Automatic identification and unloading control method and system for material transportation

Abstract

The invention discloses a material transportation automatic identification and unloading control method and system, and the method comprises the steps: obtaining the complete image information of a carriage of a material carrying vehicle and the image information of materials in the carriage through a long-focus camera and a short-focus camera for the material carrying vehicle entering a target identification region; according to the method, a vehicle cover effective shielding ratio coefficient and a material shielded ratio coefficient of a material loading vehicle are determined, so that a fusion shielding coefficient is determined, and under the condition that the fusion shielding coefficient is smaller than a preset shielding coefficient threshold value, the material category of the material loading vehicle is identified through the carriage internal material image information; under the condition that the identified material category is consistent with the material category of the current unloading area, laser scanning is carried out on a carriage of the material loading vehicle, the material carrying filling volume of the material loading vehicle is determined, and under the condition that the material carrying filling volume is smaller than the material remaining receivable volume of the current unloading area, the material loading vehicle is subjected to laser scanning; and if yes, the material carrying vehicle is released to enter the current unloading area for unloading, and the unloading efficiency and safety are improved.

Description

Technical Field

[0001] This invention relates to the field of material transportation technology, and in particular to an automatic identification and unloading control method and system for material transportation. Background Technology

[0002] In construction engineering, mining, and large-scale warehousing, the transportation and unloading management of bulk materials (such as river sand and gravel) is a critical link in the production process. Currently, during material transportation and unloading, the material information of transport vehicles needs to be manually verified before entering the warehouse. This process is not only inefficient but also prone to errors due to human factors, affecting the smooth operation of the entire production process. Furthermore, traditional unloading control methods often lack real-time capability, making it difficult to adjust unloading strategies promptly based on warehouse storage conditions, easily leading to material accumulation or wasted space in the warehouse. Summary of the Invention

[0003] In view of this, in order to solve the above-mentioned technical problems, the present invention provides an automatic identification and unloading control method and system for material transportation.

[0004] The first aspect of this invention provides an automatic identification and unloading control method for material transportation, comprising: Once the material-carrying vehicle enters the target recognition area, the complete image information of the vehicle's cargo compartment and the image information of the materials inside the cargo compartment are obtained by using a telephoto camera and a short-focus camera, respectively. Based on the complete image information of the cargo compartment, the effective occlusion ratio coefficient of the cover of the material-carrying vehicle is determined, and based on the image information of the materials inside the cargo compartment, the material occlusion ratio coefficient is determined. The fusion occlusion coefficient is determined based on the effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material. If the fusion occlusion coefficient is less than a preset occlusion coefficient threshold, the material category of the loading vehicle is identified by the material image information inside the carriage, and it is determined whether the identified material category is consistent with the material category of the current unloading area. If the identified material category is consistent with the material category in the current unloading area, the cargo compartment of the material-carrying vehicle is laser-scanned, and the material filling volume of the material-carrying vehicle is determined based on the laser scanning results. If the filling volume of the transported material is compared with the remaining capacity of the material in the current unloading area, and the filling volume of the transported material is smaller than the remaining capacity of the material in the current unloading area, then the transported vehicle is allowed to enter the current unloading area to unload.

[0005] Preferably, determining the effective occupancy ratio coefficient of the vehicle cover based on the complete image information of the cargo compartment includes: Based on the coordinate transformation relationship between the telephoto camera and the short-focus camera, the complete image information of the carriage is transformed into a complete image of the carriage in the coordinate system of the short-focus camera; In the converted complete image of the carriage, the edge contour information of the cover is extracted, and the area covered by the cover is determined; Determine whether the area covered by the vehicle cover overlaps with the image information of the material inside the vehicle compartment. If it is determined that the area covered by the vehicle cover overlaps with the image information of the material inside the vehicle compartment, then the position weight of the area covered by the vehicle cover is determined to be a first weight. If it is determined that the area covered by the vehicle cover does not overlap with the image information of the material inside the vehicle compartment, then the position weight of the area covered by the vehicle cover is determined to be a second weight. Wherein, the first weight is greater than the second weight. The area covered by the vehicle cover and the converted complete image of the vehicle compartment are processed in grayscale, and the total number of pixels in the area covered by the vehicle cover and the total number of pixels in the converted complete image of the vehicle compartment are counted. The effective occlusion ratio coefficient of the vehicle cover is determined based on the positional weight of the area covered by the vehicle cover, the total number of pixels in the area covered by the vehicle cover, and the total number of pixels in the converted complete image of the vehicle compartment.

[0006] Preferably, the material obscuration ratio is determined based on the image information of the materials inside the carriage, including: Preprocess the image information of materials inside the carriage to enhance the material features in the image; Using a pre-set material detection algorithm, material areas are detected in the pre-processed material image information inside the carriage; The material area is processed in grayscale, and the total number of pixels in the material area after grayscale processing is counted. Based on the total number of pixels in the material area and the total number of pixels in the converted complete image of the carriage, the total number of pixels in the area where the material is occluded is determined. The occlusion ratio coefficient of the material is determined based on the total number of pixels in the area where the material is obscured and the total number of pixels in the converted complete image of the carriage.

[0007] Preferably, determining the fusion occlusion coefficient based on the effective occlusion ratio coefficient of the vehicle hood and the occlusion ratio coefficient of the material includes: The effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material are weighted to obtain the fusion occlusion coefficient.

[0008] Preferably, the step of identifying the material category of the loading vehicle through the material image information inside the carriage, and determining whether the identified material category is consistent with the material category of the current unloading area, includes: The image information of the materials inside the carriage is input into a trained material recognition model, so that the trained material recognition model outputs the material category of the material-carrying vehicle; wherein, the trained material recognition model is obtained by training a preset neural network model based on a training dataset, and the training dataset contains material image information samples of various material categories inside the carriage and corresponding material category labels; The identified material category is compared with the preset material category of the current unloading area. If the identified material category matches the preset material category of the current unloading area, the material category is considered to be successfully matched. If the identified material category does not match the preset material category of the current unloading area, an alarm mechanism is triggered to prohibit the material-carrying vehicle from entering the current unloading area.

[0009] Preferably, the step of performing laser scanning on the cargo compartment of the material-carrying vehicle and determining the material filling volume of the vehicle based on the laser scanning results includes: The laser radar emits a laser beam to the surface of the material inside the cargo compartment of the material-carrying vehicle, receives the reflected laser signal, and calculates the distance from the material surface to the laser radar by measuring the time difference between the emission and reception of the laser beam and combining the time difference with the speed of light. The height of the material surface relative to the ground is determined based on the relative height of the lidar to the ground and the distance from the material surface to the lidar. The material depth is determined based on the height of the material surface relative to the ground and the distance between the bottom of the cargo compartment of the material-carrying vehicle and the ground. The material filling volume of the material-carrying vehicle is determined by multiplying the length and width of the cargo compartment of the material-carrying vehicle with the depth of the material.

[0010] Preferably, the method further includes: The current unloading area is scanned with a laser to extract the point cloud of the material surface in the current unloading area, and the average height of the material surface is determined based on the point cloud of the material surface. The material volume of the current unloading zone is determined based on the average height of the material surface and the equivalent radius of the current unloading zone. The remaining material capacity of the current unloading area is determined based on the preset total material volume of the current unloading area and the material volume of the current unloading area.

[0011] Preferably, the method further includes: If the filling volume of the transported material is not less than the remaining material capacity of the current unloading area, then multiple other candidate unloading areas that are consistent with the material category of the transported vehicle are selected, and the remaining material capacity of the multiple other candidate unloading areas is determined. By comparing the filling volume of the transported material with the remaining capacity of the material in multiple other candidate unloading areas, multiple other candidate unloading areas with a filling volume of the transported material smaller than the remaining capacity of the material are selected. Among the multiple other candidate unloading areas selected, the candidate unloading area that is closest to the material-carrying vehicle is selected as the optimal unloading area. The system notifies the material-carrying vehicle to proceed to the optimal unloading area for unloading, and sends the location information of the optimal unloading area and driving route guidance information to the material-carrying vehicle.

[0012] Preferably, the method further includes: After the material-carrying vehicle enters the current unloading area and finishes unloading, and after monitoring that the material-carrying vehicle has completely left the current unloading area, the material category of the current unloading area is updated to the material category carried by the material-carrying vehicle, and the remaining capacity of the material in the current unloading area is updated.

[0013] Secondly, the present invention also provides an automatic identification and unloading control system for material transportation, comprising: The image acquisition module is used to acquire complete image information of the cargo compartment and image information of the materials inside the cargo compartment through a telephoto camera and a short-focus camera, respectively, when the identified material-carrying vehicle enters the target identification area. The occlusion ratio determination module is used to determine the effective occlusion ratio coefficient of the cover of the material-carrying vehicle based on the complete image information of the carriage, and to determine the occlusion ratio coefficient of the material based on the image information of the material inside the carriage. The occlusion fusion determination module is used to determine the fusion occlusion coefficient based on the effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material. The material category comparison module is used to identify the material category of the loading vehicle by means of the material image information inside the carriage when the fusion occlusion coefficient is less than a preset occlusion coefficient threshold, and to determine whether the identified material category is consistent with the material category of the current unloading area. The material volume determination module is used to perform laser scanning on the cargo compartment of the material-carrying vehicle when the identified material category is consistent with the material category of the current unloading area, and to determine the material filling volume of the material-carrying vehicle based on the laser scanning results. The unloading control module compares the filling volume of the transported material with the remaining capacity of the material in the current unloading area. If the filling volume of the transported material is less than the remaining capacity of the material in the current unloading area, the module allows the transported vehicle to enter the current unloading area for unloading.

[0014] As can be seen from the above technical solution, this invention acquires complete images of the vehicle's cargo compartment and images of the materials inside the cargo compartment using both telephoto and short-focus cameras when a material-carrying vehicle enters the target recognition area. Based on the complete cargo compartment image, the effective occlusion ratio of the vehicle's roof is determined, and based on the material inside the cargo compartment image, the occlusion ratio of the materials is determined, thus determining the fusion occlusion coefficient. If the fusion occlusion coefficient is less than a preset occlusion coefficient threshold, the material category of the vehicle is identified using the material inside the cargo compartment image. If the identified material category matches the material category in the current unloading area, the cargo compartment of the vehicle is laser-scanned to determine the material filling volume. If the material filling volume is less than the remaining capacity of the current unloading area, the vehicle is allowed to enter the current unloading area for unloading, thereby improving unloading efficiency and safety. Furthermore, the unloading strategy can be adjusted promptly based on the warehouse's storage conditions to avoid material accumulation or space waste. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart of an automatic identification and unloading control method for material transportation provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an automatic material transportation identification and unloading control system provided in an embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This application provides an automatic identification and unloading control method for material transportation, including the following steps S1 to S6. Wherein: S1. After the material-carrying vehicle enters the target recognition area, the complete image information of the vehicle's cargo compartment and the image information of the materials inside the cargo compartment are obtained by using a telephoto camera and a short-focus camera, respectively.

[0019] The target identification area is a pre-defined specific range that can be flexibly adjusted according to factors such as the layout, scale, and safety requirements of the actual unloading site.

[0020] By deploying telephoto and short-focus cameras in the target recognition area, comprehensive and accurate image information of the material-carrying vehicle can be acquired from different perspectives. The telephoto camera can capture long-distance information of the entire vehicle and the edges of the cargo compartment, while the short-focus camera can focus on the details of the materials inside the cargo compartment. Dual-camera monitoring ensures the completeness and accuracy of the acquired image information.

[0021] In practical applications, the telephoto camera is installed 5m directly above the target recognition area, with the lens pointing vertically downwards and a field of view of 30°±2°, covering the entire carriage (including the edges); it is coaxially mounted with the short-focus camera (horizontal deviation ≤3mm) and fixed by a rigid bracket to avoid coordinate shifts caused by vibration.

[0022] The short-focus camera is installed 3m directly above the target recognition area, with the lens pointing vertically downwards and a field of view of 60°±2°, focusing on the core area of ​​the material inside the carriage (which accounts for 70% of the total area of ​​the carriage and is the key area for material recognition); it is aligned with the long-focus camera using a coaxial calibration tool to ensure that the optical axes of the two coincide.

[0023] S2. Based on the complete image information of the cargo compartment, determine the effective occlusion ratio of the cover of the material-carrying vehicle, and based on the image information of the material inside the cargo compartment, determine the occlusion ratio of the material.

[0024] Since material-carrying vehicles are generally equipped with covers (or tarpaulins, etc.) to shield the materials, and the materials themselves may also block each other when stacked, it is necessary to determine the effective shielding ratio coefficient of the cover and the material shielding ratio coefficient separately in order to accurately assess the degree of material shielding.

[0025] Meanwhile, the material obscuration ratio is a measure of the proportion of material that cannot be directly observed in an image due to factors such as stacking method and vehicle structure.

[0026] S3. Determine the fusion occlusion coefficient based on the effective occlusion ratio coefficient of the hood and the occlusion ratio coefficient of the material.

[0027] Specifically, by setting the weights of the effective occlusion ratio coefficient of the vehicle cover and the material occlusion ratio coefficient, such as setting the weights of the effective occlusion ratio coefficient of the vehicle cover and the material occlusion ratio coefficient to 0.4 and 0.6 respectively, and then weighting the effective occlusion ratio coefficient of the vehicle cover and the material occlusion ratio coefficient, the fusion occlusion coefficient is obtained.

[0028] S4. When the fusion occlusion coefficient is less than the preset occlusion coefficient threshold, the material category of the loading vehicle is identified by the material image information inside the carriage, and it is determined whether the identified material category is consistent with the material category of the current unloading area.

[0029] Understandably, if the fusion occlusion coefficient is less than the preset occlusion coefficient threshold, it indicates that the image of the materials inside the carriage is less obstructed and can clearly present the material characteristics. However, if the fusion occlusion coefficient is not less than the preset occlusion coefficient threshold, it indicates that the material image is severely obstructed. In this case, the system will trigger a re-capture mechanism to obtain a clearer material image by adjusting camera parameters or re-acquiring the image. If the fusion occlusion coefficient still does not meet the requirements after multiple re-captures, a manual verification prompt will be sent to the management personnel for manual intervention to determine the material category.

[0030] The material categories for the loading vehicles include river sand, gravel, etc. The preset material category for the current unloading area is set according to the actual unloading needs. For example, in a sand and gravel processing plant, if the current unloading area is used to receive river sand, the preset material category is river sand; if it is used to receive gravel, the preset material category is gravel.

[0031] If the identified material category is inconsistent with the material category of the current unloading area, for example, if the truck is carrying crushed stone, but the preset material category of the current unloading area is river sand, the system will immediately trigger the alarm mechanism, issue a warning signal through the sound and light alarm, and display the message "Material category mismatch, entry prohibited" on the monitoring screen. At the same time, the system will keep the barrier gate closed to prevent trucks from entering the current unloading area, thus preventing production accidents or material confusion caused by incorrect material categories.

[0032] S5. If the identified material category is consistent with the material category in the current unloading area, perform a laser scan on the cargo compartment of the material-carrying vehicle, and determine the material filling volume of the material-carrying vehicle based on the laser scan results.

[0033] During the laser scanning process, the lidar emits pulsed lasers at a frequency of 100 times per second. By measuring the time difference between the reflected wave and the emitted wave, the distance between each point on the material surface is accurately calculated. Combined with the pre-stored vehicle body size parameters (length × width × height baseline values) in the material vehicle model database, the material filling volume of the material vehicle is determined.

[0034] S6. Compare the filling volume of the transported material with the remaining capacity of the material in the current unloading area. If the filling volume of the transported material is less than the remaining capacity of the material in the current unloading area, then allow the transported vehicle to enter the current unloading area for unloading.

[0035] The remaining capacity of the material in the unloading area is a dynamic parameter calculated by real-time monitoring of the material accumulation height in the unloading area and combining it with the geometric dimensions of the unloading area. This parameter can be updated every 5 seconds to ensure the real-time nature of the unloading decision.

[0036] When the filling volume of the transported material is less than the remaining capacity, the barrier gate will automatically open and project a green guide light strip to the designated unloading position. The identified material result will be output to the display screen so that the driver can see the barrier gate opening. After verifying that the material result on the display screen matches the material on the vehicle, the vehicle will reverse to unload. If the filling volume of the transported material is greater than or equal to the remaining capacity, a voice prompt will be triggered to indicate that the current unloading area is not large enough. Please select another unloading area and the candidate unloading area that meets the capacity requirements will be highlighted on the electronic map.

[0037] It should be noted that this application acquires complete images of the vehicle's cargo compartment and images of the materials inside the cargo compartment using both telephoto and short-focus cameras when a material-carrying vehicle enters the target recognition area. Based on the complete cargo compartment image, the effective occlusion ratio of the vehicle's roof is determined, and based on the material inside the cargo compartment image, the occlusion ratio of the materials is determined, thus determining the fusion occlusion coefficient. If the fusion occlusion coefficient is less than a preset occlusion coefficient threshold, the material category of the vehicle is identified using the material inside the cargo compartment image. If the identified material category matches the material category in the current unloading area, the cargo compartment of the vehicle is laser-scanned to determine the material filling volume. If the material filling volume is less than the remaining capacity of the current unloading area, the vehicle is allowed to enter the current unloading area for unloading, thereby improving unloading efficiency and safety. Furthermore, the unloading strategy can be adjusted promptly based on the warehouse's storage conditions to avoid material accumulation or space waste.

[0038] Among them, based on the complete image information of the cargo compartment, the effective occupancy ratio coefficient of the vehicle cover is determined, including: S201. Based on the coordinate transformation relationship between the telephoto and short-focus cameras, transform the complete image information of the carriage to the complete image of the carriage in the coordinate system of the short-focus camera.

[0039] Because the coordinate systems of the telephoto and short-focus cameras are different, directly analyzing the images acquired by the two cameras will lead to errors. Therefore, it is necessary to convert the complete image information of the carriage acquired by the telephoto camera to the coordinate system of the short-focus camera to ensure the consistency and accuracy of image analysis.

[0040] Let the coordinate system of the telephoto camera be C. macro (pixel coordinates (u) m ,v m The coordinate system of the short-focal-length camera is C. micro(pixel coordinates (u) μ ,v μ Then, the formula for mapping from macroscopic coordinates to microscopic coordinates is: In the formula, This is the intrinsic parameter matrix for a short-focal-length camera. The rotation matrix between the two cameras. For telephoto cameras, the intrinsic parameter matrix is... It is a translation vector.

[0041] S202. In the converted complete image of the carriage, extract the edge contour information of the cover and determine the area covered by the cover.

[0042] The process involves processing the converted complete image of the carriage using edge detection algorithms (such as the Canny operator) to accurately extract the edge contour information of the carriage cover. Based on the extracted edge contours, a region filling algorithm is used to determine the area covered by the carriage cover, which reflects the actual extent to which the carriage cover occludes the carriage.

[0043] S203. Determine whether the area covered by the vehicle cover overlaps with the image information of the material inside the vehicle compartment. If it is determined that the area covered by the vehicle cover overlaps with the image information of the material inside the vehicle compartment, then the position weight of the area covered by the vehicle cover is determined as the first weight. If it is determined that the area covered by the vehicle cover does not overlap with the image information of the material inside the vehicle compartment, then the position weight of the area covered by the vehicle cover is determined as the second weight. The first weight is greater than the second weight.

[0044] The process begins by obtaining the coordinate range of the area covered by the vehicle hood and the coordinate range of the material image inside the vehicle. A coordinate comparison algorithm is then used to determine if there is any overlap between the two. If an overlap exists, it indicates an overlap between the hood-covered area and the material image. In this case, the positional weight of the hood-covered area is set as the first weight. This first weight can be set to a relatively large value, such as 0.8, to reflect the significant impact of the hood-covered area on the material image occlusion assessment. If no overlap exists, the positional weight of the hood-covered area is set as the second weight. This second weight can be set to a smaller value, such as 0.2, to reflect the degree of influence of the hood-covered area when there is no direct occlusion of the material image. This positional weight setting allows for a more accurate assessment of the actual occlusion effect of the hood on the material image, helping to more accurately evaluate the impact of hood occlusion on material recognition and thus improving the accuracy of material category determination.

[0045] S204. Perform grayscale processing on the area covered by the vehicle cover and the converted complete vehicle image respectively, and count the total number of pixels in the area covered by the vehicle cover and the total number of pixels in the converted complete vehicle image.

[0046] Grayscale processing is the process of converting a color image to a grayscale image. By removing color information from the image and retaining only brightness information, it simplifies the image analysis process. A grayscale processing algorithm (such as a weighted average method) is applied to the converted complete image of the carriage and the area covered by the canopy to convert the RGB value of each pixel to its corresponding grayscale value. Subsequently, the total number of pixels N in the grayscale-processed canopy-covered area is counted. cover The total number of pixels N in the converted complete image of the carriage. total These two values ​​will be used in the subsequent calculation of the effective shading ratio coefficient of the hood.

[0047] S205. Determine the effective occlusion ratio coefficient of the cover of the material-carrying vehicle based on the positional weight of the cover-covered area, the total number of pixels in the cover-covered area, and the total number of pixels in the converted complete image of the cargo compartment.

[0048] The weighted total number of pixels in the area covered by the hood is obtained by multiplying the positional weight of the area covered by the hood by the total number of pixels in the area covered by the hood. This weighted total number of pixels in the area covered by the hood is then divided by the total number of pixels in the converted complete image of the cargo compartment to obtain the effective occlusion ratio coefficient of the hood of the cargo vehicle.

[0049] In some embodiments, determining the material obscuration ratio coefficient based on image information of materials inside the carriage includes: S211. Preprocess the image information of materials inside the carriage to enhance the material features in the image.

[0050] The preprocessing includes denoising the image to eliminate random noise that may be introduced during image acquisition. For example, a Gaussian filtering algorithm is used, which calculates a weighted average of each pixel and its neighboring pixels by setting an appropriate kernel size and standard deviation parameter, thereby smoothing the image and reducing noise interference. At the same time, image contrast enhancement is performed to highlight the difference between the material and the background. For example, histogram equalization is used to transform the histogram of the original image into a uniformly distributed histogram through nonlinear transformation, thereby expanding the dynamic range of the image and making the material characteristics more obvious.

[0051] S212. Using a preset material detection algorithm, detect the material area in the pre-processed material image information inside the carriage.

[0052] The pre-defined material detection algorithm, such as the YOLO series, uses trained model parameters to extract features and generate region suggestions from the pre-processed image. This algorithm can automatically identify the location of materials in the image and generate bounding boxes containing the material regions, along with the coordinate information of the bounding boxes (such as the coordinates of the top left and bottom right corners).

[0053] S213. Perform grayscale processing on the material area, count the total number of pixels in the material area after grayscale processing, and determine the total number of pixels in the occluded area of ​​the material based on the total number of pixels in the material area and the total number of pixels in the converted complete image of the carriage.

[0054] Specifically, by performing grayscale processing on the material area, the material area is converted into a grayscale image, and then the total number of pixels N is counted. material Subsequently, based on the total number of pixels N of the converted complete image of the carriage... total The total number of pixels N in the material area material The difference can be used to calculate the total number of pixels N in the area where the material is obscured. occluded This simplifies to estimation by using regions where no material features were detected in image analysis.

[0055] S214. Determine the material occlusion ratio coefficient based on the total number of pixels in the area where the material is occluded and the total number of pixels in the converted complete image of the carriage.

[0056] The material occlusion ratio is determined by the ratio of the total number of pixels in the area where the material is occluded to the total number of pixels in the converted complete image of the carriage, thus reflecting the degree to which the material is occluded in the image.

[0057] In some embodiments, the material category of the loading vehicle is identified using image information of the material inside the vehicle compartment, and it is determined whether the identified material category matches the material category in the current unloading area, including: S401. Input the image information of the material inside the car into the trained material recognition model, so that the trained material recognition model outputs the material category of the loading vehicle; wherein, the trained material recognition model is obtained by training a preset neural network model based on a training dataset, and the training dataset contains material image information samples of various material categories inside the car and corresponding material category labels.

[0058] The trained material recognition model uses a deep convolutional neural network architecture and achieves accurate recognition of different material categories through multi-level feature extraction and classifier design.

[0059] S402. Compare the identified material category with the preset material category of the current unloading area. If the identified material category matches the preset material category of the current unloading area, the material category is determined to be successfully matched. If the identified material category does not match the preset material category of the current unloading area, an alarm mechanism is triggered to prohibit the material-carrying vehicle from entering the current unloading area.

[0060] During the comparison process, the system first converts the identified material category into the same format or code as the preset material category to ensure accuracy. If they match perfectly, the system is considered a successful match and continues with the subsequent unloading process. If there are discrepancies, whether in the category name or the code, the system will immediately trigger an alarm mechanism. Once activated, the alarm mechanism will not only issue a clear warning signal through an audible and visual alarm to alert on-site personnel, but will also clearly display the message "Material category mismatch, entry prohibited" on the monitoring screen, ensuring timely and accurate information delivery. Furthermore, the system will automatically keep the barrier gate closed, strictly prohibiting material-carrying vehicles from entering the current unloading area, thereby effectively preventing production accidents or material confusion caused by incorrect material categories and ensuring the safe and orderly progress of the entire unloading process.

[0061] In some embodiments, laser scanning is performed on the cargo compartment of the material-carrying vehicle, and the filling volume of the material-carrying vehicle is determined based on the laser scanning results, including: S501. A laser beam is emitted from a lidar to the surface of the material inside the cargo compartment of a material-carrying vehicle. The reflected laser signal is received. By measuring the time difference between the emission and reception of the laser beam, and combining the time difference with the speed of light, the distance from the material surface to the lidar is calculated.

[0062] The laser beam emitted by the lidar has high directionality and high energy density, enabling it to precisely illuminate specific points on the surface of materials inside the vehicle. When the laser beam encounters the material surface, some of the laser energy is reflected back and captured by the lidar's receiver. By accurately measuring the time difference between the laser beam's emission and reception, and combining this with the known speed of light, the distance from the material surface to the lidar can be accurately calculated.

[0063] S502. Determine the height of the material surface relative to the ground based on the relative height of the lidar and the distance from the material surface to the lidar.

[0064] The lidar is installed at a fixed height relative to the ground, and this height is stored as a known parameter in the system database. Once the real-time distance from the material surface to the lidar is obtained, the system can accurately determine the height of the material surface relative to the ground by subtracting the distance from the lidar from the lidar's height relative to the ground. This directly reflects the height of the material accumulation inside the vehicle.

[0065] S503. Determine the material depth based on the height of the material surface relative to the ground and the distance between the bottom of the cargo compartment of the loading vehicle and the ground.

[0066] Among them, the distance between the bottom of the cargo compartment of the material-carrying vehicle and the ground is known. This distance is defined in the vehicle design specifications and stored in the system. By calculating the difference between the height of the material surface relative to the ground and the distance between the bottom of the carriage and the ground, the actual depth of the material inside the carriage can be accurately determined.

[0067] S504. Determine the material filling volume of the material-carrying vehicle based on the product of the length of the cargo compartment, the width of the cargo compartment, and the depth of the material.

[0068] The length and width of the cargo compartment of the material-carrying vehicle are known parameters obtained from the vehicle's dimensions and stored in the system. After determining the material depth, the system will automatically retrieve the data of the cargo compartment length and width, multiply them by the material depth, and accurately determine the filling volume of the material currently being transported by the vehicle, i.e., the actual space occupied by the material in the cargo compartment.

[0069] In some embodiments, the method further includes: S51. Use laser scanning to scan the current unloading area, extract the point cloud of the material surface in the current unloading area, and determine the average height of the material surface based on the point cloud of the material surface.

[0070] Among these methods, a high-precision lidar is used to perform a 3D point cloud scan of the current unloading area, acquiring three-dimensional point cloud data of the material surface. This point cloud data accurately reflects the spatial height distribution characteristics of the material surface within the unloading area. Based on the material surface point cloud, the average height of the material surface is determined as follows: In the formula, The average height of the material surface. Let i be the height of the i-th point cloud. The density weight of the i-th point cloud (regions with high point cloud density) =1.2, areas with low point cloud density =0.8, the point cloud density threshold is set as more than 500 points per cubic meter for high density and less than 200 points per cubic meter for low density), N is the number of points in the cloud.

[0071] S52. Determine the material volume of the current unloading zone based on the average height of the material surface and the equivalent radius of the current unloading zone.

[0072] Regarding the material volume in the current unloading area, since the material accumulation pattern is uneven, it is necessary to perform equivalent processing on the material accumulation pattern in the current unloading area. The current unloading area is considered as an approximate cylinder (or other suitable geometric shape, adjusted according to the actual situation), and its equivalent radius R is obtained through measurement or known methods. Here, R is rounded up, and L and W are the length and width of the current unloading area, respectively.

[0073] Using the formula for the volume of a cylinder and the average height of the material surface, calculate the material volume V of the current unloading zone: In the formula, This is the corrected average height of the material surface. The porosity correction factor for the material (river sand) =0.95, gravel =0.9).

[0074] S53. Determine the remaining material capacity of the current unloading area based on the preset total material volume and the current material volume of the unloading area.

[0075] Among them, the preset total material volume V of the current unloading area total This is a pre-set parameter stored in the system, representing the maximum volume of material that the unloading zone can hold. It is calculated by comparing the current material volume V of the unloading zone with the preset total material volume V0. total The difference can accurately determine the remaining capacity of the material in the current unloading area.

[0076] In some embodiments, the method further includes: S61. If the filling volume of the transported material is not less than the remaining accommodating volume of the material in the current unloading area, then select multiple other candidate unloading areas that are consistent with the material category of the transported vehicle, and determine the remaining accommodating volume of the material in the multiple other candidate unloading areas.

[0077] If the filling volume of the transported material is not less than the remaining material capacity of the current unloading area, the transported vehicle will not be guided to the current unloading area. Instead, a screening mechanism will be activated to select multiple other candidate unloading areas from all available unloading areas that match the type of material being transported by the transported vehicle. This screening process is based on unloading area information stored in the system, including the preset material category for each unloading area and its current remaining material capacity. By comparing the material category of the transported vehicle with the preset material categories of each candidate unloading area, it is ensured that only unloading areas with matching categories are included in the candidate list.

[0078] S62. Compare the filling volume of the transported material with the remaining capacity of the material in multiple other candidate unloading areas, and select multiple other candidate unloading areas whose filling volume of the transported material is smaller than the remaining capacity of the material.

[0079] After identifying several other candidate unloading areas that match the material category of the loading vehicle, the system further compares the loading vehicle's material filling volume with the remaining material capacity of these candidate unloading areas. Specifically, the system compares the loading vehicle's material filling volume with the remaining material capacity of each candidate unloading area, selecting those candidate unloading areas whose loading vehicle's material filling volume is smaller than their remaining material capacity. This step ensures that the loading vehicle can be guided to an unloading area with sufficient space to accommodate its material, avoiding production problems caused by material overflow or incomplete unloading.

[0080] S63. Among the multiple other candidate unloading areas selected, the candidate unloading area that is closest to the material-carrying vehicle is selected as the optimal unloading area.

[0081] After identifying several candidate unloading areas that meet the condition that the filling volume of the transported material is less than the remaining capacity of the material, the system activates a distance calculation module. Using the real-time location information of the transport vehicle and the coordinate data of each candidate unloading area, a Geographic Information System (GIS) algorithm is used to calculate the actual travel distance between them. The candidate unloading areas are then sorted in order of distance from closest to furthest, with the closest candidate unloading area to the transport vehicle being selected as the optimal unloading area. This not only effectively shortens the travel time of the transport vehicle and reduces transportation costs, but also reduces the risk of material spillage due to long-distance travel, further improving the efficiency and safety of the unloading process.

[0082] S64. Notify the material-carrying vehicle to proceed to the optimal unloading area for unloading, and send the location information of the optimal unloading area and driving route guidance information to the material-carrying vehicle.

[0083] Once the optimal unloading area is determined, detailed unloading instructions are immediately sent to the loading vehicle via a screen set up in the target recognition area. These instructions include the specific location information of the optimal unloading area, such as its number, coordinates, or address description, as well as guidance on the best driving route from the current location to the optimal unloading area. The driving route guidance information is determined using a map in a Geographic Information System (GIS) to determine the driving route between the current unloading area and the optimal unloading area, ensuring that the driver can safely and quickly reach the optimal unloading area and preventing accidental entry or driving errors due to driver negligence.

[0084] In some embodiments, the method further includes: After the material-carrying vehicle enters the current unloading area and finishes unloading, monitor that the material-carrying vehicle has completely left the current unloading area, update the material category of the current unloading area to the material category carried by the material-carrying vehicle, and update the remaining capacity of the material in the current unloading area.

[0085] Once the material-carrying vehicle has completed unloading and completely left the current unloading area, the system automatically triggers an update mechanism. First, the system updates the material category in the current unloading area to the category transported by the vehicle. This update ensures the real-time accuracy of the material category in the unloading area. Simultaneously, the system recalculates and updates the remaining material capacity of the current unloading area based on the amount of material unloaded by the vehicle. This calculation is based on the preset total material capacity of the unloading area and the amount of material already unloaded; the new remaining material capacity is obtained through simple subtraction. The updated material category and remaining material capacity information are immediately stored in the system database for reference and use in subsequent unloading operations.

[0086] like Figure 2 As shown, this application also provides an automatic identification and unloading control system for material transportation, including: The image acquisition module 10 is used to acquire complete image information of the cargo compartment and image information of the materials inside the cargo compartment through a telephoto camera and a short-focus camera respectively after the identified material-carrying vehicle enters the target identification area. The occlusion ratio determination module 20 is used to determine the effective occlusion ratio coefficient of the cover of the material-carrying vehicle based on the complete image information of the carriage, and to determine the occlusion ratio coefficient of the material based on the image information of the material inside the carriage. The occlusion fusion determination module 30 is used to determine the fusion occlusion coefficient based on the effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material. The material category comparison module 40 is used to identify the material category of the loading vehicle by using the material image information inside the carriage when the fusion occlusion coefficient is less than the preset occlusion coefficient threshold, and to determine whether the identified material category is consistent with the material category of the current unloading area. The material volume determination module 50 is used to perform laser scanning on the cargo compartment of the material-carrying vehicle when the identified material category is consistent with the material category of the current unloading area, and to determine the material filling volume of the material-carrying vehicle based on the laser scanning results. The unloading control module 60 is used to compare the filling volume of the transported material with the remaining capacity of the material in the current unloading area. If the filling volume of the transported material is less than the remaining capacity of the material in the current unloading area, the loaded vehicle is allowed to enter the current unloading area for unloading.

[0087] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0088] It should be noted that the user information (including but not limited to vehicle images) and data (including but not limited to data used for analysis, data stored, and data displayed) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0089] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0090] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0091] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for automatic identification and unloading control of material transportation, characterized in that, include: Once the material-carrying vehicle enters the target recognition area, the complete image information of the vehicle's cargo compartment and the image information of the materials inside the cargo compartment are obtained by using a telephoto camera and a short-focus camera, respectively. Based on the complete image information of the cargo compartment, the effective occlusion ratio coefficient of the cover of the material-carrying vehicle is determined, and based on the image information of the materials inside the cargo compartment, the occlusion ratio coefficient of the materials is determined. The fusion occlusion coefficient is determined based on the effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material. If the fusion occlusion coefficient is less than a preset occlusion coefficient threshold, the material category of the loading vehicle is identified by the material image information inside the carriage, and it is determined whether the identified material category is consistent with the material category of the current unloading area. If the identified material category is consistent with the material category in the current unloading area, the cargo compartment of the material-carrying vehicle is laser-scanned, and the material filling volume of the material-carrying vehicle is determined based on the laser scanning results. If the filling volume of the transported material is compared with the remaining capacity of the material in the current unloading area, and the filling volume of the transported material is smaller than the remaining capacity of the material in the current unloading area, then the transported vehicle is allowed to enter the current unloading area to unload.

2. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, The step of determining the effective occupancy ratio coefficient of the vehicle cover based on the complete image information of the cargo compartment includes: Based on the coordinate transformation relationship between the telephoto camera and the short-focus camera, the complete image information of the carriage is transformed into a complete image of the carriage in the coordinate system of the short-focus camera; In the converted complete image of the carriage, the edge contour information of the cover is extracted, and the area covered by the cover is determined; Determine whether the area covered by the vehicle cover overlaps with the image information of the material inside the vehicle compartment. If it is determined that the area covered by the vehicle cover overlaps with the image information of the material inside the vehicle compartment, then the position weight of the area covered by the vehicle cover is determined to be a first weight. If it is determined that the area covered by the vehicle cover does not overlap with the image information of the material inside the vehicle compartment, then the position weight of the area covered by the vehicle cover is determined to be a second weight. Wherein, the first weight is greater than the second weight. The area covered by the vehicle cover and the converted complete image of the vehicle compartment are processed in grayscale, and the total number of pixels in the area covered by the vehicle cover and the total number of pixels in the converted complete image of the vehicle compartment are counted. The effective occlusion ratio coefficient of the vehicle cover is determined based on the positional weight of the area covered by the vehicle cover, the total number of pixels in the area covered by the vehicle cover, and the total number of pixels in the converted complete image of the vehicle compartment.

3. The automatic identification and unloading control method for material transportation according to claim 2, characterized in that, Based on the image information of the materials inside the carriage, determine the material obscuration ratio coefficient, including: Preprocess the image information of materials inside the carriage to enhance the material features in the image; Using a pre-defined material detection algorithm, material areas are detected in the pre-processed material image information inside the carriage; The material area is processed in grayscale, and the total number of pixels in the material area after grayscale processing is counted. Based on the total number of pixels in the material area and the total number of pixels in the converted complete image of the carriage, the total number of pixels in the area where the material is occluded is determined. The occlusion ratio coefficient of the material is determined based on the total number of pixels in the area where the material is obscured and the total number of pixels in the converted complete image of the carriage.

4. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, The step of determining the fusion occlusion coefficient based on the effective occlusion ratio coefficient of the hood and the occlusion ratio coefficient of the material includes: The effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material are weighted to obtain the fusion occlusion coefficient.

5. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, The step of identifying the material category of the loading vehicle through the material image information inside the carriage, and determining whether the identified material category is consistent with the material category of the current unloading area, includes: The image information of the materials inside the carriage is input into a trained material recognition model, so that the trained material recognition model outputs the material category of the material-carrying vehicle; wherein, the trained material recognition model is obtained by training a preset neural network model based on a training dataset, and the training dataset contains material image information samples of various material categories inside the carriage and corresponding material category labels; The identified material category is compared with the preset material category of the current unloading area. If the identified material category matches the preset material category of the current unloading area, the material category is considered to be successfully matched. If the identified material category does not match the preset material category of the current unloading area, an alarm mechanism is triggered to prohibit the material-carrying vehicle from entering the current unloading area.

6. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, The step of performing laser scanning on the cargo compartment of the material-carrying vehicle and determining the material filling volume of the vehicle based on the laser scanning results includes: The laser radar emits a laser beam to the surface of the material inside the cargo compartment of the material-carrying vehicle, receives the reflected laser signal, and calculates the distance from the material surface to the laser radar by measuring the time difference between the emission and reception of the laser beam and combining the time difference with the speed of light. The height of the material surface relative to the ground is determined based on the relative height of the lidar to the ground and the distance from the material surface to the lidar. The material depth is determined based on the height of the material surface relative to the ground and the distance between the bottom of the cargo compartment of the material-carrying vehicle and the ground. The material filling volume of the material-carrying vehicle is determined by multiplying the length and width of the cargo compartment of the material-carrying vehicle with the depth of the material.

7. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, Also includes: The current unloading area is scanned with a laser to extract the point cloud of the material surface in the current unloading area, and the average height of the material surface is determined based on the point cloud of the material surface. The material volume of the current unloading zone is determined based on the average height of the material surface and the equivalent radius of the current unloading zone. The remaining material capacity of the current unloading area is determined based on the preset total material volume of the current unloading area and the material volume of the current unloading area.

8. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, Also includes: If the filling volume of the transported material is not less than the remaining material capacity of the current unloading area, then multiple other candidate unloading areas that are consistent with the material category of the transported vehicle are selected, and the remaining material capacity of the multiple other candidate unloading areas is determined. By comparing the filling volume of the transported material with the remaining capacity of the material in multiple other candidate unloading areas, multiple other candidate unloading areas with a filling volume of the transported material smaller than the remaining capacity of the material are selected. Among the multiple other candidate unloading areas selected, the candidate unloading area that is closest to the material-carrying vehicle is selected as the optimal unloading area. The system notifies the material-carrying vehicle to proceed to the optimal unloading area for unloading, and sends the location information of the optimal unloading area and driving route guidance information to the material-carrying vehicle.

9. The automatic identification and unloading control method for material transportation according to claim 1, characterized in that, Also includes: After the material-carrying vehicle enters the current unloading area and finishes unloading, and after monitoring that the material-carrying vehicle has completely left the current unloading area, the material category of the current unloading area is updated to the material category carried by the material-carrying vehicle, and the remaining capacity of the material in the current unloading area is updated.

10. An automatic identification and unloading control system for material transportation, characterized in that, include: The image acquisition module is used to acquire complete image information of the cargo compartment and image information of the materials inside the cargo compartment through a telephoto camera and a short-focus camera, respectively, when the material-carrying vehicle enters the target recognition area. The occlusion ratio determination module is used to determine the effective occlusion ratio coefficient of the cover of the material-carrying vehicle based on the complete image information of the carriage, and to determine the occlusion ratio coefficient of the material based on the image information of the material inside the carriage. The occlusion fusion determination module is used to determine the fusion occlusion coefficient based on the effective occlusion ratio coefficient of the vehicle cover and the occlusion ratio coefficient of the material. The material category comparison module is used to identify the material category of the loading vehicle by means of the material image information inside the carriage when the fusion occlusion coefficient is less than a preset occlusion coefficient threshold, and to determine whether the identified material category is consistent with the material category of the current unloading area. The material volume determination module is used to perform laser scanning on the cargo compartment of the material-carrying vehicle when the identified material category is consistent with the material category of the current unloading area, and to determine the material filling volume of the material-carrying vehicle based on the laser scanning results. The unloading control module is used to compare the filling volume of the transported material with the remaining capacity of the material in the current unloading area. If the filling volume of the transported material is less than the remaining capacity of the material in the current unloading area, the module allows the transported vehicle to enter the current unloading area for unloading.

Images