Target detection method and device for infrared image, electronic equipment and vehicle
By constructing a target detection method for infrared images, the boundary pixels are determined by the set of pixels and the difference, and a boundary image is generated. This solves the problems of high training cost and low accuracy in the recognition of weak targets in infrared images, and achieves efficient target detection.
Patent Information
- Application Number
- CN202410612787.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-16
- Publication Date
- 2025-11-18
AI Technical Summary
Existing technologies for identifying small targets using infrared images suffer from high training costs and insufficient accuracy, making it difficult to effectively identify and detect small targets.
By acquiring target pixels and background pixels in infrared images, first and second pixel sets are constructed. Boundary pixels are determined using pixel differences and set conditions. A boundary image is generated and reliable pixels are filtered to identify the target object.
It effectively filters out salt-and-pepper noise and complex backgrounds, reduces training costs, and improves the detection accuracy of small infrared targets.
Smart Images
Figure CN120976511A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] Embodiments of the present disclosure relate to the technical field of image detection, and more particularly, to an infrared image target detection method and device, electronic equipment and vehicle. BACKGROUND
[0002] With the rapid development of image detection technology, infrared thermal imaging as a relatively reliable imaging technology can identify target objects with heat in scenes such as dim vision or night. The prior art usually trains a recognition model using a large number of weak and small target object training sets, and then detects weak and small target objects through the trained recognition model. The scheme has a high training cost and an unexpected accuracy. SUMMARY
[0003] An object of embodiments of the present disclosure is to provide a new technical solution for infrared image target detection.
[0004] According to a first aspect of the present disclosure, an infrared image target detection method is provided, the method comprising:
[0005] obtaining target pixel points and background pixel points in the infrared image; obtaining a first pixel point set and a second pixel point set from the target pixel points and the background pixel points; the pixel points in the first pixel point set are pixel points similar to the pixel values of the target pixel points, and the pixel points in the second pixel point set are pixel points greater than the pixel values of the background pixel points; determining a target object in the infrared image according to the first pixel point set and the second pixel point set.
[0006] Optionally, the pixel points in the first pixel point set are first set distances away from the target pixel points, the pixel points in the second pixel point set are second set distances away from the target pixel points, the first set distance is less than the second set distance, and a distance difference value between the second set distance and the first set distance is greater than or equal to 2 pixel points.
[0007] Optionally, the determining a target object in the infrared image according to the first pixel point set and the second pixel point set comprises:
[0008] determining a first pixel difference value between the pixel points of the first pixel point set and the target pixel points;
[0009] determining a second pixel difference value between the pixel points of the second pixel point set and the background in the infrared image;
[0010] determining a target pixel point whose first pixel difference value and second pixel difference value meet a set condition, and taking the target pixel point as a boundary pixel point;
[0011] According to the boundary pixel point, a target object in the infrared image is determined.
[0012] Optionally, the first pixel difference value is a difference value between a maximum pixel value of the first pixel point set and a first set reference value; and the second pixel difference value is a difference value between a median pixel value of the second pixel point set and a second set reference value.
[0013] Optionally, the target pixel point, in which the first pixel difference value and the second pixel difference value meet a set condition, is determined as the boundary pixel point, and comprises:
[0014] A target pixel point, in which a maximum pixel value of the first pixel point set is greater than or equal to a first set reference value and a median pixel value of the second pixel point set is less than or equal to a second set reference value, is determined as the boundary pixel point.
[0015] Optionally, the first set reference value is related to a pixel value of the target pixel point and a first fixed value, the second set reference value is related to the pixel value of the target pixel point and a second fixed value, and the first fixed value and the second fixed value correspond to different multiples of a set pixel range.
[0016] Optionally, before the target object in the infrared image is determined according to the boundary pixel point, the method comprises:
[0017] A pixel value of a boundary pixel point in the infrared image is set as a first numerical value, a pixel value of a non-boundary pixel point in the infrared image is set as a second numerical value, and a boundary image is generated.
[0018] Optionally, the target object in the infrared image is determined according to the boundary pixel point, and comprises:
[0019] The boundary image is compared with the infrared image to determine a reliable pixel point in the infrared image.
[0020] According to the reliable pixel point, a target object in the infrared image is determined.
[0021] Optionally, the first numerical value is a difference value between a pixel value of the boundary pixel point in the infrared image and a corresponding median pixel value; and the second numerical value is a set value.
[0022] Optionally, the boundary image is compared with the infrared image to determine the reliable pixel point in the infrared image, and comprises:
[0023] A first normalized numerical value of the boundary image is determined, and a second normalized numerical value of the infrared image is determined.
[0024] In a case that the first normalized value is greater than or equal to the second normalized value, a reliable pixel point is determined.
[0025] Optionally, the determining the target object in the infrared image according to the reliable pixel point comprises:
[0026] The target object in the infrared image is determined according to the boundary image and the reliable pixel point.
[0027] Optionally, the determining the target object in the infrared image according to the boundary image and the reliable pixel point comprises:
[0028] A third pixel set of the reliable pixel point is determined; wherein the third pixel set is a set of pixel points in the reliable pixel point and the pixel points in the boundary image within a third set distance; wherein the third set distance is greater than or equal to the shortest distance between the reliable pixel point and the boundary of the target object.
[0029] The target object in the infrared image is constructed according to the third pixel set.
[0030] According to a second aspect of the present disclosure, there is also provided an infrared image target detection device, the device comprising:
[0031] An acquisition module is configured to acquire target pixel points and background pixel points in the infrared image, and obtain a first pixel point set and a second pixel point set from the target pixel points and the background pixel points; the pixel points in the first pixel point set are pixel points with pixel values close to the target pixel points, and the pixel points in the second pixel point set are pixel points with pixel values greater than the background pixel points.
[0032] A determination module is configured to determine a target object in the infrared image according to the first pixel point set and the second pixel point set.
[0033] According to a third aspect of the present disclosure, there is also provided an electronic device comprising a memory and a processor, the memory being configured to store a computer program, and the processor being configured to execute the computer program to implement the method according to the first aspect of the present disclosure.
[0034] According to a fourth aspect of the present disclosure, there is also provided a computer readable storage medium, the computer readable storage medium storing a computer program, the computer program being configured to implement the method according to the first aspect of the present disclosure when executed by a processor.
[0035] According to a fifth aspect of the present disclosure, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect of the present disclosure.
[0036] According to a sixth aspect of the present disclosure, there is also provided a vehicle comprising the target detection apparatus for infrared images according to the second aspect or the electronic device according to the third aspect.
[0037] An advantage of the embodiments of the present disclosure is that the method provided by the embodiments can determine the first pixel point set and the second pixel point set of the target pixel point according to the characteristics that the pixel value of the edge point of the target object is greater than the background pixel value and similar to the pixel value of the edge point of the target object, and then determine the target object in the infrared image, which can effectively filter out the salt and pepper noise and the sharp complex image background, reduce the training cost, and improve the detection accuracy of the infrared dim small target.
[0038] Other features and advantages of the embodiments of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS
[0039] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the embodiments of the present disclosure.
[0040] Figure 1 A hardware structure schematic diagram of an electronic device that can be used to implement the target detection method for infrared images according to an embodiment of the present disclosure is shown;
[0041] Figure 2 A flowchart of the target detection method for infrared images according to an embodiment is shown;
[0042] Figure 3 A schematic diagram of determining the boundary pixel point according to an embodiment is shown;
[0043] Figure 4 A schematic diagram of determining the boundary pixel point according to another embodiment is shown;
[0044] Figure 5 A block schematic diagram of the target detection apparatus for infrared images according to an embodiment is shown;
[0045] Figure 6 A hardware structure schematic diagram of an electronic device according to an embodiment is shown. DETAILED DESCRIPTION
[0046] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the invention.
[0047] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.
[0048] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0049] In all the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.
[0050] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0051] <System Implementation>
[0052] Figure 1 A schematic diagram of the hardware structure of an electronic device that can be used to implement a target detection method for infrared images according to embodiments of the present disclosure is shown.
[0053] The electronic device 1000 is a device capable of processing images, which may include visible light images, infrared images, etc., and is not limited thereto. The electronic device 1000 may be a mobile phone, tablet computer, PC, etc., and is not limited thereto. The electronic device 1000 may be, for example, a vehicle.
[0054] like Figure 1 As shown, the electronic device 1000 may include a processor 1101, a memory 1102, an interface device 1103, a communication device 1104, an output device 1105, an input device 1106, etc. Figure 1 The hardware configuration shown is illustrative only and is not intended to limit this disclosure, its application, or its use.
[0055] The processor 1101 is configured to execute a computer program, which can be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 1102 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), a nonvolatile memory such as a hard disk, etc. The interface device 1103 includes, for example, a USB interface, a network interface, a headphone interface, etc. The communication device 1104 is capable of wired or wireless communication, for example, and can include at least one short-range communication module, such as any module for short-range wireless communication based on a Hilink protocol, a WiFi (IEEE 802.11 protocol), a Mesh, a Bluetooth, a ZigBee, a Thread, a Z-Wave, an NFC, a UWB, a LiFi, etc., and can also include a long-range communication module, such as any module for WLAN, GPRS, 2G / 3G / 4G / 5G long-range communication.
[0056] In this embodiment, the memory 1102 of the electronic device 1000 is configured to store a computer program for controlling the processor 1101 to operate to perform the target detection method of an infrared image according to any embodiment of the present disclosure.
[0057] Next, various embodiments of the target detection method of an infrared image are described by taking the electronic device 1000 as shown in Figure 1 the embodiment as an example.
[0058] <Method Embodiment>
[0059] Figure 2 A flowchart of the target detection method of an infrared image according to one embodiment is shown. The embodiment includes, for example, Figure 1 the electronic device 1000.
[0060] As shown in Figure 2 , the target detection method of an infrared image according to the embodiment can include the following steps S210 to S220:
[0061] In step S210, target pixel points and background pixel points in the infrared image are obtained; first and second pixel point sets are obtained according to the target pixel points and the background pixel points; the pixel points in the first pixel point set are pixel points with pixel values close to those of the target pixel points, and the pixel points in the second pixel point set are pixel points with pixel values greater than those of the background pixel points.
[0062] In this embodiment, the electronic device 1000 can obtain the infrared image through the configured camera, or obtain the infrared image sent by other electronic devices through the network, which is not limited here.
[0063] In this embodiment, each pixel point on the infrared image corresponds to a corresponding pixel value, in other words, the pixel value corresponding to each pixel point can reflect the infrared image. The pixel range corresponding to the infrared image is, for example, 0-255, which is not limited here.
[0064] In this embodiment, the target pixel point is any pixel point on the infrared image.
[0065] In some examples, the first pixel point set and the second pixel point set can be screened according to a set condition, which can include the following conditions. Condition one, the pixel value of the pixel point in the first pixel point set and the second pixel point set is greater than the background pixel value in the infrared image. Condition two, the first pixel point set and the second pixel point set satisfy the characteristic of the equal distance edge pixel value of the Gaussian light spot center, for example, the pixel value of the pixel point in the first pixel point set is S1 and is located around the target pixel point, the pixel value of the pixel point in the second pixel point set is S2 and is located around the target pixel point, and the first pixel point set and the second pixel point set form different closed loops, that is, the first pixel point set and the second pixel point set satisfy the characteristic of the equal distance edge pixel value of the Gaussian light spot center. Further, the second pixel point set of the target pixel point can also be determined according to the characteristic that the distance from the Gaussian light spot center is close and the edge point pixel value of the target object is close.
[0066] In step S220, the target object in the infrared image is determined according to the first pixel point set and the second pixel point set.
[0067] In some embodiments, in order to improve the accuracy of the determined boundary pixel point, the pixel point in the first pixel point set is a first set distance away from the target pixel point, the pixel point in the second pixel point set is a second set distance away from the target pixel point, the first set distance is less than the second set distance, and the distance difference between the second set distance and the first set distance is greater than or equal to 2 pixel points.
[0068] In some examples, the first set distance can be a distance value or a distance range, and the second set distance can be a distance value or a distance range, which is not limited here. For example, the first set distance is a distance value and is 0, and the second set distance is also a distance value and is 2 pixel points, and correspondingly, the first pixel point set a is {a1, a2, a3, …, a8}, and the second pixel point set b is {b1, b2, b3, …, b16}. For another example, the first set distance is a distance range and is 0-2 pixel points, and the second set distance is also a distance range and is 2-4 pixel points, and correspondingly, the first pixel point set a is {a1, a2, a3, …, a8}, and the second pixel point set b is {b1, b2, b3, …, b16}. Figure 3 Figure 4 For example, the first set distance is a distance value and is 0, and the second set distance is a distance range that includes distances of 2 pixels from the target pixel P1 and distances of 3 pixels from the target pixel P1. Accordingly, the first set of pixels c is {c1,c2,c3,……,c8}, and the second set of pixels d is {d1,d2,d3,……,d36}.
[0069] In some embodiments, in order to reduce the number of pixels in the first pixel set and the second pixel set while accurately determining whether the target pixel is a boundary pixel, thereby improving the detection efficiency of the target object, the first set distance is 0 and the second set distance is 2 pixels.
[0070] by Figure 3 For example, let the first set of pixels 'a' be {a1, a2, a3, ..., a8}, and the second set of pixels 'b' be {b1, b2, b3, ..., b16}. Then, the maximum pixel value in the first set of pixels is the largest among the eight pixel values corresponding to pixels a1 through a8. The median pixel value in the second set of pixels is the median among the sixteen pixel values corresponding to pixels b1 through b16.
[0071] Step S220 may include the following steps S230 to S260:
[0072] Step S230: Determine the first pixel difference between the pixels in the first pixel set and the target pixel.
[0073] In some examples, the maximum, minimum, average, or median pixel value of the first set of pixels is determined. The first pixel difference can be the difference between one of these values—the maximum, minimum, average, or median pixel value—and the pixel value of the target pixel.
[0074] Step S240: Determine the difference between the pixels of the second pixel set and the second pixel of the background in the infrared image.
[0075] In some examples, the maximum, minimum, average, or median pixel value of the pixels in the second pixel set is determined. The second pixel difference can be the difference between one of these values—the maximum, minimum, average, or median pixel value—and the background in the infrared image.
[0076] Step S250: Determine the target pixel point whose first pixel difference and second pixel difference meet the set conditions, and use it as the boundary pixel point.
[0077] In some examples, the set conditions may include a threshold where the maximum, minimum, average, or median pixel value in the first set of pixels is greater than or equal to a certain pixel value related to the target pixel, and a threshold where the maximum, minimum, average, or median pixel value in the second set of pixels is less than or equal to a certain pixel value related to the background in the infrared image. The threshold for the target pixel value may be the target pixel value minus a certain value or the target pixel value multiplied by a certain coefficient, etc., and the threshold for the background pixel value in the infrared image may be the background pixel value plus a certain value or the background pixel value multiplied by a certain coefficient, etc.
[0078] In this embodiment, when a target pixel meets the above-mentioned set conditions, the target pixel can be considered as a boundary pixel.
[0079] Step S260: Determine the target object in the infrared image based on the boundary pixels.
[0080] In this embodiment, the boundary pixel can be one or more, and there is no limitation here.
[0081] In some examples, the boundary pixels are multiple and form a closed loop. In this case, the closed loop and the pixels within the closed loop can represent the target object.
[0082] In some examples, the distance between two pixels can be represented by a specific size or by the number of pixels, for example, as shown in the example. Figure 3 As shown, pixel a1 and pixel b2 are 1 pixel apart.
[0083] In some examples, such as Figure 3 As shown, the first and second pixel sets are determined using a set dual-ring detection operator. The first set distance is 0, and the second set distance is 2 pixels. Therefore, the dual-ring detection operator determines the first pixel set *a* of the target pixel P as {a1, a2, a3, ..., a8}, and the second pixel set *b* of the target pixel P as {b1, b2, b3, ..., b16}. Through this determination method, the dual-ring detection operator can sequentially scan all pixels in the infrared image and obtain the corresponding first and second pixel sets.
[0084] In some embodiments, the first pixel difference is the difference between the maximum pixel value of the first pixel set and a first set reference value; the second pixel difference is the difference between the median pixel value of the second pixel set and a second set reference value.
[0085] In other words, the difference between the maximum pixel value and the first set reference value is preferably used as the first pixel difference value, and the median pixel value and the second set reference value are preferably used as the second pixel difference value, which can effectively improve the accuracy of determining whether a target pixel point is a boundary pixel point.
[0086] In some embodiments, step S250 can include the following step S2501:
[0087] Step S2501: determining a target pixel point whose maximum pixel value of the first pixel point set is greater than or equal to the first set reference value and whose median pixel value of the second pixel point set is less than or equal to the second set reference value, and regarding the target pixel point as a boundary pixel point.
[0088] In some examples, the above-mentioned set condition can be that the maximum pixel value of the first pixel point set of a target pixel point is greater than or equal to the first set reference value, and the median pixel value of the second pixel point set of the target pixel point is less than or equal to the second set reference value. By using the maximum pixel value to determine whether the pixel points of the first pixel point set meet the characteristics of the Gaussian light spot, and then using the median pixel value to determine that the pixel values of the second pixel point set are generally greater than the background pixel value, the accuracy of the screened boundary pixel points can be effectively improved.
[0089] In some embodiments, in order to improve the accuracy of the obtained boundary pixel points, the first set reference value is related to the pixel value of the target pixel point and a first fixed value, and the second set reference value is related to the pixel value of the target pixel point and a second fixed value, and the first fixed value and the second fixed value correspond to different multiples of the set pixel range.
[0090] In some examples, the pixel value of the target pixel point is I p , the first fixed value is t2, and the second fixed value is t1. Therefore, the first set reference value is I p -t2, and the second set reference value is I p -t1. The maximum pixel value of the first pixel point set is I The median pixel value of the second pixel point set is I That is, the maximum pixel value of the first pixel point set being greater than or equal to the first set reference value can be expressed as: The median pixel value of the second pixel point set being less than or equal to the second set reference value can be expressed as:
[0091] In other words, the pixel value of the target pixel point and the first fixed value represent the critical value of the adjacent pixel point of the target pixel point, i.e., the first set reference value. The comparison between the maximum pixel value of the first pixel point set and the first set reference value reflects the difference between the target pixel point and its surrounding equidistant pixel points, thereby improving the accuracy of the screening of the boundary pixel point. The pixel value of the target pixel point and the second fixed value represent the critical value of the image background of the infrared image, i.e., the second set reference value. The comparison between the median pixel value of the second pixel point set and the second set reference value reflects whether most of the pixel points in the second pixel point set are close to the pixel value of the pixel point of the image background. That is, in the case where the median pixel value of the second pixel point set is less than or equal to the second set reference value, it is indicated that most of the pixel points in the second pixel point set are close to the pixel value of the pixel point of the image background, thereby improving the accuracy of screening the pixel points of the image background while reducing the influence of the noise points in the infrared image.
[0092] In this embodiment, the multiples corresponding to the first fixed value and the second fixed value can be artificially set, which is not limited herein.
[0093] In some examples, the pixel value of the target pixel point is I p , the pixel range can be 0-255, the multiple corresponding to the first fixed value is 0.05, then the first fixed value can be 0.05x255, taking 13, and the first set reference value can be I p -13. The multiple corresponding to the second fixed value is 0.1, then the second fixed value can be 0.1x255, taking 25, and the second set reference value can be I p -25.
[0094] In some embodiments, before step S240, the method further comprises the following step S239:
[0095] In step S239, the pixel value of the boundary pixel point in the infrared image is set to a first numerical value, and the pixel value of the non-boundary pixel point in the infrared image is set to a second numerical value, thereby generating a boundary image.
[0096] In this embodiment, the non-boundary pixel point can include all pixel points in the infrared image except the boundary pixel point, or can include all pixel points in the infrared image except the boundary pixel point and the pixel points within the closed contour surrounded by the boundary pixel point, which is not limited herein.
[0097] In this embodiment, different boundary pixel points can be set to the same first numerical value, or can be set to different first numerical values, which is not limited herein.
[0098] In the embodiment, the different non-boundary pixel points can be set as the same first value or different first values, which is not limited herein.
[0099] In some embodiments, in order to reflect the difference between the boundary pixel points and the non-boundary pixel points, the first value is the difference between the pixel value of the boundary pixel point in the infrared image and the corresponding median pixel value, the pixel value of the boundary pixel point is I p The corresponding median pixel value is That is, the first value is expressed as The second value is a set value, for example, 0, and then the boundary image I is obtained. The expression of the boundary image I
[0100]
[0101] Based on the above formula, each pixel point in the infrared image can be revalued, and thus the boundary image I
[0102] On this basis, the step S240 can include the following steps S241 and S242:
[0103] Step S241, comparing the boundary image with the infrared image to determine the reliable pixel points in the infrared image.
[0104] In some embodiments, the step S241 can include the following steps S2411 to S2413:
[0105] Step S2411, determining the first normalized value of the boundary image, and determining the second normalized value of the infrared image.
[0106] In some examples, the pixel range is 0-255, and the pixel value of the pixel point f1 of the infrared image I is 51, so the second normalized value of the pixel point f1 is 0.2.
[0107] In some examples, the maximum pixel value in the boundary image is 200, and the pixel value of the boundary pixel point g1 is 100, so the first normalized value of the boundary pixel point g1 is 0.5.
[0108] Step S2412, comparing the first normalized value and the second normalized value of the boundary pixel point to obtain a comparison result.
[0109] Step S2413, in the case that the comparison result of the target boundary pixel point in the boundary pixel points is that the first normalized value is greater than or equal to the second normalized value, determining that the target boundary pixel point is a reliable pixel point.
[0110] In some examples, the first normalized result is represented as The second normalized result is represented as I, and then the comparison result I re The expression is as follows:
[0111]
[0112] Based on the above formula, in the case that the comparison result of a boundary pixel point is 1, the boundary pixel point is a reliable pixel point. In the case that the comparison result of a boundary pixel point is 0, the boundary pixel point is not a reliable pixel point.
[0113] In step S242, the target object in the infrared image is determined according to the reliable pixel points.
[0114] In some examples, the step S242 can include the following step S250:
[0115] In step S250, the target object in the infrared image is determined according to the boundary image and the reliable pixel points.
[0116] In some examples, after the reliable pixel points are obtained, the pixel points in the contour formed by the reliable pixel points on the boundary image represent the target object in the infrared image, and the pixel points around the reliable pixel points can also be determined, and the pixel points in the contour formed by the pixel points around the reliable pixel points represent the target object in the infrared image, which is not limited herein.
[0117] In other words, the target object in the infrared image is determined by using the boundary image and the reliable pixel points, and the accuracy of the detected target object is higher.
[0118] In some examples, the step S250 can include the following steps S2501 and S2502:
[0119] In step S2501, a third pixel set of the reliable pixel points is determined; wherein the third pixel set is a set of pixel points that are within a third set distance from the reliable pixel points and the pixel points in the boundary image; and wherein the third set distance is greater than or equal to the shortest distance between the reliable pixel points and the boundary of the target object.
[0120] In some examples, when the third set distance is equal to the shortest distance between the reliable pixel points and the boundary of the target object, the third pixel set can exactly include the pixel points corresponding to the boundary of the target object, so as to effectively improve the accuracy of the subsequently constructed target object. When the third set distance is greater than the shortest distance between the reliable pixel points and the boundary of the target object, the third pixel set can include the pixel points corresponding to the background around the boundary of the target object, so as to effectively improve the integrity of the subsequently constructed target object.
[0121] In some examples, the third set distance is 4 pixels from the reliable pixel point, and the third pixel set can be the pixel points in the nearby boundary image of the reliable pixel point. The nearby pixel points can be within a 9x9 pixel range around the reliable pixel point.
[0122] In step S2502, the target object in the infrared image is constructed according to the third pixel set.
[0123] In this embodiment, after determining one or more third pixel sets, the pixel points in the third pixel sets in the infrared image are retained, so as to construct the target object in the infrared image by using the third pixel set.
[0124] In other words, the target object in the infrared image is determined by using the third pixel set, which can effectively improve the integrity of the target object in the obtained infrared image.
[0125] <Device Embodiment One>
[0126] Figure 5 A principle block diagram of a target detection device of an infrared image according to an embodiment is shown. As shown in the figure, the target detection device 500 of the infrared image can include an acquisition module 510 and a determination module 520. Figure 5
[0127] The acquisition module 510 is configured to acquire target pixel points and background pixel points in the infrared image, and obtain a first pixel set and a second pixel set according to the target pixel points and the background pixel points. The pixel points in the first pixel set are pixel points with pixel values close to the target pixel points, and the pixel points in the second pixel set are pixel points with pixel values greater than the background pixel points.
[0128] The determination module 520 is configured to determine a first pixel difference value between the pixel points in the first pixel set and the target pixel points, determine a second pixel difference value between the pixel points in the second pixel set and the background in the infrared image, determine target pixel points with the first pixel difference value and the second pixel difference value meeting a set condition as boundary pixel points, and determine a target object in the infrared image according to the boundary pixel points.
[0129] Optionally, the determination module 520 is further configured to determine target pixel points with a maximum pixel value in the first pixel set greater than or equal to a first set reference value and a median pixel value in the second pixel set less than or equal to a second set reference value as the boundary pixel points.
[0130] Optionally, the target detection apparatus 500 for infrared image further comprises a generating module, configured to set a pixel value of a boundary pixel in the infrared image as a first value, and set a pixel value of a non-boundary pixel in the infrared image as a second value, and generate a boundary image.
[0131] Optionally, the determining module 520 is further configured to compare the boundary image with the infrared image, and determine reliable pixels in the infrared image; and determine the target object in the infrared image according to the reliable pixels.
[0132] Optionally, the determining module 520 is further configured to determine a first normalized value of the boundary image, and determine a second normalized value of the infrared image; and determine the reliable pixels in a case that the first normalized value is greater than or equal to the second normalized value.
[0133] Optionally, the determining module 520 is further configured to determine the target object in the infrared image according to the boundary image and the reliable pixels.
[0134] Optionally, the determining module 520 is further configured to determine a third pixel set of the reliable pixels; wherein the third pixel set is a set of pixels which are within a third set distance from the reliable pixels and the pixels in the boundary image; and wherein the third set distance is greater than or equal to a shortest distance between the reliable pixels and a boundary of the target object; and construct the target object in the infrared image according to the third pixel set.
[0135] The target detection apparatus 500 for infrared image can be an electronic device 1000. Figure 1
[0136] <Embodiment Two of Device>
[0137] Figure 6 A hardware structure schematic diagram of an electronic device according to another embodiment is shown.
[0138] As shown in Figure 6 , the electronic device 600 comprises a processor 610 and a memory 620, the memory 620 is configured to store an executable computer program, and the processor 610 is configured to execute a method according to any method embodiment above according to control of the computer program.
[0139] The electronic device 600 can be an electronic device 1000.
[0140] The above modules of the target detection apparatus 500 for infrared image can be implemented by the processor 610 in the embodiment executing the computer program stored in the memory 620, or can be implemented by other structures, which are not limited here.
[0141] The present application can be a system, a method, and / or a computer program product. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present application.
[0142] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or punched tape, a magnetically encoded device such as magnetic strip
[0143] The computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.
[0144] Computer readable program instructions for carrying out operations of the present application can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present application.
[0145] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.
[0146] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.
[0147] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.
[0148] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.
[0149] Embodiments of the present application have been described above, and the description is intended to be illustrative, and not restrictive, of the various embodiments of the present application. Many modifications and variations of the described embodiments of the present application are possible, given the benefit of the present disclosure, without departing from the scope and spirit of the described embodiments of the present application. The scope of the present application is defined by the appended claims.
Claims
1. A target detection method of an infrared image, characterized by, The method comprises: acquiring a target pixel point and a background pixel point in the infrared image; obtaining a first pixel point set and a second pixel point set according to the target pixel point and the background pixel point; the pixel points in the first pixel point set are pixel points with pixel values close to that of the target pixel point, and the pixel points in the second pixel point set are pixel points with pixel values greater than that of the background pixel point; determining a target object in the infrared image according to the first pixel point set and the second pixel point set.
2. The method of claim 1, wherein, The pixel points in the first pixel point set are at a first set distance from the target pixel point, the pixel points in the second pixel point set are at a second set distance from the target pixel point, the first set distance is less than the second set distance, and the distance difference between the second set distance and the first set distance is greater than or equal to 2 pixel points.
3. The method of claim 1, wherein, The determination of the target object in the infrared image according to the first pixel point set and the second pixel point set comprises: determining a first pixel difference value between the pixel points in the first pixel point set and the target pixel point; determining a second pixel difference value between the pixel points in the second pixel point set and the background in the infrared image; determining a target pixel point with the first pixel difference value and the second pixel difference value meeting a set condition as a boundary pixel point; determining the target object in the infrared image according to the boundary pixel point.
4. The method of claim 3, wherein, The first pixel difference value is a difference value between a maximum pixel value of the first pixel point set and a first set reference value; and the second pixel difference value is a difference value between a median pixel value of the second pixel point set and a second set reference value.
5. The method of claim 4, wherein, The determination of the target pixel point with the first pixel difference value and the second pixel difference value meeting the set condition as the boundary pixel point comprises: determining a target pixel point with the maximum pixel value of the first pixel point set greater than or equal to the first set reference value and the median pixel value of the second pixel point set less than or equal to the second set reference value as the boundary pixel point.
6. The method of claim 4, wherein, The first set reference value is related to a first fixed value and the pixel value of the target pixel point, and the second set reference value is related to a second fixed value and the pixel value of the target pixel point; the first fixed value and the second fixed value correspond to different multiples of a set pixel range.
7. The method according to any one of claims 3 to 6, characterized in that, Before the determination of the target object in the infrared image according to the boundary pixel point, the method comprises: setting the pixel value of the boundary pixel point in the infrared image as a first numerical value, and setting the pixel value of a non-boundary pixel point in the infrared image as a second numerical value to generate a boundary image.
8. The method of claim 7, wherein, The determination of the target object in the infrared image according to the boundary pixel point comprises: comparing the boundary image with the infrared image to determine reliable pixel points in the infrared image; determining the target object in the infrared image according to the reliable pixel points.
9. The method of claim 7, wherein, The first numerical value is a difference value between the pixel value of the boundary pixel point in the infrared image and a corresponding median pixel value; and the second numerical value is a set value.
10. The method of claim 8, wherein, The comparing the boundary image with the infrared image to determine reliable pixel points in the infrared image comprises: determining a first normalized value of the boundary image, and determining a second normalized value of the infrared image; in a case where the first normalized value is greater than or equal to the second normalized value, determining a reliable pixel point.
11. The method of claim 8, wherein, The determining a target object in the infrared image according to the reliable pixel points comprises: determining a target object in the infrared image according to the boundary image and the reliable pixel points.
12. The method of claim 11, wherein, The determining a target object in the infrared image according to the boundary image and the reliable pixel points comprises: determining a third pixel set of the reliable pixel points; wherein the third pixel set is a set of pixel points in the reliable pixel points and the pixel points in the boundary image within a third set distance; wherein the third set distance is greater than or equal to the shortest distance between the reliable pixel points and the boundary of the target object; constructing a target object in the infrared image according to the third pixel set.
13. An apparatus for target detection of an infrared image, characterized by comprising: The apparatus comprises: an acquisition module configured to acquire target pixel points and background pixel points in the infrared image, and to obtain a first pixel point set and a second pixel point set according to the target pixel points and the background pixel points; the pixel points in the first pixel point set are pixel points with pixel values close to the pixel values of the target pixel points, and the pixel points in the second pixel point set are pixel points with pixel values greater than the pixel values of the background pixel points; a determination module configured to determine a target object in the infrared image according to the first pixel point set and the second pixel point set.
14. An electronic device, comprising: The apparatus comprises a memory and a processor, the memory is configured to store a computer program, and the processor is configured to execute the computer program to implement the method according to any one of claims 1 to 12.
15. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the method according to any one of claims 1 to 12.
16. A computer program product, characterised in that, The computer program is executed by a processor to implement the method according to any one of claims 1 to 12.
17. A vehicle characterized by comprising: The apparatus comprises the infrared image target detection apparatus according to claim 13 or the electronic device according to claim 14.