Highway monitoring device based on multi-source data fusion

Abstract

The invention relates to the technical field of intelligent monitoring, in particular to a road monitoring device based on multi-source data fusion, which comprises a distributed fiber bragg grating sensing module for collecting various data of each monitoring area of a roadbed and a road surface; the optical signal processing module is used for analyzing the data acquired by the distributed fiber grating sensing module and judging whether the data exceed respective threshold values or not; the imaging radar and the low-illumination camera are used for acquiring radar point cloud images and visible light images of a road and a slope area; the image processing module is used for fusing the radar point cloud image and the visible light image of the same monitoring area and identifying whether rockfall, fracture or collapse conditions exist in each monitoring area on the road or not; and the alarm module is used for sending out a corresponding alarm signal when any one of the data acquired by the distributed fiber grating sensing module exceeds a threshold value or rockfall, fracture or collapse conditions exist in a certain monitoring area. According to the invention, the monitoring precision of road abnormal conditions can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and more specifically to a highway monitoring device based on multi-source data fusion. Background Art

[0002] With the rapid development of economy and the continuous progress of science and technology, the scale of transportation has been continuously expanded, and the highway network has been gradually expanded. As the terrain through which highways pass is complex and changeable, and they mostly pass through river valleys and mountains, under natural conditions, they are often affected by factors such as the rock properties, geological structure, topographic appearance, high temperature, freeze-thaw, hydrology and rainfall of the slopes, which often cause slope instability and cause collapse, landslide and other accidents, which are directly related to the operation safety of highway traffic. Some cities are affected by the marine monsoon climate, with humid and hot climate, abundant rainfall, and complex and diverse terrain. In addition, they are affected by many factors such as road design level, vehicle overload, traffic channelization and construction quality control, especially frequent typhoons and heavy rains, which are more likely to cause geological disasters such as landslides and collapses, posing a serious threat to the safe operation of highways. In addition, the expansion of cities and the increase in underground projects have increased the development and utilization of underground space, and the demand for highway collapse and fracture monitoring has also increased accordingly. Especially in large cities, the complexity and risk of underground space make collapse and fracture monitoring particularly important. Landslides and slope instability accidents on highways not only affect traffic order, cause vehicle damage and casualties, but also bring huge economic losses and negative social impacts. Therefore, timely discovery and early warning of landslides and fractures are of great significance for ensuring highway safety, reducing accidents, improving rescue efficiency, and optimizing road maintenance and management.

[0003] In highway safety monitoring, two-dimensional lidar is mostly used. However, since two-dimensional lidar is obviously affected by bad weather conditions and often has problems of false alarms and missed alarms in actual use such as rockfall monitoring, it has gradually been replaced by three-dimensional lidar products.

[0004] Although 3D LiDAR can effectively reduce system false alarms and missed alarms, and improve environmental adaptability to a certain extent, the devices used to monitor roads and slopes have the following defects: (1) Monitoring relies solely on LiDAR, which may not be able to capture detailed information such as images, and may easily miss phenomena such as falling rocks on slopes. It is not as sensitive as visual sensors such as cameras when monitoring road cracks. (2) Monitoring only alarms for detected abnormal events, and there is no disaster warning system.

[0005] Therefore, how to improve the monitoring accuracy of abnormal phenomena such as falling rocks, collapses, and fractures on highways, reduce false alarms and missed alarms, predict disasters earlier, and reduce accident risks is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0006] In view of this, the present invention provides a highway monitoring device based on multi-source data fusion, which can improve the monitoring accuracy of abnormal highway conditions.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A highway monitoring device based on multi-source data fusion, comprising: a distributed fiber grating sensor module, an optical signal processing module, an imaging radar, a low-light camera, an image processing module and an alarm module;

[0009] The distributed fiber Bragg grating sensing module is used to collect strain, displacement and temperature data of each monitoring area of ​​the roadbed and road surface;

[0010] The optical signal processing module is used to analyze various data collected by the distributed fiber grating sensing module to determine whether various data exceed respective thresholds;

[0011] The imaging radar and the low-light camera are installed on the same pole on the side of the road to obtain radar point cloud images and visible light images of the road and slope areas;

[0012] The image processing module is used to fuse the radar point cloud image and the visible light image of the same monitoring area to identify whether there are rockfalls, fractures or collapses in each monitoring area on the highway;

[0013] The alarm module is used to send out a corresponding alarm signal when any one of the data collected by the distributed fiber grating sensor module exceeds a threshold value, or when there is rockfall, fracture or collapse in a certain monitoring area.

[0014] Furthermore, the distributed fiber Bragg grating sensing module includes a fiber Bragg grating sensor and a multi-core transmission optical cable;

[0015] The fiber grating sensors are buried in multiple monitoring areas of the highway, form a distributed monitoring network through a time division multiplexing method, and are uniformly connected to the optical signal processing module through the multi-core transmission optical cable.

[0016] Furthermore, the optical signal processing module sets strain, displacement and temperature thresholds in advance according to historical data or empirical values ​​of road fractures and collapses, and demodulates the optical signal collected by the fiber grating sensor in real time to calculate the strain, displacement and temperature data of each monitoring area.

[0017] Furthermore, when the image processing module identifies that there is rockfall, fracture or collapse in a certain monitoring area, it automatically associates with the low-light camera to capture the monitoring area and captures the video of a preset time before the alarm.

[0018] Furthermore, it also includes a cloud control center;

[0019] The optical signal processing module is used to upload the strain, displacement and temperature data of each monitoring area to the cloud control center;

[0020] The image processing module is used to upload the radar point cloud image, visible light image and fusion detection result of each monitoring area to the cloud control center;

[0021] The alarm module is used to report the alarm signal of each monitoring area to the cloud control center;

[0022] The cloud control center is used to provide real-time monitoring data display, historical monitoring data query, real-time alarm data display and historical warning data query functions.

[0023] Furthermore, the cloud control center is also associated with map software for marking the monitoring area where the alarm signal occurs on the map.

[0024] Further, the image processing module includes: a target detection unit, a spatiotemporal synchronization unit and an analysis unit;

[0025] The target detection unit is used to input the radar point cloud image and the visible light image frame into the deep learning network respectively, and obtain the radar point cloud target detection frame and the visible light target detection frame respectively;

[0026] The spatiotemporal synchronization unit is used to select the visible light image frame closest to the time based on the time of the radar point cloud image, use the radar point cloud image and the visible light image frame at the time as the image pair to be fused, and project the radar point cloud target detection frame in the image pair to be fused into the visible light image, so that the radar point cloud target detection frame and the visible light target detection frame are displayed on the same frame of the image;

[0027] The analysis unit is used to associate and match the radar point cloud target detection frame and the visible light target detection frame through the IoU algorithm. When the overlapping area is greater than or equal to a preset threshold, the match is successful and the distance information and category information of the detected target are output; when the overlapping area is less than the preset threshold, the visible light target detection frame is used as the basis and the category information of the detected target is output.

[0028] Furthermore, the alarm module uses time-division and area-division methods to alarm abnormal phenomena in each monitoring area;

[0029] Among them, the time-division method is to adjust the alarm threshold according to different time periods and different weather conditions;

[0030] The regional approach is to adjust the alarm threshold for high-risk areas, ordinary areas and construction areas.

[0031] Furthermore, the alarm module also sends out a warning signal or an alarm signal in combination with the analysis result of the optical signal processing module and the analysis result of the image processing module;

[0032] When the strain, temperature or displacement data of the roadbed and pavement reaches the threshold, but no pavement collapse, fracture or rockfall occurs, an early warning signal is issued;

[0033] When road collapse, fracture or rockfall occurs, an alarm signal is issued.

[0034] It can be seen from the above technical solution that compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. The present invention integrates three types of data, namely, fiber grating sensor system, laser radar and low-light camera, to conduct all-weather, fully automatic and highly efficient intelligent monitoring of abnormal phenomena on roads and slopes. It can timely detect abnormal events such as falling rocks, fractures and collapses in the road and slope environment, track their trajectories and provide alarms, thereby improving monitoring efficiency and enhancing the guarantee for safe operation of highway traffic. Among them, fiber optic monitoring can achieve a test accuracy of several microstrains, can predict risks earlier, provide highway disaster warnings, and help reduce accident risks, reduce losses and improve public safety.

[0036] 2. The present invention combines the low-light camera with the three-dimensional laser radar, and integrates the detection results of the two. It can also monitor normally in weak light environments at night and under the influence of bad weather, and is suitable for most outdoor environments. The low-light camera can improve the recognition ability of small-volume falling rocks, fine cracks on the road surface, etc., reduce the false alarm rate, and provide stable and clear images in low light or even completely dark environments, with good imaging effects at night. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0038] Figure 1 A schematic diagram of the structure of a highway monitoring device based on multi-source data fusion provided by the present invention;

[0039] Figure 2 A schematic diagram of the structure of a distributed fiber Bragg grating sensing module provided by the present invention;

[0040] Figure 3 This is a structural schematic diagram of the image processing module provided by the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] like Figure 1 As shown, the embodiment of the present invention discloses a highway monitoring device based on multi-source data fusion, including: a distributed fiber grating sensor module, an optical signal processing module, an imaging radar, a low-light camera, an image processing module and an alarm module;

[0043] Distributed fiber Bragg grating sensing modules are used to collect strain, displacement and temperature data of each monitoring area of ​​the roadbed and pavement;

[0044] The optical signal processing module is used to analyze the data collected by the distributed fiber grating sensor module to determine whether the data exceeds the respective threshold value;

[0045] The imaging radar and low-light camera are installed on the side of the road on the same pole to obtain radar point cloud images and visible light images of the road and slope areas;

[0046] The image processing module is used to fuse the radar point cloud image and visible light image of the same monitoring area to identify whether there are rockfalls, fractures or collapses in each monitoring area on the highway;

[0047] The alarm module is used to send out a corresponding alarm signal when any of the data collected by the distributed fiber grating sensor module exceeds a threshold, or when there is rockfall, fracture or collapse in a certain monitoring area.

[0048] The above modules are further explained below.

[0049] like Figure 2 As shown, the distributed fiber Bragg grating sensing module includes a fiber Bragg grating sensor and a multi-core transmission optical cable;

[0050] Fiber Bragg grating sensors include strain fiber Bragg grating sensors, temperature fiber Bragg grating sensors and displacement fiber Bragg grating sensors. Each sensor is buried in multiple monitoring areas of the highway, forming a distributed monitoring network through time division multiplexing method, and is uniformly connected to the optical signal processing module through multi-core transmission optical cables.

[0051] The optical signal processing module sets the thresholds of strain, displacement and temperature in advance according to the historical data or empirical values ​​of highway fractures and collapses, and demodulates the optical signals collected by the fiber grating sensor in real time, calculates the strain, displacement and temperature data of each monitoring area, realizes the centralized collection and monitoring of all optical path signals, and conducts networked monitoring and control of each monitoring area of ​​the highway.

[0052] The imaging radar and the low-light camera are installed on the same pole on the side of the highway slope to scan and image the highway and slope areas. The imaging radar collects highway environment information in real time by performing three-dimensional scanning of abnormal road surface areas, so as to analyze and identify information such as the type of road surface abnormality in real time.

[0053] Low-light cameras can monitor roads around the clock and provide stable and clear images even in dim light at night and in severe weather. They are suitable for most outdoor environments. Fusion of radar images can improve the ability to identify small-volume fallen rocks, subtle cracks in the road surface, and reduce false alarm rates.

[0054] The present invention uses imaging radar and low-light camera to perform multi-dimensional perception of different monitoring areas of the road surface, obtains radar point cloud images and visible light images taken by low-light camera, and the image processing module fuses the radar point cloud image and visible light image of the same monitoring area, and finally outputs the target category, image and distance information, so as to realize automatic real-time monitoring of obstacles such as fallen rocks, road breaks, collapse and other disaster phenomena in the monitoring area.

[0055] When rockfall, fracture or collapse is detected in a certain monitoring area, the low-light camera is automatically associated to take a snapshot of the monitoring area and capture a video of a preset length of time (one minute) before the alarm is triggered, so as to intuitively understand the trajectory of the rockfall and the process of the abnormal phenomenon.

[0056] The image processing module adopts the method of fusing the detection results of camera and lidar from the result level. The camera and lidar obtain the detection frames of the target in the image data and radar point cloud data respectively through the deep learning network, and then synchronize time and space, project the three-dimensional detection frame of the radar image onto the image, and use the intersection and union ratio to screen different detection frames in the same frame of the picture, and finally output the fusion result.

[0057] Specifically, if Figure 3 As shown, the image processing module includes: a target detection unit, a spatiotemporal synchronization unit and an analysis unit;

[0058] The target detection unit is used to input the radar point cloud image and the visible light image frame into the deep learning network respectively, and obtain the radar point cloud target detection frame and the visible light target detection frame respectively;

[0059] The spatiotemporal synchronization unit is used to select the visible light image frame closest to the time based on the time of the radar point cloud image, and use the radar point cloud image and the visible light image frame at the time as the image pair to be fused, and project the radar point cloud target detection frame in the image pair to be fused into the visible light image, so that the radar point cloud target detection frame and the visible light target detection frame are displayed on the same frame of the image;

[0060] The analysis unit is used to associate and match the radar point cloud target detection frame and the visible light target detection frame through the IoU algorithm. When the overlapping area is greater than or equal to the preset threshold (for example, 0.5), the match is successful, and the distance information and category information of the detected target are output, where the distance information is detected by the radar, and the category information is mainly obtained by analyzing the visible light image collected by the camera; when the overlapping area is less than the preset threshold (for example, 0.5), the visible light target detection frame is used as the basis, and only the category information of the detected target is output.

[0061] When using deep learning networks to detect targets in visible light images and radar point cloud data, the set confidence probability threshold will filter out some targets with low confidence. However, in actual experiments, some identified targets will be filtered out due to the set confidence threshold, so the sigmoid function is used to correct the confidence of the detected targets.

[0062] In order to better determine the location of rockfall, collapse or fracture, the low-light camera and radar are calibrated for external parameters to determine the relative position of the lidar and the camera. Specifically, the camera-lidar parameter calibration is a prerequisite for three-dimensional target fusion detection. The present invention uses a calibration method based on primary and auxiliary calibration objects and projection consistency optimization to obtain the external parameters of the camera-lidar system: the first step is to extract the same-name corner points from the primary and auxiliary calibration objects to obtain 3D-3D and 3D-2D same-name point constraints. The second step is to obtain the calibration result based on the same-name corner point constraints using the external parameter optimization method based on projection consistency.

[0063] The present invention fuses radar point cloud images and visible light images, which complement each other to achieve multi-dimensional perception, accurate target recognition, positioning, and trajectory tracking. It can actively locate the real-time three-dimensional spatial coordinates and GPS coordinates and movement trajectory of falling rocks, road breaks or collapses, thereby improving the accuracy and reliability of environmental perception. This is specifically reflected in the following aspects:

[0064] (1) Spatial distance: Radar can accurately measure the distance to an object and generate a high-resolution three-dimensional point cloud map, providing detailed information about the object's position in space.

[0065] (2) Color and texture: The camera can capture information such as the color, texture, and lighting changes of an object, which is very important for object recognition and classification.

[0066] (3) Three-dimensional shape: The three-dimensional point cloud data provided by the radar can be used to model the shape and spatial structure of an object, while the camera provides surface details and texture information of the object. This combination helps to more accurately identify the type and state of the object.

[0067] (4) Ambient lighting and reflection: LiDAR is insensitive to changes in lighting conditions and can therefore operate stably under a variety of lighting conditions. Cameras, on the other hand, are very sensitive to lighting conditions and can capture visual details of the environment. Combining the two enables more comprehensive perception under different lighting conditions.

[0068] (5) Dynamic information: Cameras can capture dynamic information of moving objects, while lidar can provide spatial position information of these objects. After fusion, the movement of objects can be tracked and predicted more accurately.

[0069] The alarm module uses time periods, regions and modules to alarm abnormal phenomena in each monitoring area;

[0070] Among them, (1) time division refers to adjusting the alarm threshold according to different time periods or weather conditions to meet the actual needs of highway monitoring.

[0071] Daytime and nighttime: During the daytime when lighting conditions are good, you can set a higher alarm sensitivity, such as lowering the threshold, to monitor rockfalls, fractures, collapses, etc. in real time; at night, you may need to adjust the alarm threshold to adapt to lower lighting conditions and the possible increased risk of false alarms.

[0072] High-risk periods: In severe weather conditions such as heavy rain and heavy snow, the risk of road collapse or rockfall may increase. Lower alarm thresholds can be set during these periods to enhance the ability to detect and respond to abnormal situations.

[0073] (2) Regional division means setting different alarm thresholds according to different areas of the highway.

[0074] High-risk areas: Areas such as hillsides or cliff edges that are prone to natural disasters such as rockfalls and landslides, and areas known to have historical problems, can set lower alarm thresholds to quickly detect anomalies and take measures.

[0075] Ordinary areas: The alarm thresholds for ordinary areas such as flat roads can be relatively loose, and the focus is mainly on abnormal changes.

[0076] Construction areas: In areas where highways are under construction or undergoing reconstruction, additional risks may arise and alarm settings may need to be specially adjusted to address potential rockfall or collapse risks caused by construction.

[0077] (3) Module division refers to setting alarm rules based on the detection results of different functional modules (optical signal processing module and image processing module).

[0078] If the micro-strain of the road surface or roadbed reaches a threshold but no road collapse, fracture or rockfall occurs, an early warning signal will be issued.

[0079] If the road has collapsed, broken or fallen, an alarm signal will be issued regardless of whether the fiber grating data exceeds the threshold. In addition, based on whether the two functional modules sense the abnormality at the same time, the alarm priority is set and an alarm signal of the corresponding level is issued.

[0080] In one embodiment, the highway monitoring device of the present invention transmits monitoring data via 5G wireless, and there is no need to access a wired network on site. In addition, the device has low power consumption and can also be powered by solar energy, which greatly facilitates the construction and installation of the equipment and improves the flexibility and adaptability of the system.

[0081] The image processing module can also identify abnormal phenomena based on sample images of falling rocks, road collapse or fractures. The image processing unit determines the position and contour shape of the road from sample images of the road and slopes, and further judges the abnormal phenomena on this basis, thereby preventing the road contour and slope from interfering with the identification process.

[0082] In other embodiments, a cloud control center is also included;

[0083] The optical signal processing module is used to upload the strain, displacement and temperature data of each monitoring area to the cloud control center;

[0084] The image processing module is used to upload the radar point cloud images, visible light images and fusion detection results of each monitoring area to the cloud control center;

[0085] The alarm module is used to report the alarm signals of each monitoring area to the cloud control center;

[0086] The cloud control center is used to provide real-time monitoring data display, historical monitoring data query, real-time alarm data display and historical warning data query functions, forming a one-stop management interface for the highway.

[0087] The cloud control center is also associated with map software, which is used to mark the monitoring areas where alarm signals occur on the map.

[0088] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0089] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A highway monitoring device based on multi-source data fusion, characterized in that: include: Distributed fiber grating sensing module, optical signal processing module, imaging radar, low-light camera, image processing module and alarm module; The distributed fiber Bragg grating sensing module is used to collect strain, displacement and temperature data of each monitoring area of ​​the roadbed and road surface; The optical signal processing module is used to analyze various data collected by the distributed fiber grating sensing module to determine whether various data exceed respective thresholds; The imaging radar and the low-light camera are installed on the same pole on the side of the road to obtain radar point cloud images and visible light images of the road and slope areas; The image processing module is used to fuse the radar point cloud image and the visible light image of the same monitoring area to identify whether there are rockfalls, fractures or collapses in each monitoring area on the highway; The alarm module is used to send out a corresponding alarm signal when any one of the data collected by the distributed fiber grating sensor module exceeds a threshold value, or when there is rockfall, fracture or collapse in a certain monitoring area.

2. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: The distributed fiber grating sensing module includes a fiber grating sensor and a multi-core transmission optical cable; The fiber grating sensors are buried in multiple monitoring areas of the highway, form a distributed monitoring network through a time division multiplexing method, and are uniformly connected to the optical signal processing module through the multi-core transmission optical cable.

3. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: The optical signal processing module sets strain, displacement and temperature thresholds in advance according to historical data or empirical values ​​of road fractures and collapses, and demodulates the optical signals collected by the fiber grating sensor in real time to calculate the strain, displacement and temperature data of each monitoring area.

4. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: When the image processing module identifies that there is rockfall, fracture or collapse in a certain monitoring area, it automatically associates with the low-light camera to capture the monitoring area and captures the video of a preset time before the alarm.

5. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: It also includes a cloud control center; The optical signal processing module is used to upload the strain, displacement and temperature data of each monitoring area to the cloud control center; The image processing module is used to upload the radar point cloud image, visible light image and fusion detection result of each monitoring area to the cloud control center; The alarm module is used to report the alarm signal of each monitoring area to the cloud control center; The cloud control center is used to provide real-time monitoring data display, historical monitoring data query, real-time alarm data display and historical warning data query functions.

6. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: The cloud control center is also associated with map software for marking the monitoring area where the alarm signal occurs on the map.

7. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: The image processing module includes: a target detection unit, a time-space synchronization unit and an analysis unit; The target detection unit is used to input the radar point cloud image and the visible light image frame into the deep learning network respectively, and obtain the radar point cloud target detection frame and the visible light target detection frame respectively; The spatiotemporal synchronization unit is used to select the visible light image frame closest to the time based on the time of the radar point cloud image, use the radar point cloud image and the visible light image frame at the time as the image pair to be fused, and project the radar point cloud target detection frame in the image pair to be fused into the visible light image, so that the radar point cloud target detection frame and the visible light target detection frame are displayed on the same frame of the image; The analysis unit is used to associate and match the radar point cloud target detection frame and the visible light target detection frame through the IoU algorithm. When the overlapping area is greater than or equal to a preset threshold, the match is successful and the distance information and category information of the detected target are output; when the overlapping area is less than the preset threshold, the visible light target detection frame is used as the basis and the category information of the detected target is output.

8. The highway monitoring device based on multi-source data fusion according to claim 1 is characterized in that: The alarm module uses time-division and area-division methods to alarm abnormal phenomena in each monitoring area; Among them, the time-division method is to adjust the alarm threshold according to different time periods and different weather conditions; The regional approach is to adjust the alarm threshold for high-risk areas, ordinary areas and construction areas.

9. The highway monitoring device based on multi-source data fusion according to claim 8 is characterized in that: The alarm module also sends out a warning signal or an alarm signal in combination with the analysis result of the optical signal processing module and the analysis result of the image processing module; When the strain, temperature or displacement data of the roadbed and pavement reaches the threshold, but no pavement collapse, fracture or rockfall occurs, an early warning signal is issued; When road collapse, fracture or rockfall occurs, an alarm signal is issued.

Images