and system based on linear guide rail and scanner |
| CN113158864A (en) * | 2021-04-13 | 2021-07-23 | 北京小马慧行科技有限公司 | Method and device for determining included angle between truck head and trailer |
| CN113280730A (en) * | 2020-02-19 | 2021-08-20 | 宝钢日铁汽车板有限公司 | System and method for efficiently detecting strip head of steel coil |
| CN113426847A (en) * | 2021-07-09 | 2021-09-24 | 上海大学 | Steel coil tail press-mounting device and method |
| CN113605766A (en) * | 2021-08-06 | 2021-11-05 | 珠海丽亭智能科技有限公司 | Detection system and position adjustment method of automobile transfer robot |
-
2022
- 2022-01-18 CN CN202210056734.6A patent/CN114399550B/en active Active
Patent Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090134555A1 (en) * | 2004-07-27 | 2009-05-28 | Edw. C. Levy Co. | Steel Coil Cutting Apparatus and Method |
| CN106327044A (en) * | 2015-06-30 | 2017-01-11 | 宝山钢铁股份有限公司 | Device and method for automatically identifying and positioning vehicle-mounted steel coils and vehicle saddles |
| US20180225538A1 (en) * | 2015-08-04 | 2018-08-09 | Universite Grenoble Alpes | Device and method for automatically detecting a surgical tool on an image provided by a medical imaging system |
| CN106056659A (en) * | 2016-05-27 | 2016-10-26 | 山东科技大学 | Building corner space position automatic extraction method in vehicle laser scanning point cloud |
| CN106371104A (en) * | 2016-08-16 | 2017-02-01 | 长春理工大学 | Vehicle targets recognizing method and anti-collision device using multi-line point cloud data machine learning |
| US20180284230A1 (en) * | 2017-03-28 | 2018-10-04 | Honda Motor Co., Ltd. | Method for detecting edge of object by laser ranging device |
| US20190235062A1 (en) * | 2017-08-23 | 2019-08-01 | Tencent Technology (Shenzhen) Company Limited | Method, device, and storage medium for laser scanning device calibration |
| CN109814850A (en) * | 2017-11-20 | 2019-05-28 | 上海宝信软件股份有限公司 | The intelligent warehouse compartment recommender system and method for rule-based engine and geometry optimization |
| US20210001845A1 (en) * | 2018-03-28 | 2021-01-07 | Honda Motor Co., Ltd. | Object detection system for saddle-type vehicle, and saddle-type vehicle |
| US20200339210A1 (en) * | 2018-04-27 | 2020-10-29 | FUELL Inc. | Electric saddle type vehicle |
| CN108932475A (en) * | 2018-05-31 | 2018-12-04 | 中国科学院西安光学精密机械研究所 | A kind of Three-dimensional target recognition system and method based on laser radar and monocular vision |
| CN108985254A (en) * | 2018-08-01 | 2018-12-11 | 上海主线科技有限公司 | A kind of band based on laser hangs tag vehicle tracking |
| CN109484975A (en) * | 2018-11-06 | 2019-03-19 | 北京首钢自动化信息技术有限公司 | A kind of vehicle saddle Scan orientation method |
| CN111243010A (en) * | 2018-11-12 | 2020-06-05 | 中冶京诚工程技术有限公司 | Intelligent steel coil vehicle loading system and method for crown block image recognition |
| WO2020168742A1 (en) * | 2019-02-20 | 2020-08-27 | 苏州风图智能科技有限公司 | Method and device for vehicle body positioning |
| CN110728753A (en) * | 2019-10-09 | 2020-01-24 | 湖南大学 | Target point cloud 3D bounding box fitting method based on linear fitting |
| CN110766731A (en) * | 2019-10-21 | 2020-02-07 | 武汉中海庭数据技术有限公司 | Method and device for automatically registering panoramic image and point cloud and storage medium |
| CN110853134A (en) * | 2019-10-25 | 2020-02-28 | 西安交通大学 | Method for calculating contact state of assembly matching surface containing geometric errors |
| CN113280730A (en) * | 2020-02-19 | 2021-08-20 | 宝钢日铁汽车板有限公司 | System and method for efficiently detecting strip head of steel coil |
| CN111308987A (en) * | 2020-02-21 | 2020-06-19 | 西安理工大学 | Automatic uncoiling control system of uncoiler based on image processing and detection method |
| CN111680542A (en) * | 2020-04-17 | 2020-09-18 | 东南大学 | Steel coil point cloud identification and classification method based on multi-scale feature extraction and Pointernet neural network |
| CN111578893A (en) * | 2020-05-29 | 2020-08-25 | 苏州挚途科技有限公司 | Method for identifying included angle between tractor and trailer |
| CN111899291A (en) * | 2020-08-05 | 2020-11-06 | 深圳市数字城市工程研究中心 | Automatic registration method for coarse-to-fine urban point cloud based on multi-source dimension decomposition |
| CN112183455A (en) * | 2020-10-16 | 2021-01-05 | 飞马智科信息技术股份有限公司 | Method for improving identification efficiency based on steel point cloud information |
| CN112257707A (en) * | 2020-10-22 | 2021-01-22 | 宝钢湛江钢铁有限公司 | Automatic identification structure and method for tail of steel coil and ID of steel coil |
| CN112906128A (en) * | 2021-01-18 | 2021-06-04 | 上海交通大学 | Vehicle modeling method, equipment and system based on linear guide rail and scanner |
| CN112389437A (en) * | 2021-01-21 | 2021-02-23 | 北京主线科技有限公司 | Device and method for measuring and calculating included angle between head and trailer of automatic driving truck |
| CN112777257A (en) * | 2021-01-29 | 2021-05-11 | 佛山市诚德新材料有限公司 | Steel coil over-span transportation system |
| CN113158864A (en) * | 2021-04-13 | 2021-07-23 | 北京小马慧行科技有限公司 | Method and device for determining included angle between truck head and trailer |
| CN113426847A (en) * | 2021-07-09 | 2021-09-24 | 上海大学 | Steel coil tail press-mounting device and method |
| CN113605766A (en) * | 2021-08-06 | 2021-11-05 | 珠海丽亭智能科技有限公司 | Detection system and position adjustment method of automobile transfer robot |
Non-Patent Citations (7)
| Title |
|---|
| D. COMANICIU等: ""Image segmentation using clustering with saddle point detection"", 《PROCEEDINGS. INTERNATIONAL CONFERENCE ON IMAGE PROCESSING》, 31 December 2002 (2002-12-31), pages 1 - 17 * |
| ZIXUAN LIU等: ""A 3D Steel Coils’ Recognition Method Based on Multi-Scale Features and Pointnet"", 《 2020 39TH CHINESE CONTROL CONFERENCE (CCC)》, 9 September 2020 (2020-09-09), pages 1 - 15 * |
| 杨东海等: ""激光扫描识别技术在智能钢卷库中的研究及应用"", 《冶金自动化》, 22 September 2021 (2021-09-22), pages 1 - 10 * |
| 汪泳等: ""基于点云技术电力物资自装卸作业研究"", 《自动化仪表》, vol. 41, no. 9, 30 September 2020 (2020-09-30), pages 68 - 71 * |
| 谢永辉等: ""面向钢铁工业场景的三维点云技术研究"", 《现代信息科技》, vol. 4, no. 7, 10 April 2020 (2020-04-10), pages 142 - 144 * |
| 郑庆元等: ""基于立体视觉的钢卷检测技术"", 《计量与测试技术》, vol. 43, no. 5, 31 December 2016 (2016-12-31), pages 36 - 39 * |
| 陈欣等: ""基于图像形状检测与坐标融合技术的鞍座坐标标定方法"", 《冶金自动化》, vol. 45, no. 6, 30 November 2021 (2021-11-30), pages 90 - 97 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117784169A (en) * | 2024-02-27 | 2024-03-29 | 唐山港集团股份有限公司 | 3D point cloud-based steel coil contour measurement method, equipment and medium |
| CN117784169B (en) * | 2024-02-27 | 2024-05-07 | 唐山港集团股份有限公司 | 3D point cloud-based steel coil contour measurement method, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114399550B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107622499B (en) | Identification and space positioning method based on target two-dimensional contour model | |
| CN111797734B (en) | Vehicle point cloud data processing method, device, equipment and storage medium | |
| Oehler et al. | Efficient multi-resolution plane segmentation of 3D point clouds | |
| US9123112B2 (en) | Method for the pre-processing of a three-dimensional image of the surface of a tyre for use in the inspection of said surface | |
| CN110837814B (en) | Vehicle navigation method, device and computer readable storage medium | |
| JP2000517452A (en) | Viewing method | |
| CN109215119B (en) | Method and device for establishing three-dimensional model of damaged vehicle | |
| US11873195B2 (en) | Methods and systems for generating landing solutions for containers on landing surfaces | |
| CN114399550A (en) | Automobile saddle extraction method and system based on three-dimensional laser scanning | |
| CN112233136A (en) | Method, system, equipment and storage medium for alignment of container trucks based on binocular recognition | |
| CN114998824A (en) | Vehicle loading and unloading task monitoring method, device and system | |
| CN113184707A (en) | Method and system for preventing lifting of container truck based on laser vision fusion and deep learning | |
| CN114241475B (en) | Self-adaptive automobile model recognition method and system based on three-dimensional laser scanning | |
| CN114332219B (en) | Tray positioning method and device based on three-dimensional point cloud processing | |
| CN113343962B (en) | Visual perception-based multi-AGV trolley working area maximization implementation method | |
| CN112581519B (en) | Method and device for identifying and positioning radioactive waste bag | |
| CN115631329B (en) | Loading control method, system and storage medium for open carriage | |
| CN115909216A (en) | Cargo ship hatch detection method and system based on laser radar and monocular camera | |
| CN116469092A (en) | Self-adaptive Alpha Shapes contour extraction method based on DBSCAN algorithm | |
| CN112347664B (en) | Modeling method and device for irregular loading space | |
| Fisher et al. | Recognintion of Complex 3-D Objects from Range Data | |
| CN114519711B (en) | Method, system, medium and electronic terminal for measuring steel coil in reservoir area | |
| CN114529613B (en) | Feature point high-precision coordinate extraction method for circular array calibration plate | |
| CN117952823B (en) | Automatic extraction, classification and updating method for slope top and bottom lines of open-pit mining area | |
| CN116342695B (en) | Unmanned forklift truck goods placing detection method and device, unmanned forklift truck and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd. Address before: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant |