System and method for detecting proper seat belt usage and distance

Abstract

A system and method for detecting seat belt positioning includes capturing a near-infrared (NIR) image of an occupant by a camera, applying a median filter to the NIR image to remove glares, converting the NIR image to a black and white image, scanning the black and white (B / W) image to detect a plurality of transitions between black and white segments corresponding to stripes extending longitudinally along a length of the seat belt, and using the detection of the plurality of transitions to indicate detection of the seat belt. Converting the NIR image to the B / W image can include determining whether a given pixel in the B / W image should be black or white using a local binary threshold based on whether the corresponding source pixel within the NIR image is brighter than an average of nearby pixels within a predetermined distance of the corresponding source pixel.

Description

[0001] Cross-references to related applications

[0002] This PCT international patent application claims the benefit of U.S. Patent Application No. 17 / 343,366, filed June 9, 2021, the entire contents of which are incorporated herein by reference. Background Technology 1. Technical Field

[0004] The present invention generally relates to systems and methods for using visual systems such as near-infrared (NIR) cameras to detect correct seatbelt use and distance to occupants.

[0005] 2. Related fields

[0006] Cameras and other image detection devices have been used to detect one or more objects. A control system communicating with these cameras can receive and process images captured by the cameras. This image processing can include detecting one or more objects found in the captured images. Based on these detected objects, the control system can perform some type of action in response to these detected variables.

[0007] Conventional systems for detecting seatbelt use typically rely on seatbelt buckle switches. However, these conventional systems cannot detect whether the seatbelt is correctly positioned or whether the buckle is tampered with. Seat track sensors are commonly used to determine the distance to a vehicle occupant. However, this use of seat track sensors does not take into account the occupant's body position relative to the seat. Summary of the Invention

[0008] In one example, a method for detecting seatbelt positioning includes capturing a near-infrared (NIR) image of an occupant using a camera. The method further includes converting the NIR image to a black-and-white image; scanning the black-and-white image to detect multiple transitions between black and white segments corresponding to stripes extending longitudinally along the length of the seatbelt; and using the detection of these multiple transitions to indicate seatbelt detection.

[0009] In another example, a system for detecting seatbelt positioning includes a seatbelt having a plurality of stripes extending longitudinally along its length, the stripes arranged in an alternating pattern of bright and dark in the near-infrared. The system also includes: a camera configured to capture a near-infrared (NIR) image of an occupant wearing the seatbelt; and a processor communicating with the camera and programmed to receive the NIR image of the occupant wearing the seatbelt and determine the seatbelt's position based on detecting transitions corresponding to changes in the alternating pattern of the stripes.

[0010] Other objects, features, and advantages of the invention will become apparent to those skilled in the art upon viewing the following description with reference to the accompanying drawings and claims, which are attached to and form part of this specification. Attached Figure Description

[0011] Figure 1 A vehicle with a system for detecting correct seatbelt use and a distance for detecting the seatbelt is shown;

[0012] Figure 2 A front view of the passenger compartment of a vehicle is shown, illustrating a system for detecting correct seatbelt use and the distance at which the seatbelt is detected.

[0013] Figure 3 A block diagram of a system for detecting correct seatbelt use and for detecting the distance of the seatbelt is shown;

[0014] Figure 4 shows a first example of improper seatbelt positioning;

[0015] Figure 5 shows a second example of improper seatbelt positioning;

[0016] Figure 6 shows a third example of improper seatbelt positioning;

[0017] Figure 7A A near-infrared (NIR) image of a person wearing a seatbelt is shown according to one aspect of this disclosure;

[0018] Figure 7B The following is illustrated based on the present disclosure: Figure 7A Filtered NIR image;

[0019] Figure 7C The following is illustrated based on the present disclosure: Figure 7A Black and white images of NIR images;

[0020] Figure 7D The following is illustrated based on the present disclosure: Figure 7A The NIR image shows the image of the detection point;

[0021] Figure 8A A magnified section of the NIR image is shown;

[0022] Figure 8B It shows Figure 8A The filtered image of the magnified section;

[0023] Figure 9 A close-up NIR image of a seatbelt with an asymmetrical striped pattern according to the present disclosure is shown;

[0024] Figure 10 The following is shown in accordance with this disclosure: Figure 7C A magnified section of the black and white image, including the seatbelt and showing the horizontal scan lines;

[0025] Figure 11 The following is shown in accordance with this disclosure: Figure 7D The magnified section of the image shows the detection angle of the seatbelt; and

[0026] Figure 12 A flowchart is shown listing the steps in a method for detecting seatbelt positioning. Detailed Implementation

[0027] See Figure 1 The diagram illustrates a vehicle 10 with a seatbelt detection system 12 for detecting correct seatbelt use and / or for detecting the distance to the seatbelt. In this example, the seatbelt detection system 12 is integrated into the vehicle 10. However, it should be understood that the seatbelt detection system 12 can be a separate system independent of the vehicle 10. In some embodiments, the seatbelt detection system 12 may use some or all of the components present in the vehicle 10 for other systems and / or for other purposes, such as driver monitoring in advanced driver assistance systems (ADAS). Therefore, the seatbelt detection system 12 of this disclosure can be implemented with very low additional cost.

[0028] For vehicle 10, vehicle 10 in Figure 1 The vehicle 10 is shown as a passenger car. However, it should be understood that vehicle 10 can be any type of vehicle capable of transporting people or goods from one location to another. Thus, in addition to passenger cars, vehicle 10 can also be a light truck, a heavy truck, a tractor-trailer, a tractor unit, a mining vehicle, etc. Furthermore, it should be understood that vehicle 10 is not limited to wheeled vehicles, but can also include non-wheeled vehicles, such as aircraft and boats. Moreover, the term "vehicle" should be understood broadly to include any type of vehicle capable of transporting people or goods from one location to another, and it should not be limited to the specific examples listed above.

[0029] See Figure 2 The diagram shows the carriage 14 of vehicle 10. As is known in the art, carriage 14 is essentially the interior of vehicle 10, in which occupants and / or cargo are located when the vehicle is in motion. The carriage 14 of the vehicle may be defined by one or more pillars that structurally define the carriage 14. For example, in Figure 2 The image shows column A 16A and column B 16B. Figure 1It is also shown that a third pillar or C-pillar 16C may be present. Of course, it should be understood that vehicle 10 may include any one of a plurality of pillars to define the passenger compartment 14. In addition, it should be understood that vehicle 10 may be designed to remove these pillars, thereby substantially forming an open passenger compartment 14 such as that commonly found in automobiles with convertible roofs.

[0030] Seats 18A and 18B are located inside carriage 14. Seats 18A and 18B are configured to support the occupants of vehicle 10. Vehicle 10 may have any number of seats. Furthermore, it should be understood that vehicle 10 may not have any seats at all.

[0031] Vehicle 10 may have one or more cameras 20A-20F serving as part of a vision system, these cameras being positioned and mounted on vehicle 10 to have a field of view of at least a portion of the passenger compartment 14. Thus, cameras 20A-20F can have a field of view of occupants seated in seats 18A and / or 18B. Here, cameras 20A and 20C are located on A-pillar 16A. Camera 20B is located on rearview mirror 22. Camera 20D may be located on dashboard 24 of vehicle 10. Cameras 20E and 20F can focus on the driver and / or occupants and may be adjacent to the vehicle instrument cluster 21 or steering wheel 23, respectively. It should be understood that any one of a plurality of different cameras may be used. Thus, it should be understood that only one camera may be used or multiple cameras may be used. Furthermore, cameras 20A-20F may be positioned and mounted anywhere in vehicle 10, as long as at least a portion of the passenger compartment 14 is visible.

[0032] Cameras 20A-20F can be any type of camera capable of capturing visual information. This visual information can be information within the visible spectrum, but it can also be information outside the visible spectrum, such as infrared or ultraviolet light. Here, cameras 20A-20F are near-infrared (NIR) cameras capable of capturing images produced by the reflection of near-infrared light. Near-infrared light can include any light in the near-infrared range of the electromagnetic spectrum (from 780 nm to 2500 nm). However, the seatbelt detection system 12 of this disclosure can be configured to use a specific wavelength or wavelength range within the near-infrared range.

[0033] The source of the near-infrared light can be a natural source, such as the sun, but it can also be an artificial source, such as the near-infrared light source 26. The near-infrared light source 26 can be installed anywhere within the passenger compartment 14 of the vehicle 10, as long as it allows near-infrared light to be projected onto at least a portion of the passenger compartment 14. Here, the near-infrared light source 26 is mounted on the rearview mirror 22, but it should be understood that the near-infrared light source 26 can be installed anywhere within the passenger compartment 14. Furthermore, it should be understood that although only one near-infrared light source 26 is shown, there can be more than one near-infrared light source 26 located within the passenger compartment 14 of the vehicle 10.

[0034] Output device 28 is also located within carriage 14 for forwarding information to one or more occupants within carriage 14. Here, output device 28 is shown in a display device to convey visual information to one or more occupants within carriage 14. However, it should be understood that output device 28 can be any output device capable of providing information to one or more occupants within carriage 14. Thus, for example, the output device could be an audio output device providing audio information to one or more occupants within carriage 14 of vehicle 10. Furthermore, it should be understood that output device 28 can be a vehicle subsystem controlling the functions of the vehicle.

[0035] See Figure 3 A more detailed illustration of the seatbelt detection system 12 is shown. Here, system 12 includes a control system 13 having a processor 30 in communication with a memory 32 containing instructions 34 for performing any of the various methods disclosed herein. The processor 30 may include a single, independent processor, or it may include two or more processors distributed across multiple systems operating together. The memory 32 may be any type of memory capable of storing digital information. For example, the memory may be solid-state memory, magnetic memory, optical memory, etc. Furthermore, it should be understood that the memory 32 may be incorporated into the processor 30 or, as shown, may be separate from the processor 30.

[0036] The processor 30 can also communicate with the camera 20. The camera 20 can communicate with... Figure 2 The cameras shown and described are the same as the 20A-20F. Similar to... Figure 2 Cameras 20A-20F in the diagram, camera 20 can be a near-infrared camera. Camera 20 may include multiple physical devices, such as... Figure 2 The cameras shown are 20A-20F. Camera 20 has a field of view 21.

[0037] The near-infrared light source 26 can also communicate with the processor 30. When enabled by the processor 30, the near-infrared light source 26 projects near-infrared light 36 onto an object 38, which may absorb the near-infrared light or reflect the near-infrared light 40 toward the camera 20, whereby the camera can capture an image showing the absorbed or reflected near-infrared light 40. These images can then be provided to the processor 30.

[0038] The processor 30 can also communicate with the output device 28. The output device 28 may include devices capable of sending data to... Figure 2The output device 28 provides information to one or more occupants within the carriage 14 via visual and / or auditory output devices. Additionally, it should be understood that the output device 28 may be a vehicle system, such as a safety system that can take certain actions based on input received from the processor 30. For example, the processor 30 may instruct the output device 28 to restrict... Figure 1 The functions of the vehicle 10 may be reduced or minimized. As will be explained later in this specification, one of the functions that the seatbelt detection system 12 can perform is to detect whether the occupant is wearing the seatbelt correctly. If the seatbelt is not worn correctly, the processor 30 may instruct the output device 28 to limit the functions of the vehicle 10, so that the vehicle 10 can only travel at a greatly reduced speed.

[0039] Figure 4 illustrates a first example of improper seatbelt positioning, showing an improperly adjusted seatbelt 50 on an occupant 44 seated in seat 18A of vehicle 10. In this example, the improperly adjusted seatbelt 50 is loosely draped over the shoulder of occupant 44. Figure 5 illustrates a second example of improper seatbelt positioning, showing the seatbelt 50 passing under the armpit of occupant 44. Figure 6 illustrates a third example of improper seatbelt positioning, showing the seatbelt 50 passing behind occupant 44. The seatbelt detection system can detect other examples of improper seatbelt positioning, such as a missing seatbelt or a seatbelt not being worn by occupant 44, even in cases where the buckle is tampered with (e.g., by inserting the seatbelt into the buckle to place it behind occupant 44 or by placing a foreign object in the buckle latch).

[0040] Figure 7A A near-infrared (NIR) image of an occupant 44 wearing a seatbelt 50 according to one aspect of this disclosure is shown. This can represent an image captured by camera 20 and received by processor 30. In some embodiments, occupant 44 may be the driver of vehicle 10. However, occupant 44 may also be a passenger in vehicle 10. Figure 7B It shows the basis Figure 7A Filtered NIR image; Figure 7C It shows the basis Figure 7A Black and white images of NIR images; and Figure 7D The following is illustrated based on the present disclosure: Figure 7A The NIR image shows the image of the detection points. Specifically, Figure 7DThe seatbelt 50 is shown passing through each of a first region of interest (ROI) 60 and a second ROI 62. The first ROI 60 may be located above the shoulders of the occupant 44, and the second ROI 62 may be located below and to the left of the first ROI. The second ROI 62 may correspond to the central region of the torso of the occupant 44. ROIs 60 and 62 may each have a fixed position within the field of view 21 of the camera 20. Alternatively, the system 12 may adjust the position of one or both of the ROIs 60 and 62 based on the position of the occupant 44 detected within the field of view 21 of the camera 20.

[0041] Figure 8A A magnified section of the NIR image (including a portion of occupant 44) is shown, and Figure 8B It shows Figure 8A The filtered image of the magnified section. Figures 8A to 8B The removal of flashes, which appear as small, bright areas in the NIR image, is illustrated. In this example, the flash is located on an earring worn by occupant 44. However, flashes can originate from other sources, such as worn threads, lint, or other materials. The presence of flashes on or near the seatbelt 50 could potentially interfere with subsequent processing steps and reduce the effectiveness of the seatbelt detection system 12 in its proper operation.

[0042] Figure 9 A close-up NIR image of a seatbelt 50 with an asymmetrical striped pattern according to the present disclosure is shown. Specifically, the seatbelt 50 includes a plurality of stripes 68a-68g extending longitudinally along the length of the seatbelt 50. The stripes 68a-68g have alternating high and low brightness in the NIR image. The seatbelt 50 shown includes seven (7) stripes 68a-68g. However, the seatbelt 50 may have fewer or more stripes 68a-68g. The stripes 68a-68g are arranged in an asymmetrical pattern, and each stripe in the stripes 68a-68g has a corresponding width W in a direction perpendicular to the longitudinal dimension of the seatbelt 50. a -W g The width W of stripes 68a-68g a -W g The total width Wt of the seatbelt is 50. Stripes 68a-68g include two outermost stripes 68a, 68g surrounding a plurality of inner stripes 68b-68f, which together define the total inner width Wti. The width W of stripes 68a-68g is... a -W gThe pattern can be irregular, which reduces variations in the system 12 with false positive detection. More specifically, the widths Wb-Wf of the inner stripes 68b-68f can have an irregular pattern to reduce the chance of false positive detection. False positive detection can be any detection of a pattern that matches the pattern produced on the seat belt 50 by the camera 20 imaging objects other than the seat belt 50.

[0043] Stripes 68a-68g may be a feature of the material woven or otherwise constructed to form the seat belt 50. The material forming stripes 68a-68g may extend throughout the entire seat belt 50, so that stripes 68a-68g are visible on either of the two opposite sides of the seat belt 50. Stripes 68a-68g include an asymmetrical pattern, so the orientation of the seat belt 50 can be determined based on an image of the pattern of stripes 68a-68g. One or more twists in the seat belt 50 can be detected as a reversal of the asymmetrical pattern of stripes 68a-68g.

[0044] Figure 10 The following is shown in accordance with this disclosure: Figure 7C A magnified section of the black and white image (including seatbelt 50 and showing the horizontal scan lines). Figure 10 The diagram illustrates how system 12 scans pixel rows (horizontal lines) and searches for a series of seven consecutive segments with alternating colors, corresponding to stripes 68a-68g and separated by six transition points. The two outermost stripes 68a, 68g can have any width greater than zero pixels. In other words, they can have any width resolvable by camera 20. The outermost stripes 68a, 68g can be used to define the outer edges of the next adjacent stripes 68b, 68f. Therefore, seatbelt 50 can include five inner stripes 68b-68f surrounded by the two outermost stripes 68a, 68f. System 12 can identify seatbelt 50 based on the relative widths of the inner stripes 68b-68f. Specifically, the inner stripes 68b-68f can have corresponding widths Wb-Wf that are different from each other to define patterns with different width ratios. Figure 10 Each row of pixels shown can detect a seatbelt based on the pattern indicated at the bottom of the image. Specifically, system 12 can detect a series of one or more black pixels (b>0), followed by a series of white pixels with a scaling width of 1 unit (w1). Continuing from left to right, system 12 can further detect a black stripe 68c with a scaling width of 1 unit (b1), then a white stripe 68d with a scaling width of 4 units (w4), then a black stripe 68e with a scaling width of 2 units (b2), then a white stripe 68f with a scaling width of 1 unit (w1), and finally another series of one or more black pixels (b>0).

[0045] Figure 10 The width ratio of the inner stripes 68b-68f shown is 1:1:4:2:1; however, the inner stripes 68b-68f can have different widths to define different ratios. If the detected inner stripes 68b-68f match a ratio of 1:1:4:2:1 within a specific error tolerance, the horizontal position of the seat belt 50 within each given scan line can be marked as a detection point. In some embodiments, the cumulative width of the ratio segment of the detected event can be stored along with the detection point. Thus, the system 12 can filter out noise in a given scan line that would otherwise match a ratio of 1:1:4:2:1 but does not have a total internal width Wti within the tolerance of the total internal width Wti of the seat belt 50 detected in scan lines adjacent to or near that given scan line. The system 12 is allowed to detect the seat belt 50 using the relative ratio of the widths Wb-Wf of the corresponding inner stripes 68b-68f.

[0046] Figure 11 It shows Figure 7D The magnified section of the image shows the detection angle 70 of the seatbelt 50. Specifically, Figure 11 The diagram illustrates how system 12 identifies the seatbelt 50 and records its position as detection points 64. Once multiple detection points 64 are accumulated, the angle 70 of the seatbelt 50 can be determined. Angle 70 can represent the tilt of the seatbelt 50 in the longitudinal direction, or the difference in distance from the camera between the higher and lower portions of the seatbelt 50. Detection point 64 above the shoulder of occupant 44 within the first ROI 60 represents the higher portion of the seatbelt 50. Similarly, detection point 64 in the central region of the torso of occupant 44 within the second ROI 62 can represent the lower portion of the seatbelt 50.

[0047] Once the angle 70 is determined, the compensated pixel width can be determined using the actual width of the seatbelt 50 at detection point 64. For example, for an angle of 73 degrees, detection point 64, with a pixel width of 100 pixels (as measured by camera 20) multiplied by the sine of angle 70 (sin73°), produces a compensated pixel width of approximately 95.6 pixels. Using the known total internal width Wti of the seatbelt 50 and details from camera 20 (e.g., the arc length of pixels), the position of detection point 64 on the seatbelt 50 can be determined. This distance provides a more accurate measurement of the occupant's position compared to conventional methods such as those dependent on seat position.

[0048] Method 100 for detecting seat belt positioning Figure 12The flowchart is shown. Method 100 includes capturing an image of occupant 44 via camera 20 at step 102. Step 102 may include capturing an image in the near-infrared (NIR) spectrum, which may include detecting reflected NIR light provided by near-infrared light source 26. Step 102 may further include transmitting the image as a video stream or as one or more still images from camera 20 to control system 13 having processor 30 for additional processing.

[0049] Method 100 also includes filtering the image at step 104 to remove flash. Processor 30 may perform step 104, which may include applying a median filter to the image. The median filter can smooth out abnormally bright or dark areas (i.e., flashes) while preserving edges, which may be caused by seatbelt yarn, bad pixels in camera 20, or other noise-causing particles (such as lint stuck to seatbelt 50). Step 104 reduces the number of false detections of black / white transitions, thereby improving the performance and reliability of method 100.

[0050] Method 100 also includes converting the filtered image to black and white (B / W) at step 106. The terms black and white can include any representation of a pixel in one of two binary states representing dark or bright. Processor 30 can perform step 106, which may include using a local binary threshold to determine whether any given pixel in the B / W image should be black or white. This local binary threshold compares a source pixel in the source image (i.e., the filtered image) to neighboring pixels within a predetermined distance of that pixel. If the source pixel is brighter than the average of the neighboring pixels, the corresponding pixel in the B / W image can be set to white, and if the source pixel is darker than the average of the neighboring pixels, the corresponding pixel in the B / W image can be set to black. In some embodiments, the predetermined distance may be approximately 100 pixels. In some embodiments, the predetermined distance may be equal to or approximately equal to the pixel width of the seatbelt 50, where the seatbelt 50 is in a nominal position relative to the camera (e.g., when used by an occupant 44 of medium build sitting in the middle position of seat 18a).

[0051] Method 100 further includes scanning the B / W image at step 108 to detect black / white (or white / black) transitions and using the detection of those transitions to indicate a detection 64 of the seatbelt 50. Processor 30 may perform step 108, which may include comparing relative distances between transitions to determine whether those relative distances are related to the ratio of the widths of the internal stripes 68b-68f of the seatbelt 50, and where they are related, marking that location as a detection 64. For example, processor 30 may be programmed to scan horizontal lines in the B / W image to detect transitions to... Figure 10The internal stripes 68b-68f shown are grouped by changes in width at a 1:1:4:2:1 ratio that are matched by distances between the changes. Similarly, the processor 30 can be programmed to detect the inversion ratio of the widths of the internal stripes 68b-68f (i.e., changes separated by distances matching the 1:2:4:1:1 pattern) to detect a seatbelt 50 with an inverted orientation at a specific location.

[0052] Method 100 further includes calculating the angle of the seatbelt 50 at step 110. Processor 30 may perform step 110, which may include determining the angle 70 of the seatbelt 50 using multiple detection points 64 (such as the positions of the seatbelt 50 in two regions of interest (ROIs) 60, 62). Angle 70 may represent the tilt of the seatbelt 50 in the longitudinal direction, or the difference in distance from the camera between the higher and lower portions of the seatbelt 50.

[0053] Method 100 further includes calculating the distance to seatbelt 50 at step 112. Processor 30 may perform step 112, which may include using the pixel width of seatbelt 50 in ROIs 60, 62. Step 112 may further use the angle of seatbelt 50 as previously determined, such as the distance to 50 in one or more of ROIs 60, 62. For example, for an angle of 73°, processor 30 may determine the pixel width of detection point 64 as 100 pixels. Processor 30 may then multiply the 100-pixel pixel width by the sine of angle 70 (sin73°) to determine a compensated pixel width of approximately 95.6 pixels. This is achieved using the known total internal width W of seatbelt 50. ti Furthermore, utilizing the details of camera 20 (e.g., the arc length of pixels), processor 30 can calculate the distance between the camera and the detection point 64 of seatbelt 50. This distance provides a more accurate measurement of the occupant's position compared to conventional methods (such as those dependent on seat position).

[0054] Method 100 further includes determining at step 114 whether the seat belt 50 is correctly positioned. Processor 30 may perform step 114, which may include using the angle of the seat belt 50 and / or the distance to the seat belt 50. For example, processor 30 may calculate a measured angle of the seat belt 50 and compare that measured angle to a range of measurements corresponding to the correct position of the seat belt 50. Similarly, processor 30 may calculate one or more distances to the seat belt 50 and compare those distances to the distance corresponding to the correct positioning of the seat belt 50. In some embodiments, processor 30 may calculate the rate of change of distance to determine whether the seat belt 50 is slack, for example, as shown in Figure 4. If processor 30 cannot identify the seat belt 50 in one or more regions of the image (such as in one or more of ROIs 60, 62), processor 30 may also designate the seat belt 50 as improperly positioned. Examples of such improper positioning are shown in Figures 5 and 6.

[0055] Method 100 further includes determining at step 116 whether the seat belt 50 is twisted. Processor 30 can execute step 116, which may include detecting one or more reversals of an asymmetric pattern on the seat belt. For example, if processor 30 detects that the number of twists in the seat belt 50 exceeds a twist threshold, the processor may designate the seat belt as improperly positioned.

[0056] Method 100 further includes, at step 118, generating a first signal if system 12 determines that seatbelt 50 is correctly positioned, or generating a second signal if system 12 determines that seatbelt 50 is improperly positioned. Processor 30 may perform step 118, which may include providing clarification to occupant 44, such as an audible or displayed warning message. In another example, processor 30 may signal output device 28 (such as a safety system) to take action to limit or minimize the functionality of vehicle 10. For example, vehicle 10 may be prevented from moving or prevented from exceeding very low speeds until and unless system 12 determines that seatbelt 50 is correctly positioned.

[0057] By implementing the methods of this disclosure, the seatbelt detection system 12 can determine whether occupants 44 are correctly wearing their seatbelts 50. The systems and methods of this disclosure increase the confidence that occupants 44 are correctly wearing their seatbelts 50.

[0058] Additionally, as previously mentioned, the seatbelt 50 may have a light-absorbing and / or reflective material 50C located or disposed on the seatbelt 50. Cameras 20A-20F can capture images of the material 50C. As previously mentioned, the material 50C may be a known pattern having pattern elements separated from each other at a known distance 52. The seatbelt detection system 12 can then examine these images captured by cameras 20A-20F and determine whether the distance from the seatbelt 50 to the camera is approximately the expected distance indicating that the seatbelt 50 correctly crosses the body 48 of the occupant 44. Furthermore, because the pattern is known, clothing worn by the occupant 44 that may reflect and / or absorb light (such as infrared light) can be disregarded, as the clothing worn by the occupant is unlikely to have a pattern that matches the pattern of the stripes 68a-68g on the seatbelt 50.

[0059] If the seatbelt detection system 12 determines that occupant 44 is correctly wearing the seatbelt 50, the seatbelt detection system 12 may allow vehicle 10 to operate in normal mode. However, if the seatbelt detection system 12 indicates that occupant 44 is not correctly wearing the seatbelt 50, the control system 12 may take any of a number of different actions. For example, the seatbelt detection system 12 may use output device 28 to instruct occupant 44 to provide a visual and / or auditory cue that the seatbelt 50 is not correctly worn. Alternatively, output device 28 may communicate with any of a number of different vehicle systems to restrict the operation of vehicle 10 until the seatbelt 50 is correctly worn by occupant 44.

[0060] The seatbelt detection system 12 can also communicate with other control systems to improve system reliability. For example, the seatbelt detection system 12 can also communicate with one or more sensors, such as sensors that detect the seatbelt latch 61 or the tongue insertion into the seatbelt buckle 63. If the seatbelt detection system 12 determines that the seatbelt buckle is properly latched and that the seatbelt 50 is properly positioned across the occupant's body 48, the seatbelt detection system 12 can more confidently determine that the seatbelt 50 is being used correctly by the occupant 44.

[0061] In some implementations, dedicated hardware embodiments such as application-specific integrated circuits (ASICs), programmable logic arrays (PLA), and other hardware devices may be configured to implement one or more steps of the methods described herein. Applications of devices and systems that may include various implementations can broadly encompass a wide range of electronic and computer systems. One or more implementations described herein may use two or more specific interconnected hardware modules or devices having associated control and data signals that can be transmitted between and through modules, or as part of an ASIC, to achieve functionality. Therefore, this system encompasses software, firmware, and hardware implementations.

[0062] According to various embodiments of this disclosure, the methods described herein can be implemented by software programs executable by a computer system. Furthermore, in exemplary non-limiting embodiments, implementations may include distributed processing, component / object distributed processing, and parallel processing. Alternatively, virtual computer system processing may be configured to implement one or more of the methods or functions described herein.

[0063] Furthermore, the methods described herein may be embodied in a computer-readable medium. The term "computer-readable medium" includes a single medium or multiple media, such as a centralized or distributed database, and / or an associated cache and server storing one or more instruction sets. The term "computer-readable medium" also includes any medium capable of storing, encoding, or carrying a set of instructions for execution by a processor or causing a computer system to perform any one or more of the methods or operations disclosed herein.

[0064] It will be readily understood by those skilled in the art that the above description is intended to illustrate the principles of the invention. This description is not intended to limit the scope or application of the invention, as the invention is readily modified, altered, and modified without departing from the spirit of the invention as defined in the following claims.

Claims

1. A method for detecting seatbelt positioning, the method comprising: Near-infrared images of the occupants are captured by a camera; Convert the near-infrared image into a black and white image; The black-and-white image is scanned to detect multiple transitions between black and white segments corresponding to stripes extending longitudinally along the length of the seatbelt, and the detection of these multiple transitions is used to indicate the detection of the seatbelt, wherein the width of the stripes defines an asymmetrical pattern. The torsion in the seat belt is determined based on one or more variations in the orientation of the seat belt along its length.

2. The method of claim 1, further comprising applying a median filter to the near-infrared image to remove flare before converting the near-infrared image to the black-and-white image.

3. The method according to claim 1, wherein converting the near-infrared image into the black-and-white image comprises: Based on whether the corresponding source pixel in the near-infrared image is brighter than the average value of nearby pixels within a predetermined distance of the corresponding source pixel, a local binary threshold is used to determine whether a given pixel in the black and white image should be black or white.

4. The method of claim 3, wherein the predetermined distance is approximately 100 pixels, or wherein the predetermined distance is approximately equal to the pixel width of the seat belt.

5. The method of claim 1, wherein using the detection of the plurality of transition sections to indicate the detection of the seat belt further comprises comparing the ratio of the relative distance between the transition sections to the width of the stripe.

6. The method according to claim 1, wherein the method further comprises: The orientation of the seat belt is determined based on the order in which the multiple transition sections correspond to the asymmetrical patterns that differ based on the orientation of the seat belt.

7. The method of claim 1, further comprising using detection of the seat belt in at least two different regions of interest to calculate the angle of the seat belt.

8. The method of claim 7, further comprising using the pixel width of the seatbelt in each of the two different regions of interest to calculate the distance to the seatbelt.

9. The method of claim 8, wherein calculating the distance to the seatbelt further comprises: Calculate the sine of the angle of the seat belt; Multiply the pixel width of the seat belt by the sine of the angle of the seat belt to determine the compensated pixel width; as well as The distance to the seatbelt is calculated based on the compensated pixel width and the known internal width of the seatbelt.

10. The method of claim 9, wherein the stripes of the seatbelt comprise a plurality of inner stripes surrounded by the outermost stripe on each of the two edges along the length of the seatbelt; and The known inner width of the seat belt is the sum of the widths of the plurality of inner stripes.

11. The method according to claim 1, wherein the method further comprises: Use at least one of the angle of the seat belt or the distance to the seat belt to determine whether the seat belt is correctly positioned; as well as A signal is generated in response to determining that the seat belt is correctly positioned or in response to determining that the seat belt is not correctly positioned.

12. A system for detecting seatbelt positioning, the system comprising: The seat belt has a plurality of stripes extending longitudinally along its length, the plurality of stripes being arranged in an alternating pattern of bright and dark in the near infrared. A camera configured to capture near-infrared images of an occupant wearing the seatbelt; A processor, which communicates with the camera and is programmed to receive the near-infrared image of the occupant wearing the seatbelt and determine the position of the seatbelt based on detecting transitions in the alternating pattern corresponding to the stripes, wherein the width of the stripes defines an asymmetrical pattern, and to determine torsion in the seatbelt based on one or more variations in the orientation of the seatbelt along its length.

13. The system of claim 12, wherein the processor is further programmed to: convert the near-infrared image into a black-and-white image, and determine whether a given pixel in the black-and-white image should be black or white based on whether a corresponding source pixel in the near-infrared image is brighter than the average value of nearby pixels within a predetermined distance of the corresponding source pixel.

14. The system of claim 13, wherein the predetermined distance is about 100 pixels, or wherein the predetermined distance is approximately equal to the pixel width of the seat belt.

15. The system of claim 12, wherein determining the position of the seatbelt based on detecting the transitions of the alternating pattern corresponding to the stripes further comprises comparing the relative distance between the transitions with a ratio of the widths of the plurality of stripes.

16. The system of claim 12, wherein the processor is further programmed to use the pixel width of the seatbelt to calculate the distance to the seatbelt and to calculate the angle of the seatbelt based on the detection of the seatbelt in each of two different regions of interest within the near-infrared image.

17. The system of claim 16, wherein calculating the distance to the seatbelt further comprises the processor being programmed to: Calculate the sine of the angle of the seat belt; Multiply the pixel width of the seatbelt by the sine of the angle of the seatbelt to determine the compensated pixel width; and The distance to the seatbelt is calculated based on the compensated pixel width and the known internal width of the seatbelt.

18. The system of claim 12, wherein the processor is further programmed to: Whether the seat belt is correctly positioned is determined using at least one of the angle of the seat belt or the distance to the seat belt; and A signal is generated in response to determining that the seat belt is correctly positioned or in response to determining that the seat belt is not correctly positioned.

Images