Pedestrian detection and statistics integrated traffic light device based on human shape recognition
By integrating humanoid recognition and video display components in the traffic light device, real-time detection and warning of pedestrians are achieved, the problem of pedestrians running red lights is solved, and traffic safety and traffic management efficiency is improved.
Patent Information
- Application Number
- CN202420549951.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-21
- Publication Date
- 2025-03-18
- Estimated Expiration
- 2034-03-21
AI Technical Summary
During the use of existing traffic light devices, pedestrians often ignore traffic lights in order to hurry up, and running red lights leads to dangers. The existing reminder devices are not effective and cannot effectively prevent running red lights.
A traffic light device that integrates pedestrian detection and statistics based on humanoid recognition is designed, including a traffic light device main body, a pedestrian detection component for humanoid recognition and a video display component. The humanoid recognition component is flexiblely installed and adjusted through an image acquisition module, a movable universal ball and an electric telescopic rod. The video display component rotates through the display shaft and worm structure, which is convenient for warning pedestrians.
Through humanoid recognition technology, pedestrians are detected in real time, effectively preventing red lights and reducing traffic accidents; the flexible adjustment of video display components can better warn pedestrians, improve pedestrians' awareness and behavior of complying with traffic lights; count the number of pedestrians in real time and control the duration of signal lights through the network to improve the efficiency of traffic flow management.
Smart Images

Figure CN222636712U_ABST
Abstract
Description
Technical Field
[0001] The utility model relates to the technical field of urban road traffic intersections, in particular to a pedestrian detection and statistics-integrated traffic light device based on human figure recognition. Background Art
[0002] At the complex traffic intersections in the city, pedestrians running red lights is the most prominent and common traffic violation. This behavior not only poses a great danger to the personal safety of pedestrians, but is also the main cause of major traffic accidents.
[0003] In Chinese patent 202120070133.1, the utility model discloses an intelligent voice broadcast traffic light alarm pole based on mobile human shape detection and face recognition, the alarm pole includes a lamp pole, a traffic light assembly, a monitoring terminal, a human shape detection camera, a face recognition camera, a voice broadcast module, a clock control module and a wireless signal transmission module, the traffic light assembly includes a lamp body and a lamp body control unit, the monitoring terminal includes a mainboard, the human shape detection camera includes an electrically connected first camera assembly and a mobile human shape detection module, the face recognition camera includes an electrically connected second camera assembly and a face recognition module, the lamp body control unit is electrically connected to the first camera assembly, the mobile human shape detection module is electrically connected to the voice broadcast module and the clock control module respectively, the clock control module is electrically connected to the second camera assembly, and the face recognition module is electrically connected to the wireless signal transmission module. The utility model can effectively remind and supervise pedestrians crossing zebra crossings with traffic lights.
[0004] During the use of existing traffic light devices, some pedestrians often ignore traffic lights in order to save time, and running red lights may cause danger. Existing traffic light devices are equipped with some reminder devices, but the effect is not ideal, and the phenomenon of running red lights still exists.
[0005] Therefore, in order to solve the above problems, a traffic light device integrating pedestrian detection and statistics based on human figure recognition is proposed. Utility Model Content
[0006] In order to make up for the deficiencies of the prior art, the present invention solves the problem that during the use of the existing traffic light device, some pedestrians often ignore the traffic lights in order to save time, and running red lights may cause danger. The existing traffic light device will be equipped with some reminder devices, but the effect is not ideal.
[0007] The technical solution adopted by the utility model to solve its technical problems is: the pedestrian detection based on human figure recognition described in the utility model includes a traffic light device body, a pedestrian detection component for human figure recognition is arranged on the top of the traffic light device body, and a video display component is installed on the side of the traffic light device body, and a voice broadcast module is arranged on the top of the video display component; the pedestrian detection component for human figure recognition includes an image acquisition module, a movable universal ball, a universal ball slot, a fixed knob, an electric telescopic rod, a mounting base, and mounting screws, the bottom of the image acquisition module is fixedly connected with a movable universal ball, and the outer wall of the movable universal ball is snap-connected with the universal ball slot, and the side of the universal ball slot is threadedly connected with a fixed knob, the bottom of the universal ball slot is fixedly connected with an electric telescopic rod, and the bottom of the electric telescopic rod is fixedly connected with the mounting base, and the side of the mounting base is threadedly connected with the mounting screws.
[0008] Preferably, the fixed knob forms a threaded detachable structure through a universal ball slot and a movable universal ball, the image acquisition module forms a rotating structure through a movable universal ball and the universal ball slot, and the movable universal ball and the universal ball slot form a snap-fit structure.
[0009] Preferably, the mounting screw forms a threaded detachable structure with the mounting base and the main body of the traffic light device, the universal ball slot forms a lifting structure with the mounting base through an electric telescopic rod, and the mounting base and the main body of the traffic light device form a snap-fit structure.
[0010] Preferably, the video display assembly includes a video image display module, a display screen shaft, a worm gear body, a worm body, a positioning plate, and an adjustment crank; the side of the video image display module is movably connected to the display screen shaft, the bottom of the display screen shaft is fixedly connected to the worm gear body, and the side of the worm gear body is meshed with the worm body, one end of the worm body is provided with a positioning plate, and the other end of the worm body is installed with an adjustment crank.
[0011] Preferably, the video image display module forms a rotating structure through a display screen shaft, a worm gear body and a traffic light device body, and the worm gear body forms a rotating structure through a worm body, an adjustment crank and a positioning plate.
[0012] Preferably, a statistically integrated traffic light device is characterized by: comprising a traffic light body, wherein the traffic light body is mounted on the outer wall of the traffic light device body, and an electric control box assembly is installed at the bottom of the traffic light body; the electric control box assembly comprises an electric control box door panel, a door panel shaft, a switch handle, a clip slot, a switch clip, a clip spring, and a clip shell, one side of the electric control box door panel is movably connected to the door panel shaft, and the other side of the electric control box door panel is fixedly connected to the switch handle, and a clip slot is provided inside the switch handle, the inner wall of the clip slot is snap-connected with the switch clip, and one end of the switch clip is elastically connected to the clip spring, and the outside of the clip spring is snap-connected with the clip shell.
[0013] Preferably, the switch clip forms an elastic structure through a clip spring and a clip housing, and the switch clip and the clip slot form a clamping structure.
[0014] The utility model is beneficial in that:
[0015] 1. The fixed knob forms a threaded detachable structure with the movable universal ball through the universal ball slot, the image acquisition module forms a rotating structure with the movable universal ball and the universal ball slot, and the movable universal ball and the universal ball slot form a snap-fit structure, the mounting screw forms a threaded detachable structure with the main body of the traffic light device through the mounting base, the universal ball slot forms a lifting structure with the mounting base through the electric telescopic rod, and the mounting base and the main body of the traffic light device form a snap-fit structure, which is convenient for adjusting the installation height and angle of the image acquisition module to meet the requirements of red light running capture and pedestrian counting;
[0016] 2. The video image display module forms a rotating structure through the display screen shaft, the worm gear body and the traffic light device body, and the worm gear body forms a rotating structure through the worm body, the adjustment crank and the positioning plate, which is convenient for warning pedestrians and reducing the incidence of pedestrians running red lights. The switch clip forms an elastic structure through the clip spring and the clip shell, and the switch clip and the clip slot form a locking structure, which is convenient for sending data to the signal machine through the network to control the switching of the traffic light. When the traffic light is in the green light state, the device will count the number of pedestrians on the zebra crossing in real time, and send the data to the signal machine through the network to extend or shorten the current green light duration. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the utility model or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the utility model. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0018] Figure 1It is a schematic diagram of the three-dimensional structure of the utility model as a whole viewed from the front;
[0019] Figure 2 It is a schematic diagram of the enlarged structure of the pedestrian detection component of the human figure recognition of the utility model;
[0020] Figure 3 It is a schematic diagram of the enlarged structure of the video display assembly of the utility model;
[0021] Figure 4 It is an enlarged structural schematic diagram of the electric control box assembly of the utility model;
[0022] Figure 5 It is a schematic diagram of the exploded structure of the switch part of the electric control box assembly of the utility model.
[0023] In the figure: 1. Traffic light device body; 2. Pedestrian detection component for human figure recognition; 201. Image acquisition module; 202. Movable universal ball; 203. Universal ball slot; 204. Fixed knob; 205. Electric telescopic rod; 206. Mounting base; 207. Mounting screw; 3. Video display component; 301. Video image display module; 302. Display screen shaft; 303. Worm gear body; 304. Worm body; 305. Positioning plate; 306. Adjustment crank; 4. Voice broadcast module; 5. Traffic light body; 6. Electric control box component; 601. Electric control box door panel; 602. Door panel shaft; 603. Switch handle; 604. Clip slot; 605. Switch clip; 606. Clip spring; 607. Clip housing. DETAILED DESCRIPTION
[0024] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.
[0025] Embodiment 1
[0026] See also Figure 1 As shown, a pedestrian detection based on human figure recognition includes a traffic light device body 1, a pedestrian detection component 2 for human figure recognition is arranged on the top of the traffic light device body 1, and a video display component 3 is installed on the side of the traffic light device body 1, and a voice broadcast module 4 is arranged on the top of the video display component 3.
[0027] See also Figure 2As shown, a pedestrian detection based on human figure recognition, a pedestrian detection component 2 for human figure recognition, includes an image acquisition module 201, a movable universal ball 202, a universal ball slot 203, a fixed knob 204, an electric telescopic rod 205, a mounting base 206, and a mounting screw 207. The fixed knob 204 forms a threaded detachable structure with the movable universal ball 202 through the universal ball slot 203, the image acquisition module 201 forms a rotating structure with the universal ball slot 203 through the movable universal ball 202, and the movable universal ball 202 and the universal ball slot 203 form a snap-fit structure, the mounting screw 207 forms a threaded detachable structure with the traffic light device body 1 through the mounting base 206, and the universal ball slot 203 forms a snap-fit structure. The slot 203 forms a lifting structure with the mounting base 206 through the electric telescopic rod 205, and the mounting base 206 forms a locking structure with the traffic light device body 1. The mounting base 206 is stuck on the top of the traffic light device body 1 and is installed using the mounting screws 207. The orientation of the image acquisition module 201 is adjusted, and the image acquisition module 201 is rotated around the movable universal ball 202 to increase the effective shooting area. The fixing knob 204 is then tightened to fix the position of the image acquisition module 201, and the electric telescopic rod 205 is started to adjust the height of the image acquisition module 201, so as to facilitate the adjustment of the installation height and angle of the image acquisition module 201 to meet the requirements of red light running capture and pedestrian counting.
[0028] See also Figure 3 As shown, a pedestrian detection based on human figure recognition, a video display component 3, includes a video image display module 301, a display screen shaft 302, a worm wheel body 303, a worm body 304, a positioning plate 305, and an adjusting crank 306. The video image display module 301 forms a rotating structure with the traffic light device body 1 through the display screen shaft 302 and the worm wheel body 303, and the worm wheel body 303 forms a rotating structure with the positioning plate 305 through the worm body 304, the adjusting crank 306, and the adjusting crank 306 is rotated to drive the worm body 304 to rotate, and the worm body 304 drives the worm wheel body 303 and the display screen shaft 302 to rotate, so as to adjust the position of the video image display module 301. The position of the video image display module 301 can be adjusted according to the concentrated area of pedestrian flow, so as to warn pedestrians and reduce the incidence of pedestrians running red lights.
[0029] See also Figure 1 As shown, a pedestrian detection based on human figure recognition and a traffic light device with integrated statistics are characterized in that: it includes a traffic light body 5, the traffic light body 5 is installed on the outer wall of the traffic light device body 1, and an electric control box assembly 6 is installed at the bottom of the traffic light body 5.
[0030] See also Figure 5As shown, a pedestrian detection based on human figure recognition, an electric control box component 6, includes an electric control box door panel 601, a door panel shaft 602, a switch handle 603, a clip slot 604, a switch clip 605, a clip spring 606, and a clip shell 607. The switch clip 605 forms an elastic structure with the clip shell 607 through the clip spring 606, and the switch clip 605 and the clip slot 604 form a snap-fit structure. When the position of the switch clip 605 is moved, the clip spring 606 is squeezed and contracted. When the switch clip 605 leaves the clip slot 604, the electric control box door panel 601 can be opened for maintenance inside, so that data can be sent to the signal machine through the network to control the switching of the signal light. When the signal light is in the green light state, the device will count the number of pedestrians on the zebra crossing in real time, and send the data to the signal machine through the network to extend or shorten the current green light duration.
[0031] Working principle: First, clamp the mounting base 206 on the top of the traffic light device body 1, use the mounting screws 207 to install it, adjust the orientation of the image acquisition module 201, rotate the image acquisition module 201 around the movable universal ball 202, so that the effective area of its shooting is larger, then tighten the fixing knob 204 to fix the position of the image acquisition module 201, start the electric telescopic rod 205, and adjust the height of the image acquisition module 201. The image acquisition module 201 is a 9-megapixel high-definition camera, which is mainly used to monitor zebra crossings and capture pictures of pedestrians who run red lights and violate traffic rules. Next, turn the adjustment crank 306, the adjustment crank 306 drives the worm body 304 to rotate, and the worm body 304 drives the worm wheel body 303 and the display screen shaft 302 to rotate, so as to adjust the position of the video image display module 301. The position of the video image display module 301 can be adjusted according to the concentrated area of the flow of people. The video image display module 301 is a 37-inch LCD display screen, which is used for displaying pedestrian violation pictures and real-time video;
[0032] Next, the voice broadcast module 4 is a voice alarm speaker with an adjustable volume. It can broadcast the normal traffic light status and red light running warning. At the same time, the electric control box component 6 includes a power module, a signal light detection module, a main control machine processing module, a video storage module, etc. The main control machine module contains a human recognition analysis and system control program for identifying red light running behaviors and pedestrian counting functions, supports transmitting illegal data to the monitoring center, and supports statistical data and signal control machine linkage control of signal lights. When the electric control box component 6 needs to be maintained, the position of the switch clip 605 is moved. At this time, the clip spring 606 is squeezed and contracted. When the switch clip 605 leaves the clip slot 604, the electric control box door panel 601 can be opened for maintenance of the interior;
[0033] Next, the device uses video processing and human detection technology to automatically locate, track, detect, and identify pedestrians in the video in real time and frame by frame. By setting the identification area, it focuses on detecting pedestrians on the zebra crossing and in the waiting area at the intersection. The status of the traffic light is identified according to the traffic light signal detection module. When the traffic light is in the red light state and a pedestrian enters the zebra crossing and moves forward and backward, the capture program is started and the violation data is saved. At the same time, the number of people in the opposite waiting area is counted in real time, and the data is sent to the signal machine through the network to control the switching of the traffic light. When the traffic light is in the green light state, the device will count the number of pedestrians on the zebra crossing in real time, and send the data to the signal machine through the network to extend or shorten the current green light duration.
[0034] The above shows and describes the basic principle, main features and advantages of the utility model. Those skilled in the art should understand that the utility model is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principle of the utility model. Without departing from the spirit and scope of the utility model, the utility model may have various changes and improvements, and these changes and improvements fall within the scope of the utility model to be protected.
Claims
1. A pedestrian detection based on human figure recognition, characterized in that: The invention comprises a traffic light device body (1), wherein a pedestrian detection component (2) for human figure recognition is arranged on the top of the traffic light device body (1), a video display component (3) is installed on the side of the traffic light device body (1), and a voice broadcast module (4) is arranged on the top of the video display component (3); The pedestrian detection component (2) for human figure recognition comprises an image acquisition module (201), a movable universal ball (202), a universal ball slot (203), a fixed knob (204), an electric telescopic rod (205), a mounting base (206), and a mounting screw (207); the bottom of the image acquisition module (201) is fixedly connected to the movable universal ball (202), the outer wall of the movable universal ball (202) is snap-connected to the universal ball slot (203), the side of the universal ball slot (203) is threadedly connected to the fixed knob (204), the bottom of the universal ball slot (203) is fixedly connected to the electric telescopic rod (205), the bottom of the electric telescopic rod (205) is fixedly connected to the mounting base (206), and the side of the mounting base (206) is threadedly connected to the mounting screw (207).
2. The pedestrian detection based on human figure recognition according to claim 1, characterized in that: The fixed knob (204) forms a threaded detachable structure through a universal ball slot (203) and a movable universal ball (202); the image acquisition module (201) forms a rotating structure through the movable universal ball (202) and the universal ball slot (203); and the movable universal ball (202) and the universal ball slot (203) form a snap-fit structure.
3. The pedestrian detection based on human figure recognition according to claim 1, characterized in that: The mounting screw (207) forms a threaded detachable structure with the traffic light device body (1) through the mounting base (206), the universal ball slot (203) forms a lifting structure with the mounting base (206) through the electric telescopic rod (205), and the mounting base (206) forms a snap-fit structure with the traffic light device body (1).
4. The pedestrian detection based on human figure recognition according to claim 1, characterized in that: The video display assembly (3) comprises a video image display module (301), a display screen rotating shaft (302), a worm wheel body (303), a worm body (304), a positioning plate (305), and an adjusting crank (306); the side of the video image display module (301) is movably connected to the display screen rotating shaft (302), the bottom of the display screen rotating shaft (302) is fixedly connected to the worm wheel body (303), and the side of the worm wheel body (303) is meshed with the worm body (304); one end of the worm body (304) is provided with a positioning plate (305), and the other end of the worm body (304) is installed with the adjusting crank (306).
5. The pedestrian detection based on human figure recognition according to claim 4, characterized in that: The video image display module (301) forms a rotating structure through a display screen rotating shaft (302), a worm gear body (303) and a traffic light device body (1), and the worm gear body (303) forms a rotating structure through a worm body (304), an adjustment crank (306) and a positioning plate (305).
6. A traffic light device with integrated statistics, characterized in that: It comprises a traffic light body (5), wherein the traffic light body (5) is mounted on the outer wall of a traffic light device body (1), and an electric control box assembly (6) is mounted at the bottom of the traffic light body (5); The electric control box assembly (6) comprises an electric control box door panel (601), a door panel rotating shaft (602), a switch handle (603), a clip slot (604), a switch clip (605), a clip spring (606), and a clip housing (607). One side of the electric control box door panel (601) is movably connected to the door panel rotating shaft (602), and the other side of the electric control box door panel (601) is fixedly connected to the switch handle (603), and a clip slot (604) is provided inside the switch handle (603), the inner wall of the clip slot (604) is snap-connected with the switch clip (605), one end of the switch clip (605) is elastically connected to the clip spring (606), and the outside of the clip spring (606) is snap-connected with the clip housing (607).
7. The traffic light device with integrated statistics according to claim 6, characterized in that: The switch clip (605) forms an elastic structure through a clip spring (606) and a clip housing (607), and the switch clip (605) and the clip slot (604) form a snap-fit structure.
Citation Information
Patent Citations
Intelligent voice broadcast traffic light alarm rod based on mobile human shape detection and face recognition
CN214202651U