76 results about "Infrared vision" patented technology

The invention discloses a high-precision defect detection system for a track inspection robot, which relates to the technical field of track inspection and comprises a multi-mode visual acquisition module, a time sequence synchronization module, a data fusion processing module and a defect identification output module, by adopting a multi-modal visual fusion detection technology, various modal visual technologies of visible light vision, infrared vision and ultraviolet vision are combined, fusion processing is carried out on all modal image data, visual defects such as cracks and abrasion on the surface of a track can be clearly recognized through visible light vision, and the visual performance of the track is improved. The infrared vision can detect temperature abnormity of a track component to find out potential poor contact and other problems, the ultraviolet vision can be used for detecting corona discharge and other phenomena, track information is comprehensively obtained, the accuracy and reliability of defect recognition are effectively improved, defects which are difficult to find in a single mode can be detected, and the detection efficiency is improved. And powerful support is provided for safe operation and maintenance of the track.

The invention relates to the technical field of unmanned aerial vehicle inspection, and provides an unmanned aerial vehicle-based forest fire prevention inspection and disposal method, device and system. When an inspection unmanned aerial vehicle equipped with a multi-modal sensor is deployed to cruise according to a preset route, a visible light camera of the inspection unmanned aerial vehicle continuously collects forest region videos and transmits the videos to edge computing equipment of an inspection airport; fire hazards are analyzed in real time through a target recognition algorithm, and when a fire source is detected, position information is reported to a background terminal immediately; the system automatically dispatches the nearest fire extinguishing airport to dispatch the fire extinguishing unmanned aerial vehicle, and secondary accurate positioning is performed on a fire source by using the airborne infrared vision module, so that accurate throwing of the fire extinguishing bomb is ensured. The whole system enhances the real-time analysis capability through the edge computing device, breaks through the single-machine computing power limitation, also realizes the full-process automation from fire behavior recognition to fire extinguishing treatment, and significantly improves the response efficiency and treatment safety of forest fire prevention.

The invention provides a multi-vision fusion mining explosion-proof equipment explosion-proof performance evaluation method, and relates to the technical field of intelligent detection, and the method comprises the steps: 1, obtaining flame images of visible light and infrared light; the method specifically comprises the steps that flame images are captured at the same time through an industrial camera and a thermal imager, the images of the industrial camera are stored as a visible light image sequence, the images of the thermal imager are stored as an infrared image sequence, and a time label is bound with each frame of image; step 2, data processing of visible light and infrared images; step 3, optimizing the single-vision image data; the method specifically comprises the following steps: optimizing the features of a visible light image; a feature optimization step of the infrared image; standardizing the feature representation; step 4, feature level fusion of visible light and infrared vision; comprising a feature matrix construction step and a feature level fusion step. And step 5, quantitative evaluation of the explosion-proof performance is carried out based on the visual features.

A vehicle laminated glazing includes a first extraclear glass sheet (exterior glazing), a lamination interlayer and a second glass or plastic sheet (interior glazing) with a traversing hole.

The invention discloses an inspection method of an industrial inspection system based on multi-modal fusion, which belongs to the technical field of industrial inspection, and comprises the following steps: S1, obtaining positioning data of a node to be positioned by using an HDS-TWR distance measurement algorithm and a Taylor full centroid algorithm, and outputting a positioning coordinate; s2, using a sensor to measure the acceleration and angular velocity of the inspection system so as to align the motion and posture for evaluation; s3, improving a Kalman filtering algorithm to enable an output prediction result to be close to a true value; s4, infrared-vision dual-mode cooperative tracking is adopted, and meanwhile, a time synchronization displacement compensation mechanism is utilized to calculate a relative displacement difference between two tracking modes, and dynamic calibration is carried out; s5, a YOLOv8 model is adopted to process video frames or pictures collected in the inspection process, a target box and category probability are output, and finally an inspection result is obtained; according to the inspection method of the industrial inspection system based on multi-modal fusion, a high-precision and low-delay automatic inspection solution is provided for severe environments such as mines and nuclear power stations.

The invention discloses a photovoltaic panel intelligent cleaning system based on an unmanned aerial vehicle and a cleaning method thereof, and the cleaning system comprises the unmanned aerial vehicle which is connected with a GPS for positioning; the laser radar is used for constructing a three-dimensional model of the photovoltaic base station, and the laser radar is connected to the unmanned aerial vehicle; the infrared visual sensor is used for acquiring distribution information of stains on the surface of the photovoltaic panel; the cleaning assembly is used for cleaning stains on the surface of the photovoltaic panel, and the cleaning assembly is connected to the unmanned aerial vehicle; the controller is used for planning a flight route based on the three-dimensional model and the stain distribution information and sending the flight route to the unmanned aerial vehicle, the controller is connected to the unmanned aerial vehicle, and the GPS, the laser radar and the infrared vision sensor are all connected with the controller. By arranging the cleaning system, the cleaning efficiency of the photovoltaic panel is improved.

The invention discloses a device and a method for mobile detection of internal and external defects of a pipeline weld joint based on infrared-vision, and aims to solve the problems of poor flexibility of an existing device and low efficiency and high false detection rate of traditional detection. The device comprises a moving trolley, a camera mechanism and a laser excitation mechanism. The moving trolley is a carrier; the laser excitation mechanisms are installed on the two sides of the front end of the trolley, pose regulation and control are achieved through the transmission and tail end fine adjustment mechanism, and stable thermal excitation is provided. The camera mechanism is installed above the trolley, comprises a transverse / longitudinal movement and fine adjustment mechanism, can deflect and rotate to achieve accurate imaging, and is compact in overall structure and high in flexibility. The method comprises the following steps: constructing a space-time two-dimensional synchronous acquisition framework by adjusting a detection position; segmenting the infrared data by adopting a convolutional neural network containing attention weight, extracting a temperature anomaly region and core feature parameters, and inputting the temperature anomaly region and the core feature parameters into a Transform model for prediction after environmental parameter correction; and in combination with a temperature difference and area grading judgment rule, inner and outer defect grades are distinguished, efficient detection is realized, the detection rate is high, and the false detection rate is low.

The invention relates to a wildlife intelligent monitoring device and method based on multi-modal fusion and an ad hoc network, and relates to the technical field of wildlife monitoring. Through fusion of binocular infrared vision and microphone array hearing, more comprehensive and more accurate wild animal activity information can be obtained, and the limitation of a single sensor is overcome; intelligent false trigger screening and species identification are realized through a WS-YOLO algorithm of an equipment end, manual intervention is reduced, and data processing efficiency is improved; through the ad hoc network technology, the monitoring system can cover a wider network-free area, and equipment deployment is more flexible and is not limited by network infrastructures; by reducing false triggering, local intelligent processing and efficient data transmission, the cost of data storage, transmission and later manual analysis is reduced. The method provides a more powerful technical means for dynamic monitoring of wild animal populations, behavioral ecology research, biodiversity protection and the like, and has important ecological protection and scientific research values.

The invention provides a conveyor state monitoring device and method based on machine vision, and the device comprises a monitoring cabin which can autonomously reciprocate along a rigid guide rail at one side of a conveyor, automatic charging piles are arranged at the two ends of the guide rail, and the monitoring cabin is integrated with an infrared thermal imager, a visual camera and a sound sensor. A vibration sensor and an incremental photoelectric encoder are arranged along the line. A processor is arranged in the monitoring cabin, and time alignment, feature extraction, fusion of a multi-scale feature fusion model and three-level decision judgment are carried out on infrared signals, visual signals, sound signals and vibration signals on the basis of encoder timestamps. According to the method, fault diagnosis and false alarm filtering are achieved by controlling inspection of a monitoring cabin, multi-source data preprocessing, confrontation feature fusion network processing and three-level progressive judgment, and accurate positioning is achieved based on the mapping relation between encoder pulses and support numbers. According to the invention, the monitoring coverage range is expanded, the endurance continuity is improved, the data transmission stability is improved, and the false alarm rate is reduced.

An infrared vision positioning method for concrete pumping liquid level in tube of steel tubular arch bridge is provided. In this method, the perspective geometry algorithm is used to construct the pose transformation matrix to obtain the relative pose between the camera and the arch bridge steel pipe, the image is transformed into orthography by perspective transformation, and the real coordinates of the liquid level in the infrared image can be directly solved by the scale, so as to realize the accurate positioning of the liquid level; the proposed method is simple in structure and can realize real-time operation, which greatly improves the calculation efficiency of coordinates in infrared images, compared with the conventional knocking method, the advantage is that it does not require staff in an overhead operating, and the feedback of the liquid level position can be faster and more efficient.

The invention relates to a smoke identification and classification early warning method, which comprises the following steps: carrying an infrared camera, an infrared spectrum sensor and a temperature and humidity sensor on an unmanned aerial vehicle, and carrying out a smoke inspection activity on a set target area; the method comprises the following steps: acquiring an infrared visual image, infrared spectrum data and environmental parameters of a target area by using an unmanned aerial vehicle, and preprocessing the acquired data; the infrared spectrum data comprises the concentration of CO2 and the concentration of CO, and the environmental parameters comprise the temperature, the humidity and the wind speed; multi-modal data fusion is carried out on the preprocessed data to construct a fusion feature vector, and a trained deep learning classification model is used to identify the smoke type according to the fusion feature vector; and determining an early warning level according to the identified smoke type, and dynamically realizing early warning triggering based on the early warning level and a set grading response rule. According to the method, accurate distinguishing and early warning decision making can be carried out on smoke in the urban comprehensive treatment complex environment.

The invention discloses a mobile audio-visual cooperative unmanned aerial vehicle detection system, and belongs to the technical field of intelligent detection and automatic control. The system comprises a mobile ROS unmanned vehicle platform, an audio-visual perception module, an embedded processing unit and an execution mechanism. The mobile ROS unmanned vehicle platform comprises a motion control system, a serial port communication module and a wireless communication module; the audio-visual perception module comprises an infrared visual acquisition unit and a four-channel audio acquisition array and is used for acquiring infrared image information and acoustic signals of the unmanned aerial vehicle; the embedded processing unit comprises a multi-modal data fusion processor and a motion cooperation controller and is used for synchronously processing the infrared image information and the acoustic signal and generating a control instruction; the execution mechanism comprises a two-degree-of-freedom steering engine holder and a self-adaptive cruise system. According to the invention, through audio-visual cooperation and dynamic mode switching, a fixed detection scene is not needed, continuous tracking of the unmanned aerial vehicle and blind area complement detection can be realized, and detection continuity and accuracy are improved.

The application discloses an infrared image generation method and system based on a physical prior constraint generative adversarial network, relates to the field of infrared image generation, and aims to solve the problems of insufficient physical reality and lack of representation ability of infrared radiation characteristics of the existing infrared image generation method. The application first designs a physical prior knowledge learning network, which is used to learn the prior representation related to the infrared radiation characteristics from the infrared image, and realizes the prediction of the infrared radiation related parameters through a deep learning network. Secondly, a generative adversarial network based on the physical prior constraint is designed based on the proposed physical prior knowledge learning network, the physical prior features are introduced into the image generation process, and the learning ability of the generator to the overall distribution of the infrared radiation and the representation ability of the generator to the infrared radiation characteristics are enhanced. The method breaks through the limitation that the traditional generator only relies on shallow texture mapping. The application is suitable for the fields of visible light to infrared image generation, infrared vision algorithm research and development.

The application provides a non-contact respiratory characteristic monitoring device, and relates to the technical field of respiratory medical apparatuses, which comprises the following: two gear plates and a driving short shaft are sequentially installed on the rod segment of the L-shaped mounting rod away from the T-shaped support rod from top to bottom, the two gear plates are arranged in parallel and mesh with each other, and the driving short shaft is in transmission connection with the lower gear plate; a motor is fixedly installed on the rod segment of the L-shaped mounting rod connected with the T-shaped support rod, a six-rib transmission shaft is slidably installed in the rotating shaft of the motor, the six-rib transmission shaft is in plug-in connection with the worm in normal state, the six-rib transmission shaft is in plug-in connection with the driving short shaft when being upwardly and obliquely slid and is separated from the worm at the same time. The transmission of the six-rib transmission shaft, the motor can be used as a common driving motor for driving the infrared visual camera and the thermal imaging lens to adjust the shooting angle and driving the two cleaning sponges to rotate and wipe, which is helpful to reduce the manufacturing cost of the monitoring device as a whole.

The invention provides a high-integration uncooled infrared heterogeneous intelligent processing device, and relates to the technical field of intelligent infrared imaging and processing. The device comprises an infrared assembly used for obtaining an infrared image; the infrared vision chip circuit board comprises an input and output bus; the field programmable gate array system circuit board comprises: a buffer array; a field programmable gate array; a flash memory; and the power interface circuit board comprises a plurality of interface circuits connected with the field programmable gate array, and the plurality of interface circuits are used for receiving and outputting various types of data. The high-integration non-refrigeration infrared heterogeneous intelligent processing device provided by the invention is based on a high-energy-efficiency non-refrigeration infrared visual component and a programmable logic device heterogeneous hardware architecture, does not need operation of an operation system, is small in size, light in weight, high in speed and low in time delay, has in-situ intelligent information processing and storage capability, and is suitable for popularization and application. And the system can be conveniently integrated into an unmanned system with a limited space.

The application discloses a multi-modal fusion-based industrial inspection system inspection method, and belongs to the technical field of industrial inspection, comprising the following steps: S1, obtaining positioning data of a to-be-positioned node by using an HDS-TWR ranging algorithm and a Taylor total centroid algorithm, and outputting positioning coordinates; S2, measuring the acceleration and angular velocity of the inspection system by using a sensor, so as to evaluate the alignment movement and posture; S3, improving a Kalman filtering algorithm, so that the output prediction result is close to the true value; S4, adopting infrared-vision dual-mode cooperative tracking, and simultaneously using a time synchronization displacement compensation mechanism to calculate the relative displacement difference of the two tracking modes and perform dynamic calibration; and S5, processing video frames or pictures collected in the inspection process by using a YOLOv8 model, outputting a target frame and a category probability, and finally obtaining an inspection result; the multi-modal fusion-based industrial inspection system inspection method provided by the application provides a high-precision and low-delay automatic inspection solution for mines, nuclear power plants and other harsh environments.

The invention relates to the technical field of image recognition, in particular to a tunnel lining hollowing imaging method and system based on infrared vision fusion, and the method comprises the steps: carrying out the synchronous triggering collection through an infrared thermal imager and a visible light camera in a set mode along the axis of a tunnel, and obtaining an infrared image and a visible light image; feature point extraction and matching are carried out on the infrared image and the visible light image, a projection matrix is calculated based on successfully matched feature point pairs, and a registration visible light image is generated; carrying out the recognition and extraction of a hollowing feature region of the registered visible light image, and carrying out the fusion based on an obtained hollowing feature mask, and obtaining a hollowing fusion imaging image; and a three-dimensional point cloud model of the tunnel lining is generated based on the visible light image, and the hollowing fusion imaging graph is mapped to the three-dimensional point cloud model to mark hollowing, so that a temperature abnormal area can be quickly and accurately corresponding to the specific position of the tunnel lining.

The invention discloses a multi-camera cooperative state estimation method based on active infrared visual features, and belongs to the technical field of image processing and computer vision. The existing visual marking technology depends on ambient light and is poor in performance under dark light or complex illumination, the observation visual field of a single camera or a fixed camera is limited, distortion exists, and consequently the pose resolving precision and robustness are insufficient. According to the method, active infrared visual feature marking is adopted, dependence on ambient light is avoided, and feature point information is stably provided. And efficient and accurate feature point identification and matching are realized through multi-camera collaborative observation in combination with binarization processing of dynamic threshold adjustment, geometric feature screening and a matching algorithm. And carrying out pose calculation by using a PnP algorithm, and checking the goodness of fit between the axis and the gravity direction. Meanwhile, multiple cameras are dynamically scheduled to rotate cooperatively according to the observation quality, and the observation view is expanded. The method is mainly used for accurate positioning of targets such as an unmanned aerial vehicle, significantly improves the environmental adaptability and observation stability of the system, reduces the deployment cost, and improves the pose calculation precision and robustness.

The invention discloses a field all-terrain special target intelligent searching vehicle, which relates to the field of intelligent mobile equipment, and comprises a front-section module vehicle body connected with a rear-section integrated vehicle body through a hinge linkage mechanism; the front-section module vehicle body comprises a vehicle frame, a first-stage driving system and a second-stage driving system. The two sides of the vehicle frame are each provided with a rotationally-connected planet carrier. The primary driving system is used for driving the main gear to rotate; the output end of the secondary driving system is eccentrically connected with the planet carrier, and the secondary driving system is used for outputting eccentric torque for the planet carrier so as to drive the planet carrier to rotate relative to the frame; a multi-degree-of-freedom rotating arm is further arranged on the rear-section integrated vehicle body, and an infrared vision device is arranged on the multi-degree-of-freedom rotating arm. By the adoption of the scheme, dynamic obstacle crossing can be achieved through the front-driving front-section module vehicle body, and altitude difference terrains are overcome; and multi-angle infrared detection can be carried out, and the system is widely applied to tasks such as search, investigation and rescue in a complex field environment.

A laminated glazing of a vehicle includes a first extra clear glass sheet (exterior glazing), a lamination interlayer and a second glass sheet (interior glazing) with a through-hole in this second sheet including a mineral piece.

The invention discloses an infrared-vision cooperative tracking navigation method applied to a mobile robot and a related device, and relates to the field of robot navigation. Judging whether the infrared tracking is in a normal state or a failure state: in the normal state, generating an infrared tracking motion control signal in combination with a path surface reflected light intensity analog signal and a PID control algorithm so as to control the mobile robot to perform tracking motion; and in a failure state, starting a top camera to acquire a path image, and generating a visual tracking motion control signal in combination with the path surface image and a PID control algorithm so as to control the mobile robot to perform tracking motion. Through automatic conversion and synergistic effect of infrared and visual tracking, stable and accurate tracking navigation is realized, and the problem that tracking stability and accuracy are difficult to consider in the current tracking navigation field is solved.

The invention discloses an infrared safety belt applied to normative wearing of an infrared visual detection safety belt. The safety belt comprises warp yarns and weft yarns, the warp yarn comprises first polyester FDY high-tenacity yarn and second polyester FDY high-tenacity yarn, the first polyester FDY high-tenacity yarn is the polyester FDY high-tenacity yarn with the reflectivity larger than or equal to 70%, and the second polyester FDY high-tenacity yarn is the polyester FDY high-tenacity yarn with the reflectivity lower than 30%; according to the black or colored infrared safety belt produced by the preparation method, the identification degree under an infrared camera can be greatly improved, and the problem of misjudgment under the condition that the infrared camera detects a safety belt system due to insufficient light or passenger clothes and a braid are made of the same material is solved.

The application belongs to the technical field of cleaning unmanned aerial vehicles, and discloses a multi-mode intelligent cleaning unmanned aerial vehicle system suitable for photovoltaic panels; the system comprises an unmanned aerial vehicle and a cleaning control unit; the unmanned aerial vehicle is provided with an infrared vision sensor, a laser radar and a cleaning module; the cleaning module is arranged at the bottom of the unmanned aerial vehicle; the cleaning control unit comprises an AI control navigation module; the AI control navigation module is arranged at the central position of the unmanned aerial vehicle body and connected with a flight control bus; the infrared vision sensor and the laser radar are fused to accurately identify the contaminated area; in combination with the parameterized control of the cleaning execution mechanism, the system can maintain good coverage and adhesion under the wind field, reduce the consumption of cleaning agents and water, and improve the cleaning quality and system reliability.

The application discloses a kind of low-illumination condition fast moving target multi-view cooperative tracking method and device, the method includes low-illumination condition fast moving target multi-view tracking algorithm and unmanned aerial vehicle cluster cooperative tracking algorithm;Multi-source environment perception is carried out using millimeter wave radar sensor, RGB vision sensor and infrared vision sensor carried by unmanned aerial vehicle;Multi-source perception data is normalized in time and space dimensions by three space-time heterogeneous alignment algorithm;Multi-source fusion perception data after space-time normalization is input into multi-source fusion perception feature calculation network to calculate the world coordinates of the tracked target under the current frame;The calculation result is compared with the calculation result of last frame, to judge the change of the position and moving direction of the tracked target in world coordinate system;The world coordinate information of the tracked target is shared through cluster communication, and the trajectory of unmanned aerial vehicle cluster is formulated and updated using multi-agent reinforcement learning, to realize unmanned aerial vehicle cluster cooperative tracking.

This document relates to a connecting element (10) comprising a first part (20a) and a second part (20b) manufactured by additive manufacturing, the first part (20a) comprising a first frame (21a) intended to be fixed to one of two parts, the second part (20b) comprising a second frame (21b) intended to be fixed to the other of two parts, the first part (20a) comprising at least one first half-arm (23) extending from the first frame (21a) in a connection direction (X), each of said at least one first half-arm (23) comprising a tubular cavity (25) housing at least one portion (26) of a second half-arm (24) of the second part (20b), the second half-arm (24) extending from the tubular cavity (25) to the second frame (21b) in the connection direction (X), an elastomer (30) being annularly intercalated in the tubular cavity (25) between the first half-arm (23) and the second half-arm (24).

The invention belongs to the technical field of transfer robot obstacle avoidance, and particularly relates to a visual obstacle avoidance method for a transfer robot in a roll-on-roll-off ship in a low-illumination environment. The method comprises the steps that multi-source data are collected, the collected multi-source data are preprocessed, and the multi-source data comprise infrared images and laser radar point cloud data; performing target detection on the infrared image, and identifying an obstacle and a type in the infrared image; for the laser radar point cloud data, using an RANSAC plane fitting algorithm to calculate the height of a ground projection, and identifying an obstacle in the laser radar point cloud data; the infrared vision weight and the laser radar weight during fusion are dynamically adjusted according to the ambient illuminance, and obstacles in the infrared image and obstacles in the laser radar point cloud data are fused; and based on the position of the obstacle, the transfer robot avoids the obstacle during path planning.

The invention provides a programmable visible light infrared visual chip, and relates to the technical field of visible light and infrared visual imaging and visual information processing. Comprising a visible light-infrared detector array; a pixel-level readout circuit array; a sensor digital control circuit; a visible light-infrared image preprocessor; a visible light-infrared image heterogeneous processor; a data output interface circuit; and the metal column array is used for carrying out three-dimensional stacking interconnection on the visible light-infrared detector array, the pixel-level reading circuit array, the visible light-infrared image preprocessor and the visible light-infrared image heterogeneous processor. According to the method, through three-dimensional heterogeneous integration of the visible light-infrared detector array and the pixel-level reading circuit array, a large-scale visible light-infrared visual imaging task is realized.

According to the gingival knife capable of being positioned by the infrared vision system, a marker capable of being positioned by the infrared vision system is arranged on a gingival knife handle, space registration of the gingival knife and an optical tracker can be completed, the incision position and range of the gingival knife can be recognized and tracked, and therefore surgical operation of clinicians is facilitated; the invention relates to an identification frame, which is used for preventing soft tissue from being processed in an expanded range so as to reduce wounds, and is characterized by comprising an outer sleeve handle which sleeves an embedded handle extending upwards from the neck part of a knife body, a working end flap turning part and a working end cutting part which sequentially extend downwards from the neck part of the knife body, and an identification frame main rod which extends upwards from the top surface of the outer sleeve handle, an identification frame snakelike curve belt is coiled on the identification frame main rod in a winding manner in a step-by-step unfolding manner from bottom to top and crossing boundaries left and right, at least five infrared visual identification points are distributed on the identification frame snakelike curve belt, and a triangle formed by any three infrared visual identification points is different from a triangle formed by any other three infrared visual identification points.

The invention discloses a multi-sensor fusion positioning system and method for a shield cutterhead in-situ repair robot, and the system comprises a six-axis IMU sensor, a deflection angle measuring instrument, a GNSS positioning instrument and a UWB positioning module which are disposed on the shield cutterhead in-situ repair robot, and an end effector of the shield cutterhead in-situ repair robot is connected with a mounting seat. A driving motor is embedded in the mounting seat, the power output end of the driving motor is connected with a rotating disc, and a central processing unit, and a three-probe ultrasonic range finder, an infrared vision imager and a camera monitor which are connected with the central processing unit are fixed on the rotating disc; the method comprises the steps of time synchronization, short-time pose calculation of six IMU sensors, UWB redundancy positioning, ultrasonic ranging anti-interference, CAD-assisted vision SLAM and multi-sensor data fusion module tight coupling factor graph optimization. The method can be suitable for extreme working conditions of in-situ repair of the shield cutter head, and high-precision positioning is achieved.

The invention provides a method and a device for identifying and positioning a marked object based on infrared vision, and the method comprises the steps: obtaining an infrared image which is shot by equipment and comprises an infrared reflection point, detecting the infrared reflection point, and determining the pixel coordinate information of the infrared reflection point; any one of the infrared reflection points is selected as a candidate point, and the candidate point and the nearest infrared reflection points are selected to construct a mark point set; determining a plurality of direction identification points and id identification points of the marked pattern according to the distance between the infrared reflection points; constructing a mark number according to the position of each id identification point in the mark graph; and determining 3D coordinate information of the marked graph according to the mark number, carrying out PnP solution on the 3D coordinate information and the pixel coordinate information of the identification points in all directions, and calculating to obtain the pose of the equipment relative to the marked graph. According to the method, the infrared reflective points are used for identifying and positioning the marked graph, so that the influence of visual marking on the environmental aesthetics is reduced, the adaptability to illumination change is enhanced, and the robustness of identifying the marked graph is improved.