Target detection system for night vision and night vision target detection method

Abstract

The invention relates to a target detection system for night vision. The target detection system comprises active infrared night vision equipment, thermal imaging equipment and an image generation unit, the active infrared night vision device performs clear imaging on an object within a preset first distance and performs fuzzy imaging on an object outside the first distance; the thermal imaging equipment performs clear imaging on objects beyond the first distance and performs fuzzy imaging on objects within the first distance; an image generation unit performs image recognition based on definition information in an imaging image of the thermal imaging equipment so as to recognize a target area corresponding to the area beyond the first distance; and calculating the position information of the target object based on the assumption that the target area is located on the plane perpendicular to the optical axis at the first distance, and outputting a mark corresponding to the position information to a blank display area above an imaging picture of the active infrared night vision equipment for display. According to the invention, the driving safety can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile night vision, and in particular to a target detection system and method for night vision that combines active infrared night vision and thermal imaging technology. Background Art

[0002] Existing night vision technologies are primarily categorized into active infrared night vision and passive thermal imaging. Active infrared night vision creates images by emitting infrared beams and receiving the reflected echo from the target. It can achieve very high resolution and rich details at medium and short distances (e.g., within 200 meters). However, its range is limited by the power of the infrared illuminator and is susceptible to interference from environmental factors such as smoke, fog, and haze.

[0003] Thermal imaging technology creates images by passively receiving infrared radiation emitted by an object itself. It is not restricted by lighting conditions, has a strong ability to penetrate smoke, and has a long detection distance of 300 meters or more.

[0004] Simultaneously viewing the black-and-white imagery from active infrared night vision and the color thermal imagery from thermal imaging technology requires a high level of attention from the driver, making it easy to miss key details in either image, leading to accidents. Furthermore, existing image fusion technologies are incapable of effectively integrating these two images, and require enormous computational effort. Summary of the Invention

[0005] In view of the above problems, the present invention proposes a target detection system for night vision, which is characterized by comprising: Active infrared night vision equipment, thermal imaging equipment and image generation units; The active infrared night vision device is located on the inside of the car's windshield, and the thermal imaging device is located on the outside of the car's windshield. The active infrared night vision device and the thermal imaging device are both located on the transverse symmetrical centerline of the car, and are placed adjacent to each other in a direction perpendicular to the ground, with their optical axes parallel to each other. The active infrared night vision device is configured to produce clear images of objects within a preset first distance and produce blurred images of objects outside the first distance; The thermal imaging device is configured to produce a clear image of an object outside the first distance and a blurred image of an object within the first distance; An image generation unit is connected to the thermal imaging device and the active infrared night vision device and is configured to: perform image recognition based on clarity information in the imaging image of the thermal imaging device to identify a target area corresponding to a target area outside the first distance; and based on the assumption that the target area is located on a plane perpendicular to the optical axis at the first distance, determine whether there are one or more target objects within the target area that are within a second distance range from the optical axis of the thermal imaging device; if so, calculate the position information of the target object based on the assumption, and output a mark corresponding to the position information to a blank display area above the imaging screen of the active infrared night vision device for display, so as to achieve image synthesis.

[0006] According to some embodiments of the present invention, the optical system of the thermal imaging device is a fixed-focus lens, and half of the hyperfocal distance of the lens is set to be equal to the first distance.

[0007] According to some embodiments of the present invention, the image generation unit identifies the target area by the following steps: Segmenting an image formed by a thermal imaging device into a plurality of analysis grids; For each analysis grid, apply the Laplace operator to calculate its variance value; An analysis grid having a variance value greater than a threshold is determined as the target area.

[0008] According to some embodiments of the present invention, the image generation unit calculates the position information in the following manner: detecting the edge of the target object on the side close to the center line of the thermal imaging device within the target area, obtaining its deviation pixel value in the image coordinate system, and determining the position information through a trigonometric function relationship based on the deviation pixel value, the preset field of view angle parameter of the thermal imaging device and the first distance.

[0009] According to some embodiments of the present invention, the active infrared night vision device includes an infrared laser illuminator and a near-infrared image sensor, and the illumination range of the illuminator matches the field of view angle of the sensor.

[0010] According to some embodiments of the present invention, the active infrared night vision device pre-identifies the edges of both sides of the road, and accordingly draws the road extension line in advance in the blank area.

[0011] The present application also proposes a night vision target detection method based on the target detection system for night vision, which includes: Using an active infrared night vision device, objects within a preset first distance are imaged clearly, and objects outside the first distance are imaged fuzzily; Using a thermal imaging device, a clear image is taken of an object outside the first distance, and a blurred image is taken of an object within the first distance; An image generation unit performs image recognition based on clarity information in the imaging image of the thermal imaging device to identify a target area corresponding to a target area outside the first distance; and based on the assumption that the target area is located on a plane perpendicular to the optical axis at the first distance, determines whether there are one or more target objects within the target area that are within a second distance range from the optical axis of the thermal imaging device; if so, calculates the position information of the target object based on the assumption, and outputs a mark corresponding to the position information to a blank display area above the imaging screen of the active infrared night vision device for display, so as to achieve image synthesis.

[0012] According to some embodiments of the present invention, the image generation unit identifies the target area by the following steps: Segmenting an image formed by a thermal imaging device into a plurality of analysis grids; For each analysis grid, apply the Laplace operator to calculate its variance value; An analysis grid having a variance value greater than a threshold is determined as the target area.

[0013] According to some embodiments of the present invention, the image generation unit calculates the position information in the following manner: detecting the target object within the target area and obtaining its deviation pixel value in the image coordinate system, and determining the position information through a trigonometric function relationship based on the deviation pixel value, the preset field of view angle parameter of the thermal imaging device and the first distance.

[0014] According to some embodiments of the present invention, the active infrared night vision device pre-identifies the edges of the road and pre-draws road extension lines in the blank areas accordingly. This allows the user to simultaneously perceive the distance of the subsequent markings relative to the road sides when the markings are displayed.

[0015] Through the present invention, the operator can observe distant dangerous situations and close targets at the same time without switching viewing screens, effectively solving the problem that the operator is easily distracted while driving and cannot pay enough attention to the screens when viewing multiple screens, thereby improving driving safety.

[0016] Moreover, the present invention avoids complex focusing mechanisms and distance measurement algorithms, simplifies the system structure, reduces power consumption and computing resources, and improves the reliability of long-distance target screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A block diagram illustrating a target detection system for night vision according to some embodiments of the present invention.

[0019] Figure 2 A diagram illustrating the distribution of active infrared night vision devices and thermal imaging devices in front of and behind a windshield of a target detection system for night vision according to some embodiments of the present invention.

[0020] Figure 3 A view on a thermal imaging device of a target detection system for night vision according to some embodiments of the present invention is shown.

[0021] Figure 4 A diagram illustrating image distribution on an active infrared night vision device of a target detection system for night vision according to some embodiments of the present invention is shown.

[0022] Figure 5 A flowchart of a night vision target detection method according to some embodiments of the present invention is shown. DETAILED DESCRIPTION

[0023] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. These embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of this application may be combined and referenced with each other. In addition, the described embodiments are only some embodiments of the present invention, rather than all embodiments.

[0024] It should be understood that the terms used herein are for the purpose of describing specific example embodiments only and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. For any component, data or structure mentioned in the embodiments of the present application, in the absence of clear definition or contrary revelation given in the preceding and following text, it can generally be understood to be one or more. "Multiple" may refer to two or more. The terms "comprise", "include", "contain" and "have" are inclusive and therefore indicate the presence of the stated features, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof.

[0025] In addition, the term "and / or" in this application is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this application generally indicates that the related objects are in an "or" relationship.

[0026] Figure 1 FIG. 1 is a block diagram of a target detection system for night vision according to some embodiments of the present invention. Figure 1 As shown, the target detection system 100 for night vision of the present invention includes an active infrared night vision device 101, a thermal imaging device 102 and an image generation unit 103. The active infrared night vision device 101 and the thermal imaging device 102 are connected to the image generation unit 103 via a data line.

[0027] Figure 2 FIG. 1 shows a distribution diagram of active infrared night vision devices and thermal imaging devices in front of and behind a windshield according to a target detection system for night vision according to some embodiments of the present invention. Figure 2 As shown, the active infrared night vision device 101 is mounted on the inside of the vehicle's windshield 200 (201 represents the vehicle's roof), and the thermal imaging device 102 is mounted on the outside of the windshield 200. Both the active infrared night vision device and the thermal imaging device are located on the vehicle's transversely symmetrical centerline, placed adjacent to each other perpendicular to the ground, with their optical axes 204 and 203 parallel to each other. In the figure, both mounting surfaces are placed in close contact with the glass.

[0028] Figure 3 1 shows a view on a thermal imaging device of a target detection system for night vision according to some embodiments of the present invention. The active infrared night vision device is configured to clearly image objects within a preset first distance and to blur objects outside the first distance. Figure 3 As shown, the red squares 300 and 301 both correspond to objects within a preset first distance, which are clearly imaged relative to the surrounding objects. However, the rightmost edge of the red square 300 (i.e., the edge on the side close to the center line of the thermal imaging device) is within a preset second distance from the center line of the image. Therefore, the mark corresponding to the square 300 will be displayed Figure 4 See Figure 4 circle.

[0029] The active infrared night vision device 101 may include, for example, a laser illuminator and a near-infrared CMOS sensor, with the illumination range matching the sensor's field of view. Its lens supports fast autofocus within a range of 5-200 meters.

[0030] The thermal imaging device is configured to perform clear imaging of objects outside the first distance and perform blurred imaging of objects within the first distance.

[0031] The thermal imaging device 102 may, for example, use a vanadium oxide long-wave infrared detector with a resolution of 640x512 and a fixed-focus chrome lens. Half of the hyperfocal distance of the lens is precisely set to 200 meters, ensuring that objects 200 meters away are clearly imaged, while objects within 200 meters are relatively blurred.

[0032] An image generation unit is connected to the thermal imaging device and the active infrared night vision device and is configured to: perform image recognition based on clarity information in the imaging image of the thermal imaging device to identify a target area corresponding to a target area outside the first distance; and based on the assumption that the target area is located on a plane perpendicular to the optical axis at the first distance, determine whether there are one or more target objects within the target area that are within a second distance range from the optical axis of the thermal imaging device; if so, calculate the position information of the target object based on the assumption, and output a mark corresponding to the position information to a blank display area above the imaging screen of the active infrared night vision device for display, so as to achieve image synthesis.

[0033] According to some embodiments of the present invention, assuming that the first distance is 200 meters and the second distance is 1.5 meters, the thermal imaging device may use a vanadium oxide long-wave infrared detector with a resolution of 640x512.

[0034] The image generation unit processing flow is as follows: (1) Divide the 640x512 thermal imaging image into 16x12 analysis grids (i.e., each grid is 40x42.6 pixels).

[0035] (2) For each grid, the Laplace variance of its image is calculated in real time. For example, at time t, it is found that the variance value of grid (8, 5) is greater than a threshold.

[0036] (3) Determine grid (8, 5) as the “clearer target area” and assume its distance is 200 meters.

[0037] (4) Within the grid, a pixel cluster (target) with the highest brightness is detected, and its horizontal coordinate close to the optical axis is Px=330 pixels.

[0038] (5) The horizontal field of view of the thermal imaging lens is θ = 20°, and the horizontal pixel W = 640. The central axis is at 320 pixels.

[0039] (6) Calculate target distance: Number of pixels deviating from the central axis: ΔP = |330-320| = 10 pixels Angle of deviation from the central axis: β = ΔP × (θ / W) = 10 × (20 / 640) = 0.31° Second distance: A = 200 m × tan(β) ≈ 1.08 m (7) Similarly, the image generation unit further converts the position A = 1.08 meters into the corresponding position on the active infrared night vision device and displays it in the central blank position at the top of the display screen. It should be understood that the above-mentioned sensor resolution, number of grid divisions, and specific calculation parameters are only a preferred example of the present invention. Those skilled in the art may adopt other clarity evaluation algorithms (such as gradient function, frequency domain analysis, etc.) and target detection methods according to actual needs. Such variations fall within the scope of protection of the present invention.

[0040] When using this device, users can Figure 4 The user can see a pedestrian within 200 meters (via active infrared) and the top of the display will indicate that there is a target about 1.08 meters to the left of the center line of sight 200 meters away. This allows the user to take precautions and respond to potential threats from a distance.

[0041] In the present invention, it is assumed that the target dangerous objects in all clear areas are located on the vertical plane of the optical axis at 200 meters. In actual situation, they may be distributed at 300 meters. However, the present invention can display the danger at 300 meters to the user in advance through this method, which is an amplification and early warning of the dangerous situation at 300 meters, because it may only take a few seconds to travel from 200 meters to 300 meters, and warning the user in advance of the danger that may appear in these few seconds can greatly improve driving safety.

[0042] According to some embodiments of the present invention, the optical system of the thermal imaging device is a fixed-focus lens, and half of the hyperfocal distance of the lens is set to be equal to the first distance.

[0043] According to some embodiments of the present invention, the image generation unit identifies the target area by the following steps: Segmenting an image formed by a thermal imaging device into a plurality of analysis grids; For each analysis grid, apply the Laplace operator to calculate its variance value; An analysis grid having a variance value greater than a threshold is determined as the target area.

[0044] According to some embodiments of the present invention, the image generation unit calculates the position information in the following manner: detecting the rightmost edge of the target object within the target area, obtaining its deviation pixel value in the image coordinate system, and determining the position information through a trigonometric function relationship based on the deviation pixel value, the preset field of view angle parameter of the thermal imaging device and the first distance.

[0045] According to some embodiments of the present invention, the active infrared night vision device includes an infrared laser illuminator and a near-infrared image sensor, and the illumination range of the illuminator matches the field of view angle of the sensor.

[0046] According to some embodiments of the present invention, the active infrared night vision device pre-identifies the edges of the road and pre-draws road extension lines in the blank areas accordingly. This allows the user to simultaneously perceive the distance of the subsequent markings relative to the road sides when the markings are displayed.

[0047] This application also proposes a night vision target detection method based on the target detection system for night vision, such as Figure 5 As shown, it includes the following steps: S1. Clearly image objects within a preset first distance through active infrared night vision equipment, and blur objects outside the first distance; S2. Using a thermal imaging device to clearly image objects outside the first distance and to blur objects within the first distance; S3. Perform image recognition based on the clarity information in the imaging image of the thermal imaging device through the image generation unit to identify the target area corresponding to the area outside the first distance; and based on the assumption that the target area is located on a plane perpendicular to the optical axis at the first distance, determine whether there are one or more target objects within the target area that are within the second distance range from the optical axis of the thermal imaging device; if so, calculate the position information of the target object based on the assumption, and output the mark corresponding to the position information to the blank display area above the imaging screen of the active infrared night vision device for display, so as to realize image synthesis.

[0048] According to some embodiments of the present invention, the image generation unit identifies the target area by the following steps: Segmenting an image formed by a thermal imaging device into a plurality of analysis grids; For each analysis grid, apply the Laplace operator to calculate its variance value; An analysis grid having a variance value greater than a threshold is determined as the target area.

[0049] According to some embodiments of the present invention, the image generation unit calculates the position information in the following manner: detecting the target object within the target area and obtaining its deviation pixel value in the image coordinate system, and determining the position information through a trigonometric function relationship based on the deviation pixel value, the preset field of view angle parameter of the thermal imaging device and the first distance.

[0050] According to some embodiments of the present invention, the active infrared night vision device pre-identifies the edges of the road and pre-draws road extension lines in the blank areas accordingly. This allows the user to simultaneously perceive the distance of the subsequent markings relative to the road sides when the markings are displayed.

[0051] Through the present invention, the operator can observe distant dangerous situations and close targets at the same time without switching viewing screens, effectively solving the problem that the operator is easily distracted while driving and cannot pay enough attention to the screens when viewing multiple screens, thereby improving driving safety.

[0052] Moreover, the present invention avoids complex focusing mechanisms and distance measurement algorithms, simplifies the system structure, reduces power consumption and computing resources, and improves the reliability of long-distance target screening.

[0053] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A target detection system for night vision, characterized in that: include: Active infrared night vision equipment, thermal imaging equipment and image generation units; The active infrared night vision device is located on the inside of the car's windshield, and the thermal imaging device is located on the outside of the car's windshield. The active infrared night vision device and the thermal imaging device are both located on the transverse symmetrical centerline of the car, and are placed adjacent to each other in a direction perpendicular to the ground, with their optical axes parallel to each other. The active infrared night vision device is configured to produce clear images of objects within a preset first distance and produce blurred images of objects outside the first distance; The thermal imaging device is configured to produce a clear image of an object outside the first distance and a blurred image of an object within the first distance; an image generation unit connected to the thermal imaging device and the active infrared night vision device and configured to: perform image recognition based on clarity information in the imaged image of the thermal imaging device to identify a target area corresponding to a region outside the first distance; Based on the assumption that the target area is located on a plane perpendicular to the optical axis at the first distance, it is determined whether there are one or more target objects in the target area that are within the second distance range from the optical axis of the thermal imaging device. If so, the position information of the target object is calculated based on the assumption, and the mark corresponding to the position information is output to the blank display area above the imaging screen of the active infrared night vision device for display, so as to realize image synthesis.

2. The target detection system for night vision according to claim 1, characterized in that: The optical system of the thermal imaging device is a fixed focal length lens, and half of the hyperfocal distance of the lens is set to be equal to the first distance.

3. The target detection system for night vision according to claim 1, characterized in that: The image generation unit identifies the target area by the following steps: Segmenting an image formed by a thermal imaging device into a plurality of analysis grids; For each analysis grid, apply the Laplace operator to calculate its variance value; An analysis grid having a variance value greater than a threshold is determined as the target area.

4. The target detection system for night vision according to claim 1, characterized in that: The image generation unit calculates the position information in the following manner: detecting an edge of the target object on a side close to the center line of the thermal imaging device within the target area, obtaining its deviation pixel value in the image coordinate system, and determining the position information through a trigonometric function relationship based on the deviation pixel value, a preset field of view angle parameter of the thermal imaging device, and the first distance.

5. The target detection system for night vision according to claim 1, characterized in that: The active infrared night vision device includes an infrared laser illuminator and a near-infrared image sensor, and the illumination range of the illuminator matches the field of view angle of the sensor.

6. The target detection system for night vision according to claim 1, characterized in that: The active infrared night vision device pre-identifies the edges of both sides of the road and accordingly draws the road extension line in advance in the blank area.

7. A night vision target detection method based on the target detection system for night vision according to any one of claims 1 to 6, characterized in that: include: Using an active infrared night vision device, objects within a preset first distance are imaged clearly, and objects outside the first distance are imaged fuzzily; Using a thermal imaging device, a clear image is taken of an object outside the first distance, and a blurred image is taken of an object within the first distance; performing image recognition based on clarity information in the imaged image of the thermal imaging device by an image generating unit to identify a target area corresponding to a region outside the first distance; Based on the assumption that the target area is located on a plane perpendicular to the optical axis at the first distance, it is determined whether there are one or more target objects in the target area that are within the second distance range from the optical axis of the thermal imaging device. If so, the position information of the target object is calculated based on the assumption, and the mark corresponding to the position information is output to the blank display area above the imaging screen of the active infrared night vision device for display, so as to realize image synthesis.

8. The night vision target detection method according to claim 7, characterized in that: The image generation unit identifies the target area by the following steps: Segmenting an image formed by a thermal imaging device into a plurality of analysis grids; For each analysis grid, apply the Laplace operator to calculate its variance value; An analysis grid having a variance value greater than a threshold is determined as the target area.

9. The night vision target detection method according to claim 7, characterized in that: The image generation unit calculates the position information in the following manner: detecting the target object within the target area and obtaining its deviation pixel value in the image coordinate system, and determining the position information through a trigonometric function relationship based on the deviation pixel value, a preset field of view angle parameter of the thermal imaging device and the first distance.

10. The night vision target detection method according to claim 7, characterized in that: The active infrared night vision device pre-identifies the edges of both sides of the road and accordingly draws the road extension line in advance in the blank area.

Images