Automatic decontamination method and system for dust removal equipment based on machine vision

Abstract

The invention discloses a method and a system for automatically cleaning dust removal equipment based on machine vision, and relates to the technical field of automatic cleaning. The method comprises the steps that all pollution sources in a to-be-cleaned area are obtained, and pollution point locations are marked; a three-dimensional coordinate system with the dust removal equipment as the center is established, the pollution point positions are converted into the coordinate system of the dust removal equipment in the to-be-cleaned area, and stain coordinates are obtained; marking cleaning coordinates corresponding to the stain coordinates according to the operation range of the dust removal equipment; the method comprises the following steps: acquiring an image shot by a camera of the dust removal equipment, extracting stain coordinates in the image, and if it is obtained through image analysis that pollutants exist at the stain coordinates, driving the corresponding dust removal equipment to reach the cleaning coordinates corresponding to the stain coordinates, and executing dust removal operation. According to the control method, fixed-point cleaning of the dust removal equipment is achieved, the labor cost is reduced, and the cleaning efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of automated cleaning technology, and in particular to an automated cleaning method and system for dust removal equipment based on machine vision. Background Art

[0002] Dust removal equipment refers to a directional fog cannon that can move in multiple directions and spray different types of cleaning sprays for different pollution sources. This type of spray-type dust removal equipment consumes only 20% to 30% of the liquid of traditional water and liquid spraying equipment, but the coverage area and cleaning area are 30 times higher.

[0003] Currently, this type of dust removal equipment is mainly controlled manually, and the spraying direction needs to be manually controlled so that the liquid column is aimed at and covers the pollution source, and the task is completed after continuous spraying for a period of time. Another more automated way is to use the circulating spraying function of the dust removal equipment to continuously spray in a fixed direction.

[0004] The use of manual control will lead to labor costs, and when there are too many pollution sources that need to be cleaned, multiple dust removal equipment is often required. Different dust removal equipment covers different areas, and operators need to switch between different dust removal equipment, or more operators are required, which takes more time and increases labor costs. Although the circular spraying method reduces labor costs, the overlap between the spraying direction and the pollution source is not high, the spraying time is difficult to control, and continuous spraying will waste a lot of cleaning fluid, which in turn reduces the efficiency of pollution source cleaning.

[0005] In view of the current operational problems of dust removal equipment, a cleaning method with a high degree of automation and resource conservation is urgently needed. Summary of the invention

[0006] The present invention provides a method and system for automatically cleaning dust removal equipment based on machine vision, so as to solve the problem of waste of manpower and material resources in the existing dust removal control mode.

[0007] The present invention is achieved through the following technical solutions:

[0008] A first aspect of the present invention provides a method for automatically cleaning dust from a dust removal device based on machine vision, comprising:

[0009] Acquire all pollution sources in the area to be cleaned, and mark pollution points according to the pollution range of the pollution sources;

[0010] Convert the contamination point into the coordinate system of the dust removal device in the area to be cleaned, and obtain the contamination point coordinates of the contamination point in the coordinate system of the dust removal device;

[0011] The cleaning coordinates corresponding to the stain coordinates are marked according to the operating range of the dust removal equipment; wherein the area to be cleaned includes at least one dust removal equipment, and each of the dust removal equipment establishes a three-dimensional coordinate system with itself as the center;

[0012] The image captured by the camera of the dust removal device is obtained, and the coordinates of the stains in the image are extracted. If the image analysis shows that there are pollutants at the stain coordinates, the dust removal device is driven to reach the cleaning coordinates corresponding to the stain coordinates and the dust removal operation is performed.

[0013] The dust removal control method of the present invention first marks the polluted points in the area to be cleaned, and establishes a coordinate system with each dust removal device as the center, unifies the two-dimensional image and the polluted points in the real world through the coordinate system of each dust removal device itself, and issues operation instructions as the control coordinate system to achieve precise motion control, realize fixed-point dust removal based on machine vision, and reduce personnel management and dust removal costs. In addition, pollutant identification of the image is performed based on the marked points, which improves the image processing efficiency, controls multiple dust removal devices in the same area, and improves the dust removal efficiency.

[0014] Furthermore, the method also includes: arranging at least one dust removal device according to the size of the area to be cleaned and the range that can be clearly monitored by the dust removal device, so that the sum of the monitoring areas of all dust removal devices can cover the area to be cleaned.

[0015] Furthermore, the number and arrangement positions of the dust removal devices are determined according to the number and distribution of the pollution points, so that each of the dust removal devices can monitor and clean a predetermined number of pollution points in a balanced manner.

[0016] Furthermore, the pollution source includes a fixed pollution source and a mobile pollution source; for the fixed pollution source, the location of the fixed pollution source is marked as a pollution point, and for the mobile pollution source, multiple pollution points are marked on the movement trajectory of the mobile pollution source.

[0017] Furthermore, the coordinate system of the dust removal device itself takes the camera on the dust removal device as the origin, the two movement directions of the dust removal device as the X-axis and the Y-axis, and the direction perpendicular to the ground as the Z-axis.

[0018] Furthermore, the dust removal operation includes spraying.

[0019] A second aspect of the present invention provides an automatic cleaning system for dust removal equipment based on machine vision, comprising:

[0020] A marking module, used to obtain all pollution sources in the area to be cleaned, and mark pollution points according to the pollution range of the pollution sources;

[0021] A coordinate conversion module is used to establish the dust removal device's own coordinate system, and convert the contaminated point into the dust removal device's own coordinate system, obtain the contamination point coordinates of the contaminated point in the dust removal device's own coordinate system, and mark the cleaning coordinates corresponding to the contamination point coordinates according to the operating range of the dust removal device;

[0022] An image processing module is used to obtain an image taken by a camera of the dust removal device, extract the coordinates of stains in the image, and analyze whether there are pollutants at the coordinates of the stains;

[0023] The control module is used to drive the dust removal device to the cleaning coordinates corresponding to the stain coordinates and perform dust removal operations if it is determined through image analysis that there are pollutants at the stain coordinates.

[0024] According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the automatic cleaning method for dust removal equipment based on machine vision as described in any one of the first aspect of the present invention is implemented.

[0025] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the automatic cleaning method for dust removal equipment based on machine vision as described in any one of the first aspects of the present invention is implemented.

[0026] In a fifth aspect of the present invention, a computer program product is provided. When the computer program product is run on a computer, the computer executes the automatic cleaning method for dust removal equipment based on machine vision as described in any one of the first aspects of the present invention.

[0027] Compared with the prior art, the present invention has the following advantages and beneficial effects: marking the polluted points in the area to be cleaned, establishing a coordinate system with each dust removal device as the center, unifying the two-dimensional image and the polluted points in the real world through the coordinate system of each dust removal device itself, and issuing operation instructions as the control coordinate system, thereby solving the problem of image coordinate distortion, achieving precise motion control, and realizing fixed-point dust removal based on machine vision, reducing personnel management and dust removal costs. Controlling multiple dust removal devices in the same area improves dust removal efficiency. Image pollutant identification based on marked points improves image processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0029] Figure 1 This is a flow chart of an automatic cleaning method for dust removal equipment based on machine vision according to an embodiment of the present invention;

[0030] Figure 2 This is a layout effect diagram of a dust removal device according to an embodiment of the present invention;

[0031] Figure 3 is a mapping schematic diagram of a control coordinate system according to an embodiment of the present invention;

[0032] Figure 4 This is an automatic spraying control flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0034] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to or inherent to other steps or units of the device.

[0035] The terms used in the various embodiments of the application are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments of the application. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meanings commonly understood by ordinary technicians in the field of the various embodiments of the application. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the application.

[0036] An embodiment of the present invention provides an automatic cleaning method for dust removal equipment based on machine vision, which uses a program with an algorithm to control the dust removal equipment to automatically clean the pollution source, locates the pollution source based on machine vision, and realizes fixed-point cleaning of the dust removal equipment, thereby freeing up labor, reducing labor costs, and improving cleaning efficiency.

[0037] The dust removal equipment of the present invention is based on the existing fixed dust removal equipment. The fixed dust removal equipment is mainly composed of the fog cannon itself and the control cabinet. The fog cannon includes equipment such as a spray gun, a fan, a water pump, etc. The control cabinet generally includes a PLC control system, a motion control server, a button or a touch screen, etc. The PLC control system includes a CPU module, an IO module, a power module, etc., and is generally used in industrial automation control scenarios. The dust removal equipment receives sensor or network device signals through the IO module, outputs corresponding signals through PLC programming, and controls the device to perform related actions to achieve the purpose of automatic control.

[0038] The above equipment and control systems are the basis of this method. They themselves do not have the function to achieve the purpose of the present invention. The present invention realizes the operation control of the dust removal equipment based on them. The dust removal equipment can quickly perform dust reduction operations on the pollution source and quickly adjust the relevant indicators to a safe range.

[0039] See also Figure 1 The flowchart of the automatic cleaning method of dust removal equipment based on machine vision is used to control the dust removal equipment to perform dust removal operations. The camera image of the dust removal equipment is used as a reference. The corresponding relationship between the two-dimensional coordinates of the image and the three-dimensional coordinates of the actual on-site area is created in combination with the server pulse count corresponding to the actual on-site spatial area, so as to solve the conversion problem between computer vision and actual spatial coordinates. The following control steps are included.

[0040] S1, first obtain all pollution sources in the area to be cleaned, and mark the pollution points according to the pollution range of the pollution sources.

[0041] S2, establishing a three-dimensional coordinate system centered on the dust removal device, converting the contamination point into the dust removal device's own coordinate system in the area to be cleaned, and obtaining the contamination point coordinates of the contamination point in the dust removal device's own coordinate system.

[0042] S3, marking the cleaning coordinates corresponding to the stain coordinates according to the operating range of the dust removal equipment.

[0043] S4, obtaining an image taken by a camera of the dust removal device, extracting the coordinates of the stain in the image, and if the image analysis shows that there is a pollutant at the stain coordinate, driving the corresponding dust removal device to reach the cleaning coordinate corresponding to the stain coordinate and performing the dust removal operation.

[0044] During construction work, the construction area generally has multiple pollution sources with relatively fixed positions, which can be divided into fixed pollution sources and mobile pollution sources according to whether the position of the pollution source changes. Fixed pollution sources are fixed in position, but the time of pollution generation is uncertain; mobile pollution sources refer to mobile objects that generate pollution at irregular times and points within a given range. It can be seen that the location where pollutants are generated in an area is relatively fixed, and the points where pollutants will appear can be pre-marked according to the usual pollution range of the pollution source, so that the appropriate number of dust removal equipment can be equipped in the area based on the number and distribution of pollution points. One dust removal equipment is responsible for its own monitoring area to improve the efficiency of dust removal.

[0045] For fixed pollution sources, they are generally installed near the pollution sources according to the effective range of the dust removal equipment and ensure that the operating range and spraying range of the dust removal equipment can include the target point. The camera needs to be able to clearly see the target point to ensure the accuracy of recognition. For non-fixed pollution sources, if the range is large, multiple fog cannons and multiple cameras are generally required to cooperate. The spraying range of all fog cannons and the monitoring range of the cameras are sufficient to include the entire construction range.

[0046] like Figure 2 The figure shows the layout effect of the dust removal equipment. During the specific layout, at least one dust removal equipment is arranged in the area to be cleaned according to the size of the cleaning area and the range that the dust removal equipment can clearly monitor, so that the sum of the monitoring areas of all dust removal equipment can cover the area to be cleaned.

[0047] The range that the dust removal equipment can clearly monitor is based on the pixels and focal length of its camera. The captured picture is clear and the image size is appropriate, which makes it easy to accurately identify pollutants through images and improve the accuracy and efficiency of image processing. At the same time, it also takes into account the operating range of a single dust removal device. If the operating range is too large, the time for a dust removal operation will be increased, affecting the overall operating efficiency in the area.

[0048] Furthermore, the number and arrangement positions of the dust removal devices are determined according to the number and distribution of the pollution points, so that each dust removal device can monitor and clean a predetermined number of pollution points in a balanced manner.

[0049] In addition to meeting the need for comprehensive coverage of the clean area, the number and distribution of pollution points must also be considered. Since some sub-areas may have concentrated pollution sources while others may have dispersed pollution sources, if only the overall area coverage is considered, some dust removal equipment may be overloaded while others may not be saturated. Therefore, the location of the dust removal equipment must be set taking into account the distribution of pollution points to ensure that each dust removal equipment has a balanced workload.

[0050] In one embodiment of the present invention, for a fixed pollution source, the location of the fixed pollution source is marked as a pollution point, and for a mobile pollution source, multiple pollution points are marked on the movement trajectory of the mobile pollution source.

[0051] The pollution points can be a set of points concentrated in an area in the coordinate system, such as a circular area where the pollution source is located, and the coordinate point set formed by the circular area is the pollution point of the pollution source. For a mobile pollution source, a pollution point is marked at a fixed length interval on its motion trajectory, so that the image area where the motion trajectory is located can be tracked through the image.

[0052] In the conversion of the control coordinate system of the present invention, the real world coordinate system is the basis of this method. The coordinate system of computer vision is generally based on images. The actual situation on the scene will be captured by the camera and then input into the computer, which will cause scaling and distortion problems, so the computer vision coordinate system cannot reflect the real world coordinates. At the same time, the dust removal equipment itself can rotate in multiple directions, so its effective working area is a sphere, and the coordinate position cannot be expressed by simple two-dimensional coordinates x and y. Therefore, it is not possible to directly use the computer vision coordinate system to generate instructions to control the direction of the dust removal equipment, which will produce a large deviation in the coordinates of the real world.

[0053] like Figure 3 The figure shows a mapping diagram of the control coordinate system. The present invention uses the dust removal device as the origin to create the dust removal device's own coordinate system, and describes the range in which the dust removal device can operate and clean in this coordinate system. For example, the movement direction of the dust removal device (its own longitudinal direction) is defined as the X-axis, the vertical X-axis in the plane is defined as the Y-axis, and the vertical direction (vertical to the ground) is defined as the Z-axis. Then, a correspondence between the point position based on this coordinate system and the coordinates of the camera's two-dimensional screen is established, that is, the pixel coordinates of the marked points in each screen and the actual coordinates of the dust removal device sprayed to that position are recorded. When there are enough marked points, the marked points within the target object's marking frame are the pollution sources that need to be sprayed, and the dust removal device moves to the corresponding position for spraying and cleaning operations.

[0054] The marking points are stored in the database of the control system. The database adopts an associative database, and the corresponding cleaning coordinates are determined according to the coordinates of the marking points and the operating range of the dust removal equipment. That is, after the dust removal equipment is driven to the cleaning coordinates, the dust removal operation can be performed on the marking points.

[0055] In one implementation, for a general dust removal device with two degrees of freedom in a plane, a three-dimensional coordinate system of the dust removal device itself is established with a camera on the dust removal device as the origin, the two movement directions of the dust removal device as the X-axis and the Y-axis, and the direction perpendicular to the ground as the Z-axis.

[0056] Based on the above coordinate system settings, the two-dimensional images collected by each dust removal device and the coordinates of the pollution points in the monitoring area are based on the coordinate system of the dust removal device itself. The control system only needs to process the image data in the coordinate system corresponding to each dust removal device, and control the dust removal device to perform dust removal operations based on the processing results. Multiple dust removal devices can be controlled in one area.

[0057] When performing image processing, the detection results of multiple frames of images are combined and then deduplicated to solve the problem that the detection effect of a single image of computer vision does not meet production requirements.

[0058] A second aspect of the present invention provides an automatic cleaning system for dust removal equipment based on machine vision, comprising:

[0059] A marking module, used to obtain all pollution sources in the area to be cleaned, and mark pollution points according to the pollution range of the pollution sources;

[0060] A coordinate conversion module is used to establish the dust removal device's own coordinate system, and convert the contaminated point into the dust removal device's own coordinate system, obtain the contamination point coordinates of the contaminated point in the dust removal device's own coordinate system, and mark the cleaning coordinates corresponding to the contamination point coordinates according to the operating range of the dust removal device;

[0061] An image processing module is used to obtain an image taken by a camera of the dust removal device, extract the coordinates of stains in the image, and analyze whether there are pollutants at the coordinates of the stains;

[0062] The control module is used to drive the dust removal device to the cleaning coordinates corresponding to the stain coordinates and perform dust removal operations if it is determined through image analysis that there are pollutants at the stain coordinates.

[0063] In one embodiment of the present invention, the automatic spraying control process is as follows Figure 4 As shown, the following steps are included.

[0064] Step 1: Start the control system.

[0065] Step 2: Add a control algorithm group and add the camera to be analyzed.

[0066] Step 3: Bind and register the dust removal device in the system.

[0067] Step 4: Mark enough marking points on each camera image, verify and record the motion coordinates of each marking point where the dust removal equipment can spray.

[0068] Step 5: The algorithm loads the pollution source model and connects to the camera to obtain real-time video stream information.

[0069] Step 6: When the algorithm detects a pollution source in the image, it frames the location of the pollution source and identifies the marked points in the detection frame.

[0070] Step 7: Convert the coordinates of the marked points in the image into the motion coordinates of the actual dust removal device.

[0071] Step 8: According to the binding relationship between the camera and the dust removal device, the motion coordinates are sent to the corresponding dust removal device.

[0072] Step 9: After receiving the running coordinates, the dust removal device self-checks the current state. If the current state is normal, it controls itself to move to this coordinate; if the current state is abnormal, it refuses to execute the command and reports an error prompt.

[0073] Step 10, spray for a fixed time or stop spraying when it is detected that the pollution source has disappeared.

[0074] Step 11, wait for the next job.

[0075] This solution can control all dust removal equipment at the same time, and it will automatically turn on when there is a pollution source, and automatically turn off when there is no pollution source. This solution can effectively reduce the workload of manpower, reduce management costs, improve work efficiency while reducing work intensity, and reduce resource waste.

[0076] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory, and the number of processors may be one or more. The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs, and modules. The processor executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory, so as to implement the automatic cleaning method of dust removal equipment based on machine vision according to any of the above embodiments of the present invention.

[0077] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the automatic cleaning method for dust removal equipment based on machine vision according to any embodiment of the present invention.

[0079] An embodiment of the present invention further provides a computer program product. When the computer program product is run on a computer, the computer executes the automatic cleaning method for dust removal equipment based on machine vision according to any of the above embodiments of the present invention.

[0080] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. Automatic cleaning method for dust removal equipment based on machine vision, characterized in that: include: Acquire all pollution sources in the area to be cleaned, and mark pollution points according to the pollution range of the pollution sources; Convert the contamination point into the coordinate system of the dust removal device in the area to be cleaned, and obtain the contamination point coordinates of the contamination point in the coordinate system of the dust removal device; The cleaning coordinates corresponding to the stain coordinates are marked according to the operating range of the dust removal equipment; wherein the area to be cleaned includes at least one dust removal equipment, and each of the dust removal equipment establishes a three-dimensional coordinate system with itself as the center; The image captured by the camera of the dust removal device is obtained, and the coordinates of the stains in the image are extracted. If the image analysis shows that there are pollutants at the stain coordinates, the dust removal device is driven to reach the cleaning coordinates corresponding to the stain coordinates and the dust removal operation is performed.

2. The automatic cleaning method for dust removal equipment based on machine vision according to claim 1 is characterized in that: The method further includes: arranging at least one dust removal device according to the size of the area to be cleaned and the range that can be clearly monitored by the dust removal device, so that the sum of the monitoring areas of all dust removal devices can cover the area to be cleaned.

3. The automatic cleaning method for dust removal equipment based on machine vision according to claim 2 is characterized in that: The number and arrangement positions of the dust removal devices are determined according to the number and distribution of the pollution points, so that each of the dust removal devices can monitor and clean a predetermined number of pollution points in a balanced manner.

4. The automatic cleaning method for dust removal equipment based on machine vision according to claim 1 is characterized in that: The pollution sources include fixed pollution sources and mobile pollution sources; for the fixed pollution sources, the locations of the fixed pollution sources are marked as pollution points, and for the mobile pollution sources, multiple pollution points are marked on the movement trajectory of the mobile pollution sources.

5. The automatic cleaning method for dust removal equipment based on machine vision according to claim 1 is characterized in that: The coordinate system of the dust removal device itself takes the camera on the dust removal device as the origin, the two movement directions of the dust removal device as the X-axis and the Y-axis, and the direction perpendicular to the ground as the Z-axis.

6. The automatic cleaning method for dust removal equipment based on machine vision according to claim 1 is characterized in that: The dust removal operation includes spraying.

7. Automatic cleaning system for dust removal equipment based on machine vision, including: A marking module, used to obtain all pollution sources in the area to be cleaned, and mark pollution points according to the pollution range of the pollution sources; A coordinate conversion module is used to establish the dust removal device's own coordinate system, and convert the contaminated point into the dust removal device's own coordinate system, obtain the contamination point coordinates of the contaminated point in the dust removal device's own coordinate system, and mark the cleaning coordinates corresponding to the contamination point coordinates according to the operating range of the dust removal device; An image processing module is used to obtain an image taken by a camera of the dust removal device, extract the coordinates of stains in the image, and analyze whether there are pollutants at the coordinates of the stains; The control module is used to drive the dust removal device to the cleaning coordinates corresponding to the stain coordinates and perform dust removal operations if it is determined through image analysis that there are pollutants at the stain coordinates.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the automatic cleaning method for dust removal equipment based on machine vision described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the automatic cleaning method for dust removal equipment based on machine vision described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the computer program product is run on a computer, the computer is enabled to execute the automatic cleaning method for dust removal equipment based on machine vision as described in any one of claims 1 to 6.

Images