CN113080550A - Headband for recognizing obstacle and method for recognizing obstacle - Google Patents
Headband for recognizing obstacle and method for recognizing obstacle Download PDFInfo
- Publication number
- CN113080550A CN113080550A CN202110519578.8A CN202110519578A CN113080550A CN 113080550 A CN113080550 A CN 113080550A CN 202110519578 A CN202110519578 A CN 202110519578A CN 113080550 A CN113080550 A CN 113080550A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- user
- area
- distance
- headband
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A41—WEARING APPAREL
- A41D—OUTERWEAR; PROTECTIVE GARMENTS; ACCESSORIES
- A41D23/00—Scarves; Head-scarves; Neckerchiefs
-
- A—HUMAN NECESSITIES
- A41—WEARING APPAREL
- A41D—OUTERWEAR; PROTECTIVE GARMENTS; ACCESSORIES
- A41D27/00—Details of garments or of their making
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B6/00—Tactile signalling systems, e.g. personal calling systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/57—Mechanical or electrical details of cameras or camera modules specially adapted for being embedded in other devices
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Textile Engineering (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a headband for identifying obstacles and a method for identifying the obstacles by the headband, wherein the headband comprises a headband body and an obstacle identification system arranged on the headband body, the obstacle identification system identifies the obstacles in an environment image acquired in real time through a control chip, and the obstacle condition existing in an area shot by a camera device can be accurately judged; the position of the obstacle is extracted, the distance sensor is requested to detect the distance between the obstacle and the user according to the position of the obstacle, and early warning information can be accurately obtained according to the recognition result and the obstacle; therefore, the early warning module is controlled based on the early warning information, so that the user can be reminded of avoiding obstacles in time, and the personal safety of the user is protected. In addition, the headband for identifying the obstacles is convenient for a user to carry and liberates hands.
Description
Technical Field
The application relates to the technical field of blind people tools, in particular to a headband for identifying obstacles and a method for identifying the obstacles.
Background
Because of the lack of vision, the blind (visually impaired people or blind people) is very inconvenient in walking and daily life, and it is very important for them to sense external things.
The trip of the blind mostly relies on the blind stick perception blind road and some barriers on the road at present, and this kind of mode needs the blind person to walk with the blind stick with the ground always and is tired more easily, and leaves out some danger points easily thereby causes dangers such as stepping on the hole, falling down. Some blind people also walk by means of the guide dogs in an auxiliary mode, and the number of the guide dogs is limited and the cost is high due to the fact that the guide dogs need to be trained for a long time, so that most blind people cannot walk by means of the guide dogs in an auxiliary mode; in addition, many public places (such as buses, subways, restaurants, malls, etc.) do not allow animals to enter. Some blind guiding tools (such as blind guiding glasses and blind guiding prompters) appearing in the market can achieve certain auxiliary functions, but the situation of mistaken identification or missing identification of obstacles often occurs.
Therefore, a portable blind guiding tool capable of accurately identifying obstacles is needed to be developed.
Disclosure of Invention
In view of the above, the present application provides a headband for identifying an obstacle and a method for identifying an obstacle thereof, so as to solve the problem that the existing blind guiding tool has the problem of identifying an obstacle by mistake or missing.
The application provides a headband for identifying obstacles, which comprises a headband body and an obstacle identification system arranged on the headband body; the obstacle identification system comprises a camera device, a distance sensor, an early warning module and a control chip, wherein the camera device, the distance sensor and the early warning module are respectively connected with the control chip; the camera shooting equipment is used for shooting an environment image in front of the vision of the user in real time; the control chip is used for acquiring the environment image, identifying obstacles in the environment image, judging whether the obstacles exist in the area shot by the camera equipment through identification, if so, extracting the positions of the obstacles, transmitting the positions of the obstacles to the distance sensor, and requesting the distance sensor to detect the distance from the obstacles to a user; the distance sensor is used for receiving the distance between the obstacle and the user, judging whether the distance between the obstacle and the user reaches a preset distance threshold value, if so, acquiring early warning information according to the recognition result and the distance between the obstacle and the user, and sending the early warning information to the early warning module; the distance sensor is used for receiving the position of the obstacle, detecting the distance from the obstacle to a user according to the position of the obstacle, and sending the distance from the obstacle to the user to the control chip; the early warning module is used for receiving the early warning information and reminding a user to avoid obstacles according to the early warning information.
In some embodiments, the barrier comprises at least one of a figure, a barricade, and a manhole cover; the control chip stores a human shape detection algorithm, a barrier detection algorithm and a ground cave well lid detection algorithm, and the method for identifying the barrier in the environment image comprises the following steps: and recognizing the human shape in the environment image by adopting the human shape detection algorithm, recognizing the barrier in the environment image by adopting the barrier detection algorithm, and recognizing the barrier in the environment image by adopting the manhole cover detection algorithm.
In some embodiments, the barrier comprises at least one of a zebra line, a popsicle canister, a cement column, a utility pole, a car, a ground deposit, and a water spot; and/or the manhole cover comprises at least one of ponding, a pit and a manhole without a cover.
In some embodiments, the warning module includes a broadcaster and/or a vibrator, the broadcaster is configured to broadcast the warning information in voice to remind the user of avoiding the obstacle, and the vibrator is configured to vibrate to remind the user of avoiding the obstacle.
In some embodiments, the image capturing apparatus includes an RGB camera for day-time capturing and a night-vision camera for night-time capturing, which are respectively connected to the control chip, and the control chip is configured to obtain light intensity of an environment and automatically switch the capturing mode according to the light intensity of the environment.
In some embodiments, the distance sensor is an ultrasonic distance detection device or an infrared distance detection device, by which the distance from the obstacle to the user is detected.
In some embodiments, the headband body is provided with a positioning convex part, the positioning convex part is arranged in the area where the camera device is located, and the positioning convex part is used for aligning with the front of the vision so that the camera device can shoot an environment image in front of the vision of the user.
Another aspect of the present application provides a method of identifying an obstacle using a headband for identifying an obstacle as described in any of the above, comprising the steps of: acquiring an environment image in front of the user vision shot by a camera device in real time; recognizing obstacles in the environment image, and judging whether the obstacles exist in the area shot by the camera device; if yes, extracting the position of the obstacle, transmitting the position of the obstacle to the distance sensor, and requesting the distance sensor to detect the distance from the obstacle to a user; receiving the distance from the obstacle to the user, which is detected by the distance sensor, and judging whether the distance from the obstacle to the user reaches a preset distance threshold value; if yes, acquiring early warning information according to the recognition result and the distance from the obstacle to the user; and reminding the user to avoid the obstacle according to the early warning information.
In some embodiments, the recognizing an obstacle in the environment image and determining whether an obstacle exists in an area captured by the imaging device includes: and binarizing the environment image, extracting a target region in the environment image, calculating the area of the target region, and judging as an obstacle if the area of the target region is greater than or equal to a preset area threshold value. Further, if the area of the target area is larger than or equal to a preset area threshold, the height of the object in the target area is calculated, and if the area of the target area is larger than a first preset height, the obstacle is determined.
In other embodiments, if the area of the target region is smaller than a preset area threshold, calculating the height of the object in the target region, and if the area of the target region is larger than a second preset height, determining that the object is an obstacle; the second preset height is greater than the first preset height.
In other embodiments, if the area of the target region is smaller than the preset area threshold, the shape of the object in the target region is detected, and if the object is a sphere, the object is determined to be an obstacle.
In some embodiments, the step of extracting the position of the obstacle comprises: and acquiring the outline of the obstacle, and taking the center position of the outline of the obstacle as the position of the obstacle.
In other embodiments, if the length of the obstacle in the visual direction is smaller than a preset length value, the center position of the obstacle contour is used as the position of the obstacle.
In other embodiments, if the length of the obstacle in the visual direction is greater than or equal to the preset length value, the position of the obstacle contour closest to the user is taken as the position of the obstacle.
According to the headband for identifying the obstacle and the method for identifying the obstacle, the headband comprises a headband body and an obstacle identification system arranged on the headband body, the obstacle identification system identifies the obstacle in the environment image acquired in real time through a control chip, and the condition of the obstacle existing in the area shot by the camera equipment can be accurately judged; by extracting the position of the obstacle, a distance sensor is requested to detect the distance between the obstacle and a user according to the position of the obstacle, and early warning information (such as the type of the obstacle and the range of the obstacle) can be accurately obtained according to the recognition result and the obstacle; therefore, the user can be timely reminded of avoiding obstacles based on the early warning information, and the personal safety of the user is further protected. In addition, the headband for identifying the obstacles is convenient for a user to carry and liberates hands.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of a headband for identifying obstacles according to an embodiment of the present application;
FIG. 2 is an overall architecture diagram of an obstacle identification system according to an embodiment of the present application;
fig. 3 is a flowchart of a method of identifying an obstacle using a headband for identifying obstacles according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. The following embodiments and their technical features may be combined with each other without conflict.
Referring to fig. 1, the present application provides an embodiment of a headband 100 for identifying obstacles, including a headband body 1 and an obstacle identification system disposed on the headband body 1; the obstacle identification system comprises a camera device 3, a distance sensor 4, an early warning module 5 and a control chip 6, wherein the camera device 3, the distance sensor 4 and the early warning module 5 are respectively connected with the control chip 6; the camera device 3 is used for shooting an environment image in front of the vision of the user in real time; the control chip 6 is configured to obtain the environment image, identify an obstacle in the environment image, determine whether the obstacle exists in the area captured by the image capture device 3 through identification, if so, extract a position of the obstacle, transmit the position of the obstacle to the distance sensor 4, and request the distance sensor 4 to detect a distance from the obstacle to a user; the distance sensor is used for receiving the distance from the obstacle to the user, and judging whether the distance from the obstacle to the user reaches a preset distance threshold value, if so, acquiring early warning information according to the recognition result and the distance from the obstacle to the user, and sending the early warning information to the early warning module 5; the distance sensor 4 is used for receiving the position of the obstacle, detecting the distance from the obstacle to the user according to the position of the obstacle, and sending the distance from the obstacle to the user to the control chip 6; the early warning module 5 is used for receiving the early warning information and reminding a user to avoid obstacles according to the early warning information. It should be understood that the headband body 1 of the present embodiment refers to a support for supporting the obstacle recognition system, and the headband body 1 may be a headband, a head cover, or the like.
In some embodiments, the image pickup apparatus 3 includes an image pickup apparatus for taking an environmental image visually behind the user and on both sides of the user.
The control chip 6 is also used for identifying the obstacles in the environment image, and if the identified obstacles are static objects, the obstacle avoidance reminding operation instruction is not responded. If the recognized barrier is an object in a motion state, continuous multi-frame shooting is carried out on the barrier, the motion track of the barrier is predicted, and if the motion track points to the front of the vision of the user, early warning information is sent out to the early warning module 5 to remind the user to avoid the barrier.
In some embodiments, the control chip 6 is further configured to binarize the environment image, extract a target region in the environment image, calculate an area of the target region, and determine that the obstacle is present if the area of the target region is greater than or equal to a preset area threshold. By setting the standard for identifying the barrier, the barrier with the size small enough not to influence the blind to move is ignored, the time for identifying the barrier is favorably shortened, and the power consumption generated by identifying the barrier not to influence the blind to move is reduced.
Further, the control chip 6 is further configured to calculate a height of an object in the target region when the area of the target region is greater than or equal to a preset area threshold, and determine that the obstacle is present if a ratio of the height of the object to the area of the target region is greater than a first preset height-to-area ratio.
In other embodiments, the control chip 6 is further configured to calculate a height of an object in the target region when the area of the target region is smaller than a preset area threshold, and determine that the obstacle is present if a ratio of the height of the object to the area of the target region is larger than a second preset height-to-area ratio; the second preset height-to-area ratio is greater than the first preset height-to-area ratio. Such as very sharp nails, can harm the blind and it is necessary to remind people to avoid obstacles.
In other embodiments, the control chip 6 is further configured to detect the shape of the object in the target region when the area of the target region is smaller than a preset area threshold, and determine that the object is an obstacle if the object is a sphere. Such as beads, ocean balls and the like, when the shoes are stepped on, the shoes can easily slip, and the obstacle avoidance needs to be reminded.
In some embodiments, the control chip 6 is further configured to obtain the contour of the obstacle, and use the center position of the contour of the obstacle as the position of the obstacle. By setting the position points of the obstacles, the calculation is convenient, thereby being beneficial to quickly extracting the positions of the obstacles.
In other embodiments, the control chip 6 is further configured to use the center position of the obstacle contour as the position of the obstacle when the length of the obstacle in the visual direction is smaller than the preset length value.
In other embodiments, the control chip 6 is further configured to, when the length of the obstacle in the visual direction is greater than or equal to the preset length value, take the position of the obstacle contour closest to the user as the position of the obstacle. The distance between the longer barrier and the user can be determined more accurately in the next step.
In the embodiment, the obstacle recognition system in the headband for recognizing the obstacle recognizes the obstacle in the environment image acquired in real time through the control chip, and can accurately judge the obstacle existing in the area shot by the camera device; by extracting the position of the obstacle, a distance sensor is requested to detect the distance between the obstacle and a user according to the position of the obstacle, and early warning information (such as the type of the obstacle and the range of the obstacle) can be accurately obtained according to the recognition result and the obstacle; therefore, the user can be timely reminded of avoiding obstacles based on the early warning information, and the personal safety of the user is further protected. In addition, the headband for identifying the obstacles is convenient for a user to carry and liberates hands.
During concrete realization, obstacle identification system still includes insulated wire, camera device 3, distance sensor 4 and early warning module 5 respectively through insulated wire with control chip 6 is connected, insulated wire alternates on the headband body 1, thereby will camera device 3, distance sensor 4, early warning module 5 and control chip 6 are fixed on the headband body 1, but each components and parts evenly distributed is on the headband body in the obstacle identification system. The headband can further comprise a storage bag which is fixed on the headband body 1, the obstacle recognition system is arranged in the storage bag, a through hole is formed in the storage bag, and a camera of the camera device 1 extends out of the through hole. Each component in the obstacle recognition system is a micro device to reduce deformation of the headband 100 caused by overweight. Referring also to fig. 2, in some embodiments, the barrier may include at least one of a figure, a barricade, and a manhole cover; the control chip 6 stores a human shape detection algorithm 61, a barrier detection algorithm 62 and a manhole cover detection algorithm 63, and the identification of the obstacles in the environment image includes: and recognizing the human shape in the environment image by adopting the human shape detection algorithm 61, recognizing the barrier in the environment image by adopting the barrier detection algorithm 62, and recognizing the barrier in the environment image by adopting the manhole cover detection algorithm 63. And the corresponding detection algorithm is adopted for identifying different types of obstacles, so that the identification accuracy is improved, and the false identification rate and the missing identification rate are reduced. Optionally, the information identifying the obstacle in the environment image may include, but is not limited to, a shape, a size, a position, a state (static or dynamic) and the like of the obstacle. Further, the humanoid detection algorithm 61 may be a full-convolution head detection algorithm, which is an end-to-end trainable anchor-based head detection model with anchor dimensions of 2 (anchor size 32 × 32 pixels) and 4 (anchor size 64 × 64 pixels). The human shape in the environmental image can be rapidly and accurately identified by adopting a full convolution head detection algorithm, the running speed can reach 5fps, and the average precision can reach 0.70.
In some embodiments, the barrier may include, but is not limited to, at least one of a zebra line, ice cream cone, cement column, utility pole, automobile, ground deposit, and water stain; and/or the manhole cover may include, but is not limited to, at least one of standing water, a pit, and a manhole without a cover.
In some embodiments, the warning module 5 includes a broadcaster 51 and/or a vibrator 52, the broadcaster 51 is configured to broadcast the warning information in voice to remind the user of obstacle avoidance, and the vibrator 52 is configured to vibrate to remind the user of obstacle avoidance. The user can select the early warning mode according to own hobby and the environment, and the user experience is favorably improved. Optionally, the warning information may include, but is not limited to, the name of the obstacle, the distance range of the obstacle, and the like.
In some embodiments, the image capturing device 3 includes an RGB camera 31 for day-time shooting and a night-vision camera 32 for night-time shooting, which are respectively connected to the control chip, and the control chip is further configured to obtain the light intensity of the environment and automatically switch the shooting mode according to the light intensity of the environment. Therefore, the method is beneficial to the barrier recognition system to shoot clearer environment images, thereby being beneficial to improving the accuracy of recognition results and accelerating the recognition speed.
In some embodiments, the distance sensor 4 is an ultrasonic distance detection device or an infrared distance detection device, by which the distance of the obstacle to the user is detected. The distance from the obstacle to the user is selectively detected by adopting ultrasonic distance detection equipment and/or infrared distance detection equipment according to the real scene of the environment where the obstacle is located, so that the distance detection accuracy is guaranteed, and meanwhile, the energy can be saved.
Referring to fig. 1, in some embodiments, the obstacle recognition system further includes a power supply device 7, and the image pickup device 3, the distance sensor 4, the early warning module 5, and the control chip 6 are electrically connected to the power supply device 7, respectively. Alternatively, the power supply device 7 may be, but is not limited to, a storage battery.
In some embodiments, the obstacle recognition system further comprises a switch 8, the switch 8 is electrically connected with the power supply device 7, and the switch 8 is used for controlling the obstacle recognition system to be turned on and off.
In some embodiments, the headband body 1 is provided with a positioning protrusion 9, the positioning protrusion 9 is provided in a region where the image capturing device 3 is located, and the positioning protrusion 9 is used for aiming at the front of the vision, so that the image capturing device 3 captures an environmental image in front of the vision of the user. Alternatively, the positioning boss 9 may be provided above or below the image pickup apparatus 3 along the longitudinal center line of the image pickup apparatus 3. Alternatively, the positioning protrusion 9 may be a cylinder, a prism, a sphere, or the like. Further, the positioning boss 9 may be integrated with the switch 8.
Referring to fig. 3, the present application also provides a method for identifying an obstacle using the headband for identifying an obstacle as described above, including the steps of: s1, acquiring an environment image in front of the user vision shot by the camera in real time; s2, recognizing the obstacles in the environment image and judging whether the obstacles exist in the area shot by the camera device; s3, if yes, extracting the position of the obstacle, transmitting the position of the obstacle to the distance sensor, and requesting the distance sensor to detect the distance from the obstacle to a user; s4, receiving the distance between the obstacle and the user detected by the distance sensor, and judging whether the distance between the obstacle and the user reaches a preset distance threshold value; s5, if yes, acquiring early warning information according to the recognition result and the distance from the obstacle to the user; and S6, reminding the user to avoid obstacles according to the early warning information.
In some embodiments, step S1 may further include: and shooting environment images behind the vision of the user and on two sides of the user.
And identifying the obstacle in the environment image, and if the identified obstacle is an object in a static state, not responding to an obstacle avoidance reminding operation instruction.
If the recognized object in the barrier motion state is in a continuous multi-frame shooting mode, the barrier is subjected to continuous multi-frame shooting, the motion track of the barrier is predicted, and if the motion track points to the front of the vision of the user, early warning information is sent out to remind the user to avoid the barrier.
In some embodiments, step S2 is followed by: s3', if not, re-executing steps S1 and S2. That is, when no obstacle exists in the area captured by the image capturing apparatus, step S3 is executed. When no obstacle exists in the area photographed by the image pickup apparatus, step S3' is executed.
In some embodiments, step S4 is followed by: s5', if not, re-executing steps S3 and S4. That is, when no obstacle exists in the area captured by the image capturing apparatus, step S5 is executed. When no obstacle exists in the area photographed by the image pickup apparatus, step S5' is executed.
In some embodiments, step S2 includes: and binarizing the environment image, extracting a target region in the environment image, calculating the area of the target region, and judging as an obstacle if the area of the target region is greater than or equal to a preset area threshold value. By setting the standard for identifying the barrier, the barrier with the size small enough not to influence the blind to move is ignored, the time for identifying the barrier is favorably shortened, and the power consumption generated by identifying the barrier not to influence the blind to move is reduced.
Further, if the area of the target area is larger than or equal to a preset area threshold, calculating the height of the object in the target area, and if the ratio of the height of the object to the area of the target area is larger than a first preset height-area ratio, determining that the obstacle is present.
In other embodiments, if the area of the target region is smaller than a preset area threshold, calculating the height of an object in the target region, and if the ratio of the height of the object to the area of the target region is larger than a second preset height-area ratio, determining that the object is an obstacle; the second preset height-to-area ratio is greater than the first preset height-to-area ratio. Such as very sharp nails, can harm the blind and it is necessary to remind people to avoid obstacles.
In other embodiments, if the area of the target region is smaller than the preset area threshold, the shape of the object in the target region is detected, and if the object is a sphere, the object is determined to be an obstacle. Such as beads, ocean balls and the like, when the shoes are stepped on, the shoes can easily slip, and the obstacle avoidance needs to be reminded.
In some embodiments, in step S3, the step of extracting the position of the obstacle includes: and acquiring the outline of the obstacle, and taking the center position of the outline of the obstacle as the position of the obstacle. By setting the position points of the obstacles, the calculation is convenient, thereby being beneficial to quickly extracting the positions of the obstacles.
In other embodiments, if the length of the obstacle in the visual direction is smaller than a preset length value, the center position of the obstacle contour is used as the position of the obstacle.
In other embodiments, if the length of the obstacle in the visual direction is greater than or equal to the preset length value, the position of the obstacle contour closest to the user is taken as the position of the obstacle. The distance between the longer barrier and the user can be determined more accurately in the next step.
In some embodiments, the barrier comprises at least one of a figure, a barricade, and a manhole cover; the identifying obstacles in the environment image further comprises: and recognizing the human shape in the environment image by adopting the human shape detection algorithm, recognizing the barrier in the environment image by adopting the barrier detection algorithm, and recognizing the barrier in the environment image by adopting the manhole cover detection algorithm.
Further, the barrier comprises at least one of a zebra crossing, a ice cream cone, a cement column, a telegraph pole, a car, a ground deposit and water stains; and/or the manhole cover comprises at least one of ponding, a pit and a manhole without a cover.
Although the application has been shown and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. This application is intended to embrace all such modifications and variations and is limited only by the scope of the appended claims. In particular regard to the various functions performed by the above described components, the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated exemplary implementations of the specification.
That is, the above description is only an embodiment of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent flow transformations made by using the contents of the specification and the drawings, such as mutual combination of technical features between various embodiments, or direct or indirect application to other related technical fields, are included in the scope of the present application.
In addition, in the description of the present application, it is to be understood that the terms "center", "longitudinal", "lateral", "upper", "lower", "inner", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present application. In addition, structural elements having the same or similar characteristics may be identified by the same or different reference numerals.
In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The previous description is provided to enable any person skilled in the art to make and use the present application. In the foregoing description, various details have been set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes are not shown in detail to avoid obscuring the description of the present application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
Claims (10)
1. A headband for identifying obstacles is characterized by comprising a headband body and an obstacle identification system arranged on the headband body;
the obstacle identification system comprises a camera device, a distance sensor, an early warning module and a control chip, wherein the camera device, the distance sensor and the early warning module are respectively connected with the control chip;
the camera shooting equipment is used for shooting an environment image in front of the vision of the user in real time;
the control chip is used for acquiring the environment image, identifying obstacles in the environment image, judging whether the obstacles exist in the area shot by the camera equipment through identification, if so, extracting the positions of the obstacles, transmitting the positions of the obstacles to the distance sensor, and requesting the distance sensor to detect the distance from the obstacles to a user; the distance sensor is used for receiving the distance between the obstacle and the user, judging whether the distance between the obstacle and the user reaches a preset distance threshold value, if so, acquiring early warning information according to the recognition result and the distance between the obstacle and the user, and sending the early warning information to the early warning module;
the distance sensor is used for receiving the position of the obstacle, detecting the distance from the obstacle to a user according to the position of the obstacle, and sending the distance from the obstacle to the user to the control chip;
the early warning module is used for receiving the early warning information and reminding a user to avoid obstacles according to the early warning information.
2. An identification headband for identifying an obstacle according to claim 1 wherein the obstacle comprises at least one of a figure, a barricade and a manhole cover;
the control chip stores a human shape detection algorithm, a barrier detection algorithm and a ground cave well lid detection algorithm, and the method for identifying the barrier in the environment image comprises the following steps: and recognizing the human shape in the environment image by adopting the human shape detection algorithm, recognizing the barrier in the environment image by adopting the barrier detection algorithm, and recognizing the barrier in the environment image by adopting the manhole cover detection algorithm.
3. The headband of claim 2 wherein the barrier comprises at least one of a zebra line, a popsicle canister, a column of cement, a utility pole, a car, a floor deposit, and a water spot; and/or the manhole cover comprises at least one of ponding, a pit and a manhole without a cover.
4. The headband of claim 1, wherein the pre-warning module comprises a speaker and/or a vibrator, the speaker is used for voice-broadcasting the pre-warning information to remind a user of obstacle avoidance, and the vibrator is used for vibrating to remind the user of obstacle avoidance.
5. The headband according to claim 1, wherein the camera device comprises an RGB camera for daytime photographing and a night vision camera for nighttime photographing, which are respectively connected to the control chip, and the control chip is configured to obtain light intensity of an environment and automatically switch the photographing mode according to the light intensity of the environment.
6. The headband according to claim 1, wherein the distance sensor is an ultrasonic distance detection device or an infrared distance detection device by which a distance from the obstacle to a user is detected.
7. The headband for identifying obstacles according to claim 1, wherein the headband body is provided with a positioning protrusion, the positioning protrusion is disposed in an area where the camera device is located, and the positioning protrusion is used for aiming at the front of the vision, so that the camera device can shoot an environmental image in front of the vision of the user.
8. A method of identifying an obstacle using a headband for identifying obstacles according to any one of claims 1 to 7, comprising the steps of:
acquiring an environment image in front of the user vision shot by a camera device in real time;
recognizing obstacles in the environment image, and judging whether the obstacles exist in the area shot by the camera device;
if yes, extracting the position of the obstacle, transmitting the position of the obstacle to the distance sensor, and requesting the distance sensor to detect the distance from the obstacle to a user;
receiving the distance from the obstacle to the user, which is detected by the distance sensor, and judging whether the distance from the obstacle to the user reaches a preset distance threshold value;
if yes, acquiring early warning information according to the recognition result and the distance from the obstacle to the user;
and reminding the user to avoid the obstacle according to the early warning information.
9. The method of claim 8, wherein the step of recognizing the obstacle in the environment image and determining whether the obstacle exists in the area captured by the image capturing apparatus comprises: binarizing the environment image, extracting a target region in the environment image, calculating the area of the target region, and judging as an obstacle if the area of the target region is greater than or equal to a preset area threshold value;
if the area of the target area is larger than or equal to a preset area threshold value, calculating the height of an object in the target area, and if the ratio of the height of the object to the area of the target area is larger than a first preset height-area ratio, judging that the object is an obstacle;
if the area of the target area is smaller than a preset area threshold value, calculating the height of an object in the target area, and if the ratio of the height of the object to the area of the target area is larger than a second preset height-area ratio, judging that the object is an obstacle; the second preset height-to-area ratio is greater than the first preset height-to-area ratio;
and if the area of the target area is smaller than a preset area threshold value, detecting the shape of the object in the target area, and if the object is a sphere, judging the object to be an obstacle.
10. The method of identifying an obstacle using a headband for identifying obstacles according to claim 8, wherein the extracting the location of the obstacle comprises: acquiring the outline of an obstacle, and taking the central position of the outline of the obstacle as the position of the obstacle;
if the length of the obstacle along the visual direction is smaller than a preset length value, taking the center position of the obstacle outline as the position of the obstacle;
and if the length of the obstacle in the visual direction is greater than or equal to the preset length value, taking the position, closest to the user, of the obstacle outline as the position of the obstacle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110519578.8A CN113080550A (en) | 2021-05-12 | 2021-05-12 | Headband for recognizing obstacle and method for recognizing obstacle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110519578.8A CN113080550A (en) | 2021-05-12 | 2021-05-12 | Headband for recognizing obstacle and method for recognizing obstacle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113080550A true CN113080550A (en) | 2021-07-09 |
Family
ID=76665448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110519578.8A Pending CN113080550A (en) | 2021-05-12 | 2021-05-12 | Headband for recognizing obstacle and method for recognizing obstacle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113080550A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113963509A (en) * | 2021-10-22 | 2022-01-21 | 安徽拓强电气有限公司 | Old man prevents falling down device and system based on thing networking |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102973395A (en) * | 2012-11-30 | 2013-03-20 | 中国舰船研究设计中心 | Multifunctional intelligent blind guiding method, processor and multifunctional intelligent blind guiding device |
| CN104127301A (en) * | 2014-07-15 | 2014-11-05 | 深圳先进技术研究院 | Smart glasses for guiding blind person and guiding method thereof |
| CN104751158A (en) * | 2015-03-11 | 2015-07-01 | 广西科技大学 | Visual identifying method for road barriers in surface mining area |
| CN106176157A (en) * | 2016-08-12 | 2016-12-07 | 李乾 | A kind of blind person's blind-guide device and control method thereof |
| CN106859929A (en) * | 2017-01-25 | 2017-06-20 | 上海集成电路研发中心有限公司 | A kind of Multifunctional blind person guiding instrument based on binocular vision |
| CN109602585A (en) * | 2018-11-30 | 2019-04-12 | 西安工程大学 | A kind of glasses for guiding blind and its anti-collision early warning method |
| KR20190069919A (en) * | 2017-12-12 | 2019-06-20 | (주)리터너블 | Walking assistive device and system for visually impaired people |
| CN110522617A (en) * | 2019-09-05 | 2019-12-03 | 张超 | Blind person's wisdom glasses |
| CN110782626A (en) * | 2019-08-15 | 2020-02-11 | 天津中德应用技术大学 | Artificial intelligence navigation head based on thing networking |
-
2021
- 2021-05-12 CN CN202110519578.8A patent/CN113080550A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102973395A (en) * | 2012-11-30 | 2013-03-20 | 中国舰船研究设计中心 | Multifunctional intelligent blind guiding method, processor and multifunctional intelligent blind guiding device |
| CN104127301A (en) * | 2014-07-15 | 2014-11-05 | 深圳先进技术研究院 | Smart glasses for guiding blind person and guiding method thereof |
| CN104751158A (en) * | 2015-03-11 | 2015-07-01 | 广西科技大学 | Visual identifying method for road barriers in surface mining area |
| CN106176157A (en) * | 2016-08-12 | 2016-12-07 | 李乾 | A kind of blind person's blind-guide device and control method thereof |
| CN106859929A (en) * | 2017-01-25 | 2017-06-20 | 上海集成电路研发中心有限公司 | A kind of Multifunctional blind person guiding instrument based on binocular vision |
| KR20190069919A (en) * | 2017-12-12 | 2019-06-20 | (주)리터너블 | Walking assistive device and system for visually impaired people |
| CN109602585A (en) * | 2018-11-30 | 2019-04-12 | 西安工程大学 | A kind of glasses for guiding blind and its anti-collision early warning method |
| CN110782626A (en) * | 2019-08-15 | 2020-02-11 | 天津中德应用技术大学 | Artificial intelligence navigation head based on thing networking |
| CN110522617A (en) * | 2019-09-05 | 2019-12-03 | 张超 | Blind person's wisdom glasses |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113963509A (en) * | 2021-10-22 | 2022-01-21 | 安徽拓强电气有限公司 | Old man prevents falling down device and system based on thing networking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107792261B (en) | Management system for intelligently identifying vehicle parking environment through detection and identification equipment | |
| TWI332454B (en) | Intelligent vehicle traffic safety supply system | |
| JP6617651B2 (en) | Pedestrian detection device, pedestrian detection method | |
| US20190204448A1 (en) | Imaging device and electronic device | |
| US20170007459A1 (en) | Vision aiding method and apparatus integrated with a camera module and a light sensor | |
| US9077907B2 (en) | Image processing apparatus | |
| JP4377439B1 (en) | Vehicle periphery monitoring device | |
| JP3574780B2 (en) | Vehicle safe driving support system | |
| CN110293965A (en) | Method of parking and control device, mobile unit and computer-readable medium | |
| CN106953977B (en) | A kind of monitoring method and system based on mobile terminal | |
| GB2500214A (en) | Robot vision apparatus and control method and corresponding land robot | |
| JP2009301494A (en) | Image processing unit and image processing method | |
| JP4609076B2 (en) | Moving object detection apparatus and moving object detection method | |
| US20120105221A1 (en) | Real-time warning system for vehicle windshield and performing method thereof | |
| CN113080550A (en) | Headband for recognizing obstacle and method for recognizing obstacle | |
| JP2010026601A (en) | Vehicle periphery monitoring device | |
| CN111383248B (en) | Pedestrian red light running judging method and device and electronic equipment | |
| JP5434277B2 (en) | Driving support device and driving support method | |
| JPWO2018230496A1 (en) | Map updating device, map updating system, map updating method, and program | |
| CN215350472U (en) | Headband for recognizing obstacle | |
| KR20120088320A (en) | Object recognition and for the visually impaired pedestrian guidance system | |
| CN114639230B (en) | Walking assistance system | |
| US11607362B2 (en) | Walking support system | |
| KR101924643B1 (en) | Recognition system for vehicle | |
| CN112472538A (en) | Artificial intelligence blind-guiding walking robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210709 |
|
| RJ01 | Rejection of invention patent application after publication |