Passage monitoring control method, apparatus, device, storage medium and program

Abstract

To provide a passage monitoring control method in a production workshop for a wound yarn package.SOLUTION: A method includes: acquiring scan data acquired within a vehicle body peripheral region of an AGV that needs to be used to transport a wound yarn package in a production workshop for the wound yarn package; performing video acquisition on at least a portion of a region of any one of a plurality of monitoring control target passages by one of a plurality of cameras; acquiring a target passage in which a target body is located when it is determined that the target body is present based on the scan data acquired by the vehicle body acquisition assembly and / or the video data acquired by the camera; and generating target forecast / warning information for the target passage in which the target body is located.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to the field of data processing technology, and in particular to an aisle monitoring control method, apparatus, device, storage medium, and program. [Background technology]

[0002] In a yarn package production workshop, an automated guided vehicle (AGV) is an important means of transportation. Generally, an AGV runs along a predetermined route. If an operator appears on the route, it may cause a safety accident, even resulting in injury or death. Therefore, an effective monitoring and control method is required to effectively solve the above problem. Summary of the Invention [Problem to be solved by the invention]

[0003] The present disclosure provides an aisle monitoring control method, apparatus, device, storage medium, and program to solve or alleviate one or more technical problems in the prior art. [Means for solving the problem]

[0004] In a first aspect, the present disclosure provides an aisle monitoring control method, the method comprising: Obtaining scanning data collected within a vehicle body surrounding area by a vehicle body collection assembly of an automated guided vehicle AGV, the AGV being one of a plurality of AGVs, the AGV in the plurality of AGVs traveling along one of a plurality of monitored and controlled paths, the plurality of monitored and controlled paths being a plurality of paths that need to be used to transport wound yarn packages in a wound yarn package production workshop, the vehicle body surrounding area including at least a portion of the monitored and controlled path along which the AGV travels; Obtaining video data collected by a camera within a video collection area, the camera being one of a plurality of cameras and used to collect video of at least a portion of a surveillance-controlled passageway among the plurality of surveillance-controlled passageways, the video collection area including at least a portion of the surveillance-controlled passageway that can be collected by the camera; When determining that a target object exists based on the scanning data collected by the vehicle body collection assembly and / or the video data collected by the camera, obtain a target passageway in which the target object is located, and the target passageway is one of the plurality of monitored and controlled passageways; and generating target pre-alarm information for a target passage in which the target object is located.

[0005] In a second aspect, the present disclosure provides an aisle monitoring control device, the device comprising: an acquisition unit for acquiring scanning data collected within a vehicle body surrounding area by a vehicle body collection assembly of an automated guided vehicle AGV and acquiring video data collected within a video collection area by a camera, the AGV being one of a plurality of AGVs, the AGV in the plurality of AGVs traveling along one of a plurality of monitored and controlled paths, the plurality of monitored and controlled paths being a plurality of paths that need to be used to transport wound packages in a wound package production workshop, the vehicle body surrounding area including at least a portion of the monitored and controlled path along which the AGV travels, the camera being one of a plurality of cameras, and being used to perform video collection for at least a portion of the monitored and controlled path of the one of the plurality of monitored and controlled paths, the video collection area including at least a portion of the monitored and controlled path that the camera can collect; and a processing unit for, when it is determined that a target object exists based on the scanning data collected by the vehicle body collection assembly and / or the video data collected by the camera, acquiring a target passage in which the target object is located, which is one of the plurality of monitored and controlled passages, and generating target predictive / alarm information for the target passage in which the target object is located.

[0006] In a third aspect, the present disclosure provides an electronic device, the device comprising: At least one processor; a memory in communication with the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, cause the implementation of any one of the methods in the embodiments of the present disclosure.

[0007] In a fourth aspect, there is provided a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform any one of the methods in the embodiments of the present disclosure. In a fifth aspect, there is provided a program for implementing any one of the methods in the embodiments of the present disclosure when executed by a processor.

[0008] In this way, according to the solution disclosed herein, the acquired scanning data and / or video data can be detected, thereby effectively improving the response efficiency to pre-alarm information, and laying the foundation for effectively improving the efficiency of troubleshooting through monitoring and control data of different granularities.

[0009] It should be understood that the contents described herein are not intended to describe key points or important features of the embodiments of the present disclosure, nor are they used to limit the scope of the present disclosure. Other features of the present disclosure are facilitated by the following description. [Brief description of the drawings]

[0010] In the accompanying drawings, the same numbers represent the same or similar parts or elements throughout the several views, unless otherwise stated. The accompanying drawings are not necessarily drawn to scale. It should be understood that the drawings depict only some embodiments provided by the present disclosure and should not be considered as limiting the scope of the present disclosure. [Figure 1] 1 is a schematic flowchart of an aisle monitoring control method according to an embodiment of the present disclosure; [Diagram 2] FIG. 2 is a schematic diagram illustrating a configuration of a first detection model according to an embodiment of the present disclosure. [Diagram 3] FIG. 13 is a schematic diagram illustrating the configuration of a fourth network layer including two dense layers according to one embodiment of the present disclosure. [Figure 4] FIG. 2 is a schematic diagram illustrating the configuration of a second detection model according to an embodiment of the present disclosure. [Diagram 5] 1 is a schematic diagram showing a configuration of a passage monitoring control device according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a block diagram of an electronic device for an aisle monitoring control method according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] The present disclosure will now be described in more detail with reference to the accompanying drawings, in which like reference numbers represent functionally identical or similar elements, and in which various aspects of embodiments are illustrated, and which, unless otherwise noted, are not necessarily drawn to scale.

[0012] Furthermore, in order to better explain the present disclosure, many specific details are described in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can be similarly implemented without specific details. In some embodiments, methods, means, components, circuits, etc. that are well known to those skilled in the art are not described in detail so as not to obscure the gist of the present disclosure. Currently, in a yarn package production workshop, the produced yarn package is generally transported to a designated location by an automated guided vehicle (AGV), but in a yarn package production workshop using an AGV, people and vehicles may travel together, and especially when the passage is narrow, a collision accident may occur, resulting in damage to the AGV and even causing injury to personnel. Therefore, in order to reduce damage to the AGV and effectively avoid injury to personnel, a real-time and efficient monitoring and control method is required.

[0013] Based on this, the solution disclosed herein provides an aisle monitoring and control method, which monitors and controls multiple aisles along which an AGV travels in real time and efficiently.

[0014] Specifically, Figure 1 is a schematic flow chart of an aisle monitoring control method according to an embodiment of the present application. The method is optionally applied to electronic devices such as personal computers, servers, server clusters, etc. The method includes at least a part of the following contents. As shown in Figure 1, it includes:

[0015] In step S101, scan data collected within the vehicle body surrounding area by the vehicle body collection assembly of the AGV is obtained.

[0016] Here, the AGV is one of a plurality of AGVs, and the AGV in the plurality of AGVs travels along one of a plurality of monitored and controlled paths, the plurality of monitored and controlled paths being paths that need to be used to transport wound yarn packages in a wound yarn package production workshop, and the vehicle body surrounding area includes at least a portion of the monitored and controlled path along which the AGV travels.

[0017] In one example, a vehicle body collection assembly (e.g., laser radar) is provided at the front of the AGV. In addition, a vehicle body collection assembly (e.g., laser radar) may be provided at the rear of the AGV, so that the AGV in the monitored and controlled passage can always collect data in the traveling direction.

[0018] In step S102, video data collected by a camera within a video collection area is obtained.

[0019] Here, the camera is one of a plurality of cameras, and the camera is used to collect video of at least a portion of an area of ​​one of the plurality of monitored and controlled passages, and the video collection area includes at least a portion of the area of ​​the monitored and controlled passage that the camera can collect video from.

[0020] It should be understood that at least one camera can be installed in the same monitored and controlled passageway, and can be used to monitor and control the monitored and controlled passageway. Furthermore, when two or more cameras are installed in the same monitored and controlled passageway, the video collection areas of different cameras can be different, as long as the monitored and controlled passageway can be monitored and controlled, and the solution of the present disclosure does not limit the specific locations where the cameras are installed. Furthermore, the number of cameras installed in different monitored and controlled passageways can be the same or different, and the solution of the present disclosure does not limit this.

[0021] In step S103, if it is determined that a target object exists based on the scanning data collected by the body collection assembly and / or the video data collected by the camera, a target passage in which the target object is located is obtained.

[0022] Here, the target passage is one of a plurality of passages subject to monitoring and control.

[0023] It should be understood that the solution of the present disclosure can obtain a target passage in which the target object is located when it is determined that a target object exists based on the scanning data collected by the body collection assembly, or can obtain a target passage in which the target object is located when it is determined that a target object exists based on the video data collected by the camera, or can obtain a target passage in which the target object is located when it is determined that a target object exists based on the scanning data collected by the body collection assembly and the video data collected by the camera.

[0024] In one example, the object may specifically include, but is not limited to, at least one of a person and an AGV that has stopped working.

[0025] In step S104, target pre-alarm information of the target passage where the target object is located is generated.

[0026] In one example, the target pre-alarm information includes a pre-set pre-alarm signal, such as a pre-alarm audio (e.g., a pre-set broadcast), a pre-alarm signal light, a pre-alarm telephone, etc., but the solution of the present disclosure is not limited thereto.

[0027] Therefore, the solution disclosed herein can detect whether a target object exists based on the acquired scanning data and / or video data, thereby quickly locating a target passage where the target object is located, and further generate target pre-alarm information for the target passage, thus effectively improving the response efficiency to the pre-alarm information, and laying a foundation for effectively improving the efficiency of troubleshooting through monitoring and control data of different granularities.

[0028] Furthermore, in an application scenario of wound yarn package production, the solution of the present disclosure can quickly notify workers based on the generated pre-alarm information, so that they can avoid or eliminate the danger in a timely manner, thus providing technical support for effectively reducing damage to AGVs and production equipment and effectively preventing injuries to personnel, and further providing technical support for maximally ensuring the normal operation of the workplace and improving workplace safety.

[0029] In one specific example of the solution disclosed herein, the target predictive / alarm information of the target passage where the target object is located can be obtained by the following manner: Specifically, when it is determined that a target object exists based on the scanning data collected by the body collecting assembly and / or the video data collected by the camera described above, obtaining the target passage where the target object is located and generating the target predictive / alarm information of the target passage where the target object is located (i.e., step S103 described above) specifically includes any one of the following: In method 1, based on the scanning data collected by the vehicle body collection assembly, if it is determined that a target object exists in the scanning data, a target passage in which the target object is located in the scanning data is obtained, and scanning pre-alarm information of the target passage in which the target object is located in the scanning data is generated. It should be understood that in method 1, the scanning data collected by the body collection assembly of the AGV can be detected to determine whether an object exists; if it is determined that an object exists, the target passage in which the object is located in the scanning data is obtained; and at this time, scanning pre-alarm information of the target passage in which the object is located in the scanning data is directly generated.

[0030] In method 2, based on the video data collected by the camera, if it is determined that a target object is present in the video data, a target passage in which the target object is located in the video data is obtained, and video pre-alarm information of the target passage in which the target object is located in the video data is generated. It should be understood that in method 2, the video data collected by the camera within the video collection area can be detected, and whether or not a target object exists can be determined. If it is determined that a target object exists, the target passage in which the target object is located in the video data is obtained, and at this time, video pre-alarm information of the target passage in which the target object is located in the video data is directly generated. In addition, the "target object" present in the scanning data and the "target object" present in the video data may be the same "target object" or may be two different "target objects", and the solution disclosed herein is not limited thereto. In method 3, based on the scanning data collected by the vehicle body collection assembly, if it is determined that a target object exists in the scanning data, a target passage in which the target object is located is obtained in the scanning data; based on the video data collected by the camera, if it is determined that a target object exists in the video data, a target passage in which the target object is located is obtained in the video data; if it is determined that the target passage in which the target object is located obtained by the scanning data is the same as the target passage in which the target object is located obtained by the video data, mixed pre-alarm information for the target passage is generated.

[0031] That is, in the method 3, when it is determined that there is a target in the scanning data, the pre-alarm information is not generated directly, and when it is determined that there is a target in the video data, the pre-alarm information is not generated directly, but it is further determined whether the target passage in which the target is located in the scanning data is the same as the target passage in which the target is located in the video data, and when the target passage in which the target is located in the scanning data is the same as the target passage in which the target is located in the video data, the mixed pre-alarm information is generated. Alternatively, when the target passage in which the target is located in the scanning data is different from the target passage in which the target is located in the video data, the scanning pre-alarm information of the target passage in which the target is located in the scanning data can be generated for the scanning data, and the video pre-alarm information of the target passage in which the target is located in the video data can be generated for the video data.

[0032] For example, in one example, scanning data collected by a body collection assembly is detected, it is determined that Worker A is present in the scanning data, and the target passage in which Worker A is located is obtained; video data collected within the video collection area by a camera is detected, it is determined that Worker A is also present in the video data, and the target passage in which Worker A is located is obtained. At this time, it is indicated that the area collected by the body collection assembly and the area collected by the camera both correspond to the same monitored and controlled passage, i.e., the target passages of both are the same, and based on this, mixed pre-alarm information for the target passage is generated.

[0033] Alternatively, in another example, scanning data collected by the body collection assembly is detected, it is determined that worker A is present in the scanning data, and the target passage in which worker A is located is obtained, and video data collected within the video collection area by the camera is detected, it is determined that worker B is present in the video data, and the target passage in which worker B is located is obtained. In this case, if the target passages of both workers are the same, i.e., they belong to the same passage, it can be determined that worker A and worker B are simultaneously present in the same target passage, and at this time, mixed pre-alarm information for the target passage is generated.

[0034] In another example, scanning data collected by a vehicle body collection assembly is detected, it is determined that worker A is present in the scanning data, and the target passage in which worker A is located is obtained, and video data collected within the video collection area by a camera is detected, it is determined that worker B is present in the video data, and the target passage in which worker B is located is obtained. In this case, if the two target passages are different, it can be determined that workers are present in both of the two different target passages, and at this time, respective pre-alarm information is generated for each target passage; for example, for the scanning data, scanning pre-alarm information of the target passage in which the target object is located in the scanning data is generated, and for the video data, video pre-alarm information of the target passage in which the target object is located in the video data is generated.

[0035] Furthermore, in practical applications, according to the needs of different scenarios, any one of the above three methods can be selected to generate early warning information, or two of them, or all three can be selected, and this is not a limitation of the solution disclosed herein.

[0036] In one specific example of the solution of the present disclosure, the mixed pre-alarm information, the scanning pre-alarm information and the video pre-alarm information have decreasing priorities.

[0037] That is, in this example, the mixed pre-warning information has a higher priority than the scanned pre-warning information, which in turn has a higher priority than the video pre-warning information.

[0038] It should be understood that the pre-alarm information of different priorities may be different, which makes it easier for operators to clearly distinguish the priority of the current pre-alarm information, thereby further improving the granularity of supervisory control.

[0039] In addition, different processing measures can be set according to the above-mentioned priorities. For example, the mixed pre-alarm information generated by the method 3 belongs to the highest level of danger, and at this time, the mixed pre-alarm information can be generated and a highest level control command can be generated to remotely control the AGV traveling along the target passage, and the highest level control command is used to control the AGV to adjust its current operating state, such as adjusting from the current normal operating state to a temporary stop state, and then restoring to the normal operating state after stopping for a preset time, or adjusting the current planned route to avoid the target object, etc.

[0040] For example, the scanning pre-alarm information generated by the method 1 belongs to the next higher level of danger, and in this case, the scanning pre-alarm information is generated and a next higher level control command can be generated to remotely control the AGV traveling along the target passage, and the next higher level control command is used to control the AGV to adjust the current traveling speed, such as deceleration processing, etc. For example, the video pre-alarm information generated by the method 2 belongs to the general level of danger, and in this case, only the video pre-alarm information is generated and presented to the operator.

[0041] In this way, corresponding emergency measures can be taken for different pre-alarm situations, which greatly improves the granularity of monitoring and control, maximizes the normal operation of the workplace, and lays the foundation for improving work safety in the workplace.

[0042] In one specific example of the solution disclosed herein, after obtaining scan data, the following manner can be used to determine whether an object exists in the scan data, and the specific process includes:

[0043] A scan image included in the scan data collected by the body collection assembly is input into a first detection model to obtain a first detection result, where the first detection model is used to identify whether at least a part of a local feature of an object exists in the image, and the first detection result indicates whether an object exists in the scan image included in the scan data.

[0044] It should be understood that the scan image included in the scan data may include at least a part of a local feature of a target object, such as a body part of a worker, and then the first detection model is used to identify the scan image to determine whether the at least a part of the local feature of the target object exists, and further determine whether the target object exists in the scan image included in the scan data.

[0045] Furthermore, in one specific example, the first detection result can be obtained by using the following manner: Specifically, inputting the scanning image included in the scanning data collected by the body collection assembly into a first detection model to obtain a first detection result specifically includes: In step 1-1, a scan image included in the scan data collected by the body collection assembly is pre-processed to remove edge regions in the scan image and obtain a sub-image corresponding to a core region in the scan image.

[0046] For example, the edge areas in the scanned image are removed, the areas in the scanned image where the passages are located (i.e., the core areas) are retained, and a sub-image corresponding to the areas of the passages in the scanned image (i.e., the core areas) is further obtained, thus effectively improving the efficiency of the classification process for performing image classification using the subsequent first detection model, and further improving the processing efficiency of the model.

[0047] It should be understood that the above-mentioned pre-processing may further include performing image scaling, normalization of pixel values ​​in the image, etc. on the scanned image included in the scan data. In step 1-2, a sub-image corresponding to a core region in the scanned image is input into a first detection model to obtain a first detection result. Here, the first detection model is used to perform feature extraction on a sub-image corresponding to a core region in the scanned image to obtain a feature map of the core region, and detect whether at least a part of a local feature of the target object is present in the feature map of the core region. Furthermore, in one specific example, the first detection model includes at least a first network layer, a second network layer, and a third network layer.

[0048] Wherein, the first network layer is used to perform feature extraction on the sub-image corresponding to the core region, so as to obtain at least one feature map corresponding to the sub-image, where the number of feature maps in the at least one feature map is negatively correlated with the size of the feature block of the feature map.Furthermore, in one example, in the process of performing feature extraction on the sub-image, the first network layer can reduce the size of the feature block of the extracted feature map, for example to a preset value, thereby increasing the number of feature maps, thus obtaining rich feature information under the premise of ensuring the complexity of the model, and further improving the accuracy of the model identification result. Furthermore, the second network layer is used for predicting whether at least a part of a local feature of the object exists based on at least one feature map corresponding to the sub-image, and obtaining a probability value, for example, a specific value greater than 0 and less than 1. Further, the third network layer processes the probability value obtained by the second network layer to obtain a first value or a second value, the first detection result is the first value or the second value, the first value is used to represent the presence of at least some local features of the target body, and the second value is used to represent the absence of at least some local features of the target body.

[0049] For example, in one example, the first network layer described above may be a deep residual network (ResNet) layer, the second network layer described above may be a multilayer perceptron (MLP) layer, and the third network layer may be a nonlinear activation layer, such as a Sigmoid function layer. As shown in FIG. 2, first, a sub-image corresponding to a core region in a scanned image is input to a ResNet layer in a first detection model to obtain at least one feature map corresponding to the sub-image, then, the at least one feature map corresponding to the sub-image is input to an MLP layer to predict a probability value that at least a part of a local feature of a target object exists in the sub-image, and finally, the predicted probability value is input to a Sigmoid layer to obtain an output result, for example, a first value or a second value. Furthermore, if the output result is the first value, it is considered that at least a part of a local feature of a target object exists in the sub-image, or if the output result is the second value, it is considered that at least a part of a local feature of a target object does not exist in the sub-image.

[0050] In one specific example of the solution of the present disclosure, after obtaining video data, the following manner can be further used to determine whether an object exists in the video data, and the specific process includes: The video data collected by the camera is input to a second detection model to obtain a second detection result, where the second detection model is used to identify whether an object is present in the video data (e.g., whether a full contour of the object is present), and the second detection result indicates whether an object is present in the video data, e.g., whether a full contour of the object is present.

[0051] Here, the time complexity of the second detection model is greater than the time complexity of the first detection model. It should be understood that the second detection model identifies the entire contour of the target object, while the first detection model identifies local features of the target object, therefore, in terms of processing efficiency, the processing efficiency of the first detection model may be superior to the processing efficiency of the second detection model, for example, the time complexity of the first detection model is smaller than the time complexity of the second detection model, thus effectively ensuring different granularity of monitoring and control and effectively improving the overall processing efficiency of the passage monitoring and control method according to the solution of the present disclosure. In one specific example of the solution of the present disclosure, the second detection result can be obtained by using the following manner. Specifically, inputting the video data collected by the camera into the second detection model to obtain the second detection result specifically includes: In step 2-1, the video data collected by the camera is pre-processed to obtain a video image set.

[0052] Wherein, the set of video images includes at least one set of two adjacent frames of video images, and the two adjacent frames of video images meet the requirement that the difference value between the feature maps of the two adjacent frames of video images is greater than a preset difference value, wherein the preset difference value is an empirical value, which can be set according to actual needs, and is not limited thereto in the solution disclosed herein.

[0053] That is, after obtaining the video data, it is necessary to select video images that meet the requirements from the video data. For example, video images with large differences in the feature maps of two adjacent frames are selected to form a video image set, so as to maximize the efficiency of model processing. In step 2-2, each video image in the set of video images is input to a second detection model to obtain a sub-result corresponding to the video image, for example, to obtain a sub-result corresponding to each video image. In step 2-3, if at least one sub-result of all the video images in the set of video images is a third value, the third value is a second detection result, or if all the sub-results of each video image in the set of video images are a fourth value, the fourth value is a second detection result, the third value is used to represent the presence of a target object, and the fourth value is used to represent the absence of a target object.

[0054] That is, if any one of the sub-results is a third value, e.g., a pre-set character such as 1, it indicates that a target object is present in the video data; otherwise, if all the sub-results are a fourth value, e.g., all 0, it indicates that a target object is not present in the video data. Furthermore, in one specific example, the second detection model includes at least a fourth network layer, a fifth network layer, and a sixth network layer.

[0055] Here, the fourth network layer includes at least two dense layers connected in sequence, where the connection feature map obtained by the previous dense layer becomes the initial feature map of the next dense layer. For example, as shown in FIG. 3, the fourth network layer includes two dense layers, where the connection feature map obtained by the first dense layer becomes the initial feature map of the second dense layer. Furthermore, the dense layer in the two dense layers is used to perform a convolution process on the initial feature map to obtain a convolution feature map, and perform a connection process on the initial feature map and the convolution feature map to obtain a connection feature map. Here, the initial feature map of the first dense layer in the at least two dense layers is obtained based on a video image. In this way, the amount of calculation can be effectively reduced, and the size of the feature map can be reduced while effectively ensuring the inference speed and the richness and accuracy of feature extraction. Furthermore, the fifth network layer is used for performing feature aggregation on the connection feature map obtained by the last dense layer in the at least two dense layers to obtain a target feature map.

[0056] Further, the sixth network layer is used for performing prediction on the target feature map to obtain the third value or the fourth value, where the third value is used for representing the presence of the target object, and the fourth value is used for representing the absence of the target object.

[0057] For example, in one example, the fourth network layer described above is a Cross Stage Partial Networks (CSPNet) layer, for example, the CSPNet layer can include two dense layers, and the fifth network layer described above can be a Path Aggregation Network (PANet) layer, and the sixth network layer described above can be a Prediction layer. As shown in FIG. 4, first, a video image in a video image set is input to a CSPNet layer in a second detection model to obtain a connection feature map corresponding to the video image, then the connection feature map is input to a PANet layer to obtain a feature-aggregated target feature map, and finally, the target feature map is input to a prediction layer to obtain an output result, for example, a third value or a fourth value. Furthermore, if the output result is the third value, it is considered that a target object exists in the video data, or if the output result is the fourth value, it is considered that a target object does not exist in the video data.

[0058] In one specific example of the solution of the present disclosure, after obtaining a target path in which a target object is located in the video data, the method specifically includes: The method further includes determining whether an AGV is traveling on the target passage, In addition, the above-mentioned video data is used to generate video pre-warning information of a target passage where a target object is located, specifically, When it is determined that the AGV is traveling, the method includes generating video pre-warning information of a target passage where the object is located in the video data.

[0059] That is, when the presence of an object in the video data is detected and the target passage in which the object is located is determined, it can be further determined whether an AGV is traveling in the target passage. Furthermore, if an AGV is traveling, video pre-warning information of the target passage in which the object is located in the video data is generated, whereas if not, there is no need to generate video pre-warning information.

[0060] Furthermore, in one example, when it is determined that an AGV is traveling on the target passage, the distance between the target and the AGV can be further determined, and when the distance between the target and the AGV is smaller than a preset safe distance, video pre-alarm information of the target passage where the target is located in the video data is generated. Here, the preset safety distance is an empirical value, which can be set according to actual needs, and is not limited in the solution of the present disclosure.

[0061] As described above, the aisle monitoring and control method provided by the solution of the present disclosure has the following advantages over the prior art: First, to improve the processing efficiency and accuracy of target detection: the solution disclosed in the present disclosure uses different detection models for processing different monitoring and control data, thus greatly improving the processing efficiency of detection and the accuracy of identifying targets. Secondly, improve the efficiency of response to pre-alarm: the solution disclosed in the present disclosure can monitor and control data with different monitoring and control granularity, quickly know the safety situation in the passage, and quickly generate pre-alarm information for the passage where the object exists, thus helping workers to take corresponding handling measures in a timely manner. Third, improve workplace safety. The solution disclosed herein can provide technical support for effectively reducing the incidence of safety hazards in the yarn package production workshop, and lay the foundation for reducing damage to AGVs and production equipment, and effectively avoiding injuries to personnel, thus maximally ensuring the normal operation of the workshop and improving the overall safety of the workshop.

[0062] The disclosed solution further provides an aisle monitoring and control device, as shown in FIG. 5, which includes: an acquisition unit 501 for acquiring scanning data collected within a vehicle body surrounding area by a vehicle body collection assembly of an automated guided vehicle AGV and acquiring video data collected within a video collection area by a camera, the AGV being one of a plurality of AGVs, the AGV in the plurality of AGVs traveling along one of a plurality of monitored and controlled paths, the plurality of monitored and controlled paths being a plurality of paths that need to be used to transport wound packages in a wound package production workshop, the vehicle body surrounding area including at least a portion of the monitored and controlled path along which the AGV travels, the camera being one of a plurality of cameras, used for video collection of at least a portion of the monitored and controlled path of the one of the plurality of monitored and controlled paths, the video collection area including at least a portion of the monitored and controlled path that the camera can collect; and a processing unit 502 for, when it is determined that a target object exists based on the scanning data collected by the vehicle body collection assembly and / or the video data collected by the camera, acquiring a target passage in which the target object is located, which is one of the plurality of monitored and controlled passages, and generating target pre-alarm information for the target passage in which the target object is located.

[0063] In one specific example of the solution of the present disclosure, the processing unit specifically includes: According to the scan data collected by the vehicle body collection assembly, when it is determined that a target object exists in the scan data, obtain a target passage in which the target object is located in the scan data, and generate scan pre-alarm information of the target passage in which the target object is located in the scan data; When it is determined that a target object exists in the video data based on the video data collected by the camera, acquiring a target passage in which the target object is located in the video data, and generating video pre-warning information of the target passage in which the target object is located in the video data; acquiring a target passage in which the target is located in the scan data when it is determined based on the scan data collected by the vehicle body collection assembly that a target object exists in the scan data; acquiring a target passage in which the target is located in the video data when it is determined based on the video data collected by the camera that a target object exists in the video data; and generating mixed pre-alarm information for the target passage when it is determined that the target passage in which the target object is located acquired by the scan data is the same as the target passage in which the target object is located acquired by the video data; It is used in one of the following ways.

[0064] In one specific example of the solution of the present disclosure, the mixed pre-alarm information, the scanning pre-alarm information and the video pre-alarm information have decreasing priorities. In one specific example of the solution of the present disclosure, the processing unit comprises: A scanned image included in the scan data collected by the vehicle body collection assembly is input into a first detection model to obtain a first detection result, the first detection model is used to identify whether at least a part of a local feature of a target object is present in the image, and the first detection result is further used to indicate whether a target object is present in the scanned image included in the scan data.

[0065] In one specific example of the solution of the present disclosure, the processing unit is specifically: performing pre-processing on a scan image included in the scan data collected by the body collection assembly to remove edge regions in the scan image and obtain a sub-image corresponding to a core region in the scan image; inputting a sub-image corresponding to a core region in the scanned image into a first detection model to obtain a first detection result; Here, the first detection model is used to perform feature extraction on a sub-image corresponding to a core region in the scanned image to obtain a feature map of the core region, and detect whether at least a part of a local feature of the target object is present in the feature map of the core region.

[0066] In one specific example of the solution of the present disclosure, the first detection model includes at least a first network layer, a second network layer and a third network layer; Wherein, the first network layer is used for performing feature extraction on the sub-image corresponding to the core region, to obtain at least one feature map corresponding to the sub-image, where the number of feature maps in the at least one feature map is negatively correlated with the size of the feature block of the feature map; The second network layer is used for predicting whether a local feature of at least a part of the object exists based on at least one feature map corresponding to the sub-image, and obtaining a probability value; The third network layer processes the probability values ​​to obtain a first value for representing the presence of at least a part of a local feature of the target body, or a second value for representing the absence of at least a part of a local feature of the target body, and the first detection result is used to be the first value or the second value. In one specific example of the solution of the present disclosure, the processing unit comprises: The video data collected by the camera is further used to input into a second detection model to obtain a second detection result, where the second detection model is used to identify whether a target object exists in the video data, and the second detection result indicates whether a target object exists in the video data, and the time complexity of the second detection model is greater than the time complexity of the first detection model.

[0067] In one specific example of the solution of the present disclosure, the processing unit is specifically: Pre-processing the video data collected by the camera to obtain a video image set, the video image set including at least one set of two adjacent frames of video images, the two adjacent frames of video images satisfying a requirement that a difference value between feature maps of the two adjacent frames of video images is greater than a preset difference value; inputting each video image in the set of video images into a second detection model to obtain a sub-result corresponding to the video image; If at least one sub-result of all video images in the video image set is a third value indicating that a target object is present, the third value is used as the second detection result; or, if all sub-results of each video image in the video image set are a fourth value indicating that a target object is not present, the fourth value is used as the second detection result.

[0068] In one specific example of the solution of the present disclosure, the second detection model includes at least a fourth network layer, a fifth network layer, and a sixth network layer; The fourth network layer includes at least two dense layers connected in sequence, in which a connection feature map obtained by a previous dense layer becomes an initial feature map of a next dense layer, and the dense layers in the two dense layers are used for performing a convolution process on the initial feature map to obtain a convolution feature map, and performing a connection process on the initial feature map and the convolution feature map to obtain a connection feature map, and the initial feature map of a first dense layer in the at least two dense layers is obtained based on a video image; the fifth network layer is used for performing feature aggregation on the connection feature map obtained by the last dense layer in the at least two dense layers to obtain a target feature map; The sixth network layer is used to make a prediction on the target feature map to obtain the third value or the fourth value.

[0069] In one specific example of the solution of the present disclosure, the processing unit comprises: After acquiring a target passage in which the target object is located from the video data, it is determined whether an AGV is traveling on the target passage; When it is determined that the AGV is traveling, the video pre-warning information is further used to generate video pre-warning information of a target passage where the object is located in the video data.

[0070] The specific functions and exemplary descriptions of each unit of the apparatus in the embodiments of the present disclosure may refer to the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0071] In the technical solution of the present disclosure, the acquisition, storage, and application of users' personal information comply with the provisions of relevant laws and regulations and do not violate public order and morals.

[0072] FIG. 6 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 6, the electronic device includes a memory 610 and a processor 620, and the memory 610 stores a computer program executable by the processor 620. The number of the memory 610 and the processor 620 may be one or more. The memory 610 may store one or more computer programs, which, when executed by the electronic device, cause the electronic device to perform the method provided by the above method embodiment. The electronic device may further include: The communication interface 630 is used for communicating with an external device and performing data interaction and transmission.

[0073] When the memory 610, the processor 620, and the communication interface 630 are implemented independently, the memory 610, the processor 620, and the communication interface 630 are connected to each other via a bus and can communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be classified into an address bus, a data bus, a control bus, and the like. For ease of explanation, only one thick line is shown in FIG. 6, but it does not represent only one bus or only one type of bus.

[0074] Optionally, in a specific implementation, when the memory 610, the processor 620, and the communication interface 630 are integrated on one chip, the memory 610, the processor 620, and the communication interface 630 can communicate with each other via an internal interface.

[0075] It should be understood that the processor may be a Central Processing Unit (CPU), or may be another general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware assembly, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. In addition, the processor may be a processor supporting the Advanced RISC Machine S (ARM) architecture.

[0076] In addition, optionally, the memory may include read-only memory and random access memory, and may further include non-volatile random access memory. The memory may be either volatile or non-volatile memory, or may include both volatile and non-volatile memory. Here, non-volatile memory may include Read-Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM), or flash memory. Volatile memory may include Random Access Memory (RAM) that acts as an external cache. By way of example and not limitation, many forms of RAM are available. For example, static random access memory (StaticRAM, SRAM), dynamic random access memory (DynamicRandomAcceSSMemory, DRAM), Synchronous DRAM (SynchronouSDRAM, SDRAM), Double Data Rate SDRAM (DoubleDataDateSDRAM, DDRSDRAM), Enhanced SDRAM (EnhancedSDRAM, ESDRAM), SynchlinkDRAM (SynchlinkDRAM, SLDRAM), and DirectRAMBUSRAM (DirectRAMBUSRAM, DRRAM).

[0077] The above-mentioned embodiments may be implemented in whole or in part in software, hardware, firmware, or any combination thereof. When implemented in software, the whole or in part may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, a process or function according to the embodiments of the present disclosure is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, Bluetooth, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device including a server, a data center, etc. integrated with one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a Digital Versatile Disc (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)). Note that the computer-readable storage medium referred to in this disclosure may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0078] Those skilled in the art can understand that all or part of the steps for realizing the above embodiments may be implemented by hardware, or may be implemented by instructing relevant hardware by a program, and the program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk, an optical disk, etc.

[0079] In describing the embodiments of the present disclosure, the reference words "one embodiment", "some embodiments", "example", "particular example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. And, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in any one or more embodiments or examples. Furthermore, a person skilled in the art may combine different embodiments or examples described herein and features of different embodiments or examples to the extent that they are not mutually inconsistent.

[0080] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means "or", for example, A / B can mean either A or B. In this specification, "and / or" is merely for describing the related relationship of related objects, and indicates that three types of relationships may exist, for example, A and / or B can indicate the following three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0081] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying a relative importance, nor should they be construed as implying a number of technical features shown. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, "plurality" means two or more, unless otherwise specified.

[0082] The above are merely illustrative examples of the present disclosure, and are not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present disclosure should be included within the scope of protection of the present disclosure.

Claims

1. Obtaining scanning data collected within a vehicle body surrounding area by a vehicle body collection assembly of an automated guided vehicle AGV, the AGV being one of a plurality of AGVs, an AGV in the plurality of AGVs traveling along one of a plurality of monitored and controlled paths, the plurality of monitored and controlled paths being paths that need to be used to transport wound yarn packages in a wound yarn package production work area, the vehicle body surrounding area including at least a portion of the monitored and controlled path along which the AGV travels; Obtaining video data collected by a camera within a video collection area, the camera being one of a plurality of cameras and used to collect video of at least a portion of a surveillance-controlled passageway among the plurality of surveillance-controlled passageways, the video collection area including at least a portion of the surveillance-controlled passageway that can be collected by the camera; When determining that a target object exists based on the scanning data collected by the vehicle body collection assembly and / or the video data collected by the camera, obtain a target passageway in which the target object is located, and the target passageway is one of the plurality of monitored and controlled passageways; generating target pre-alarm information for a target passage in which the target object is located; Aisle monitoring and control method.

2. When it is determined that a target object exists based on the scanning data collected by the vehicle body collection assembly and / or the video data collected by the camera, obtaining a target passage in which the target object is located, and generating target pre-alarm information of the target passage in which the target object is located, According to the scanning data collected by the vehicle body collection assembly, when it is determined that a target object exists in the scanning data, a target passage in which the target object is located in the scanning data is obtained, and scanning pre-alarm information of the target passage in which the target object is located in the scanning data is generated; When it is determined that a target object exists in the video data based on the video data collected by the camera, a target passage in which the target object is located is obtained in the video data, and video pre-warning information of the target passage in which the target object is located in the video data is generated; acquiring a target passage in which the target is located in the scan data when it is determined based on the scan data collected by the vehicle body collection assembly that a target object exists in the scan data; acquiring a target passage in which the target is located in the video data when it is determined based on the video data collected by the camera that a target object exists in the video data; and generating mixed pre-alarm information for the target passage when it is determined that the target passage in which the target object is located acquired by the scan data is the same as the target passage in which the target object is located acquired by the video data; Including any one of the following:

2. The passage monitoring control method according to claim 1.

3. The mixed pre-alarm information, the scanning pre-alarm information and the video pre-alarm information have decreasing priorities.

3. The passage monitoring control method according to claim 2.

4. The passage monitoring and control method includes: inputting a scan image included in the scan data collected by the vehicle body collection assembly into a first detection model to obtain a first detection result, the first detection model being used to identify whether or not a local feature of at least a portion of an object is present in the image, and the first detection result indicating whether or not an object is present in the scan image included in the scan data.

3. The passage monitoring control method according to claim 2.

5. inputting a scan image included in the scan data collected by the body collection assembly into a first detection model to obtain a first detection result, performing pre-processing on a scan image included in the scan data collected by the body collection assembly to remove edge regions in the scan image and obtain a sub-image corresponding to a core region in the scan image; inputting a sub-image corresponding to a core region in the scanned image into a first detection model to obtain a first detection result; Wherein, the first detection model is used for performing feature extraction on a sub-image corresponding to a core region in the scanned image to obtain a feature map of the core region, and detecting whether at least a part of a local feature of the target object exists in the feature map of the core region.

5. The passage monitoring control method according to claim 4.

6. the first detection model includes at least a first network layer, a second network layer, and a third network layer; The first network layer is used for performing feature extraction on the sub-image corresponding to the core region to obtain at least one feature map corresponding to the sub-image, where a number of feature blocks in the at least one feature map is negatively correlated with a size of a feature block of the feature map; The second network layer is used for predicting whether a local feature of at least a part of the object exists based on at least one feature map corresponding to the sub-image, and obtaining a probability value; The third network layer processes the probability value to obtain a first value for representing the presence of at least a part of the local feature of the target object, or a second value for representing the absence of at least a part of the local feature of the target object, and the first detection result is used to be the first value or the second value.

6. The passage monitoring control method according to claim 5.

7. The passage monitoring and control method includes: inputting the video data collected by the camera into a second detection model to obtain a second detection result, where the second detection model is used to identify whether an object exists in the video data, and the second detection result indicates whether an object exists in the video data, and a time complexity of the second detection model is greater than a time complexity of the first detection model; 5. The passage monitoring control method according to claim 4.

8. inputting the video data collected by the camera into a second detection model to obtain a second detection result, Pre-processing the video data collected by the camera to obtain a video image set, the video image set including at least one set of two adjacent frames of video images, the two adjacent frames of video images satisfying a requirement that a difference value between feature maps of the two adjacent frames of video images is greater than a preset difference value; inputting each video image in the set of video images into a second detection model to obtain a sub-result corresponding to the video image; and if at least one sub-result of all the video images of the set of video images is a third value representing the presence of a target object, the third value is a second detection result; or if all the sub-results of each video image of the set of video images are a fourth value representing the absence of a target object, the fourth value is a second detection result.

8. The passage monitoring control method according to claim 7.

9. the second detection model includes at least a fourth network layer, a fifth network layer, and a sixth network layer; The fourth network layer includes at least two dense layers connected in sequence, in which a connection feature map obtained by a previous dense layer becomes an initial feature map of a next dense layer, and the dense layers in the two dense layers are used for performing a convolution process on the initial feature map to obtain a convolution feature map, and performing a connection process on the initial feature map and the convolution feature map to obtain a connection feature map, and the initial feature map of a first dense layer in the at least two dense layers is obtained based on a video image; the fifth network layer is used for performing feature aggregation on the connection feature map obtained by the last dense layer in the at least two dense layers to obtain a target feature map; The sixth network layer is used to perform prediction on the target feature map to obtain the third value or the fourth value.

9. The passage monitoring control method according to claim 8.

10. The passage monitoring and control method includes: acquiring a target passage in which a target object is located from video data; The method further includes determining whether an AGV is traveling on the target passage, Wherein, generating video pre-warning information of a target passage where a target object is located in the video data includes: generating video pre-warning information of a target passage in which a target object is located in the video data when it is determined that the AGV is traveling; 3. The passage monitoring control method according to claim 2.

11. an acquisition unit for acquiring scanning data collected within a vehicle body surrounding area by a vehicle body collection assembly of an automated guided vehicle AGV and acquiring video data collected within a video collection area by a camera, the AGV being one of a plurality of AGVs, an AGV in the plurality of AGVs traveling along any one of a plurality of monitored and controlled paths, the plurality of monitored and controlled paths being a plurality of paths that need to be used to transport wound yarn packages in a wound yarn package production workshop, the vehicle body surrounding area including at least a portion of the monitored and controlled path along which the AGV travels, the camera being one of a plurality of cameras, and being used to perform video collection for at least a portion of the any one of the plurality of monitored and controlled paths, the video collection area including at least a portion of the monitored and controlled path that can be collected by the camera; and a processing unit for, when determining that a target object exists based on the scanning data collected by the vehicle body collection assembly and / or the video data collected by the camera, acquiring a target path in which the target object is located, which is one of the plurality of monitored and controlled paths, and generating target pre-warning information for the target path in which the target object is located. Aisle monitoring control device.

12. The processing unit specifically includes: According to the scanning data collected by the vehicle body collection assembly, when it is determined that a target object exists in the scanning data, a target passage in which the target object is located in the scanning data is obtained, and scanning pre-alarm information of the target passage in which the target object is located in the scanning data is generated; When it is determined that a target object exists in the video data based on the video data collected by the camera, a target passage in which the target object is located is obtained in the video data, and video pre-warning information of the target passage in which the target object is located in the video data is generated; acquiring a target passage in which the target is located in the scan data when it is determined based on the scan data collected by the vehicle body collection assembly that a target object exists in the scan data; acquiring a target passage in which the target is located in the video data when it is determined based on the video data collected by the camera that a target object exists in the video data; and generating mixed pre-alarm information for the target passage when it is determined that the target passage in which the target object is located acquired by the scan data is the same as the target passage in which the target object is located acquired by the video data; Used in one of the following:

12. The passage monitoring and control system according to claim 11.

13. The mixed pre-alarm information, the scanning pre-alarm information and the video pre-alarm information have decreasing priorities.

13. The passage monitoring and control system of claim 12.

14. The processing unit includes: inputting a scan image included in the scan data collected by the vehicle body collection assembly into a first detection model to obtain a first detection result, the first detection model being used to identify whether at least a part of a local feature of an object exists in the image, and the first detection result being used to indicate whether an object exists in the scan image included in the scan data; 13. The passage monitoring and control system of claim 12.

15. The processing unit specifically includes: performing pre-processing on a scan image included in the scan data collected by the body collection assembly to remove edge regions in the scan image and obtain a sub-image corresponding to a core region in the scan image; inputting a sub-image corresponding to a core region in the scanned image into a first detection model to obtain a first detection result; Wherein, the first detection model is used for performing feature extraction on a sub-image corresponding to a core region in the scanned image to obtain a feature map of the core region, and detecting whether at least a part of a local feature of the target object exists in the feature map of the core region.

15. The passage monitoring and control system of claim 14.

16. the first detection model includes at least a first network layer, a second network layer, and a third network layer; The first network layer is used for performing feature extraction on the sub-image corresponding to the core region to obtain at least one feature map corresponding to the sub-image, where a number of feature blocks in the at least one feature map is negatively correlated with a size of a feature block of the feature map; The second network layer is used for predicting whether a local feature of at least a part of the object exists based on at least one feature map corresponding to the sub-image, and obtaining a probability value; The third network layer processes the probability value to obtain a first value for representing the presence of at least a part of the local feature of the target object, or a second value for representing the absence of at least a part of the local feature of the target object, and the first detection result is used to be the first value or the second value.

16. The passage monitoring and control system according to claim 15.

17. The processing unit includes: The video data collected by the camera is further inputted into a second detection model to obtain a second detection result, where the second detection model is used to identify whether an object exists in the video data, and the second detection result indicates whether an object exists in the video data, and a time complexity of the second detection model is greater than a time complexity of the first detection model.

15. The passage monitoring and control system of claim 14.

18. The processing unit specifically includes: Pre-processing the video data collected by the camera to obtain a video image set, the video image set including at least one set of two adjacent frames of video images, the two adjacent frames of video images satisfying a requirement that a difference value between feature maps of the two adjacent frames of video images is greater than a preset difference value; inputting each video image in the set of video images into a second detection model to obtain a sub-result corresponding to the video image; if at least one sub-result of all the video images of the set of video images is a third value for indicating that a target object is present, the third value is used as a second detection result; or if all the sub-results of each video image of the set of video images are a fourth value for indicating that a target object is not present, the fourth value is used as a second detection result.

18. The path monitoring and control system of claim 17.

19. the second detection model includes at least a fourth network layer, a fifth network layer, and a sixth network layer; The fourth network layer includes at least two dense layers connected in sequence, in which a connection feature map obtained by a previous dense layer becomes an initial feature map of a next dense layer, and the dense layers in the two dense layers are used for performing a convolution process on the initial feature map to obtain a convolution feature map, and performing a connection process on the initial feature map and the convolution feature map to obtain a connection feature map, and the initial feature map of a first dense layer in the at least two dense layers is obtained based on a video image; the fifth network layer is used for performing feature aggregation on the connection feature map obtained by the last dense layer in the at least two dense layers to obtain a target feature map; The sixth network layer is used to perform prediction on the target feature map to obtain the third value or the fourth value.

20. The path monitoring and control system of claim 18.

20. The processing unit includes: After acquiring a target passage in which a target object is located from the video data, determining whether an AGV is traveling on the target passage; When it is determined that the AGV is traveling, generating video pre-warning information of a target passage where the target object is located in the video data; The passage monitoring and control device according to any one of claims 12 to 16.

21. At least one processor; a memory in communication with the at least one processor; 11. An electronic device, comprising: a processor configured to process a plurality of processors each of which includes a processor and a processor configured to process the plurality of processors; a processor configured to process the plurality of processors;

22. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to carry out the aisle monitoring control method according to any one of claims 1 to 10.

23. A program for implementing the passage monitoring control method according to any one of claims 1 to 10, when executed by a processor.

Images