402 results about "Shooting range" patented technology

The embodiment of the invention provides a multi-mode unmanned material checking method based on combination of RFID and machine vision, the method is applied to a mobile module and a camera module, an RFID read-write module is arranged on a mobile trolley, and the method comprises the following steps: in response to movement of the mobile module, the RFID read-write module scans a target material to obtain RFID identification data, and filters and de-duplicates the RFID identification data to obtain a target material; an RFID identification result is determined; dividing a shooting range of the camera module based on a scanning area of the RFID read-write module, and detecting a material box and a material surface sheet label in video image data when the video image data is shot; and identifying the material surface sheet label to obtain material data information, and matching the material data information with the RFID identification result to obtain a multi-modal material matching result.

The application discloses a kind of visual-based end mill flank wear detection method and its image acquisition device, method includes fixing tool on the tool holder of image acquisition device, and the wear area of tool is observed by microscope of image acquisition device and S is photographed End mill flank wear picture under multiple shooting angles;Contrast the topography of tool flank face in the picture shot before and after wear, measure the wear of tool flank face in the picture shot, obtain S group of tool wear data under different shooting angles;Establish the mathematical model of tool wear and shooting angle, solve the only fitting function describing the change of tool wear with shooting angle;Draw the image of fitting function y (x) in the shooting range K, solve image peak value.The maximum wear of tool can be obtained simply, intuitively and accurately by the application.Under the premise of image acquisition automation, automatic measurement of tool wear can be realized, and has high engineering application value.

The invention provides a measurement method and a measurement system, and relates to the technical field of measurement. The measurement method comprises the following steps of: S1, aligning shooting centers of a plurality of photogrammetric assemblies with a reference point; in the step S2, a conversion relation between a photogrammetry assembly coordinate system and a base station coordinate system is calibrated; in the step S3, intersection measurement is carried out on the to-be-measured point, and coordinates of the reference point and the to-be-measured point in the base station coordinate system are calculated; s4, calculating the coordinates of the reference point and the to-be-measured point in the world coordinate system; in the step S5, the control assembly is used for controlling the rotating assembly to drive the photogrammetry assemblies to rotate until the shooting centers of the multiple photogrammetry assemblies are aligned with the point to be measured; a new reference point is determined in the step S6; and the steps S3-S6 are repeated in the step S7, so that the coordinates of all the to-be-measured points in the world coordinate system are calculated, automatic tracking measurement of the multiple to-be-measured points can be achieved, the photogrammetry assembly can be controlled to rotate, and the shooting range of the photogrammetry assembly can be expanded.

The embodiment of the invention provides a stamping part online detection system, visual detection equipment, a detection method and a device. The system is used for detecting stamping parts moving on a conveying belt. Comprising visual detection equipment, first position detection equipment and control equipment, the visual inspection equipment comprises a follow-up mechanism, a camera shooting mechanism and a first controller, the first controller controls the follow-up mechanism to enable the camera shooting mechanism to move synchronously with the stamping part under the condition that the stamping part enters the shooting range of the camera shooting mechanism, and controls the camera shooting mechanism to collect an image of the stamping part in the synchronous moving process of the camera shooting mechanism and the stamping part. The stamping part is detected based on the collected image, and a detection result is obtained; the first position detection equipment is used for detecting the position of the stamping part on the conveying belt, and the control equipment is used for receiving a detection result sent by the first controller. On-line detection of the stamping parts moving along with the conveying belt on the stamping part production line is achieved.

The invention discloses a vehicle position alignment and internal transverse movement widening mechanism which comprises a vehicle plate, a displacement unit, a follow-up assembly, a photographing device, a selection key and a control unit. The displacement unit is composed of a motor speed reducer assembly, a clutch assembly, a first driving assembly and a second driving assembly. The vehicle plate is divided into two sides by a longitudinal center line, a first driving assembly and a second driving assembly which are composed of a driving roller and a self-driving transmission pair are arranged on one side, and two sets of follow-up assemblies are arranged on the other side; the shooting range of the shooting device comprises an area above the vehicle plate outer frame, and obtaining relative position information of the vehicle on the vehicle plate; the selection key is used for determining the vehicle plate with the vehicle position aligned or determining the vehicle plate with the interior transversely-moving widened and the transversely-moving direction. The control unit instructs related parts to work, the motor reducer assembly and the clutch assembly are matched, position alignment is achieved by rotating and transversely moving a vehicle, and the width size of a driver side entrance and exit is remarkably increased through internal transverse moving widening; the related scheme is applied to lifting transverse moving, multi-parking-space simple lifting new product and equipment updating and transformation, and is also applied to plane parking spaces.

The invention relates to the technical field of unmanned aerial vehicle remote sensing surveying and mapping and building information identification, and discloses a building surveying and mapping method and system based on unmanned aerial vehicle remote sensing, and the method comprises the following steps: determining the shooting range of an unmanned aerial vehicle according to task requirements, setting shooting parameters, and operating the unmanned aerial vehicle to carry out the shooting operation in the shooting range of the unmanned aerial vehicle. The method comprises the following steps: carrying out batch preprocessing on images obtained by aerial photography to obtain preprocessed image data, carrying out data integration on the preprocessed image data, carrying out spatial triangulation calculation on the integrated image data, constructing a three-dimensional model of a target building according to a triangulation calculation result, and carrying out precision analysis on the three-dimensional model to obtain a three-dimensional model of the target building. A precision analysis result is transmitted to the man-machine interface module, a three-dimensional model construction method of the target building is data cluster operation, the server issues an operation task to a plurality of hosts through a local area network, the constructed three-dimensional model of the target building is processed, and a vertical view of the target building is drawn.

The invention relates to the technical field of intelligent interaction, in particular to an intelligent interaction training robot target range system and method. According to the method, the recursive optimization algorithm is combined to analyze the action point positions of the trainee and the target geometric parameters, the characteristic values of the relation between the actions of the trainee and the target position are extracted, the preferential shooting target state set is established through position vector calculation and priority ranking, the accuracy and dynamic adaptability of target selection are improved, and the target selection accuracy and dynamic adaptability are improved. Through interpolation calculation of the speed between target vehicle track nodes and displacement node sequence adjustment, and through a simulated annealing algorithm, analyzing the relation between the action deviation degree of a trainer and shooting track intersection points, precisely marking the directional deviation and amplitude of shooting actions, and generating a shooting action deviation result; the correction efficiency and feedback precision of the shooting action are improved, the optimal hit position is extracted by combining discrete value calculation of hit point track distribution and dense interval marking, and a trainer is helped to clarify the hit rule and optimize the shooting strategy.

The embodiment of the invention provides a planning method and device for an unmanned aerial vehicle route and a storage medium. The planning method comprises the steps of determining a view angle range of the unmanned aerial vehicle for each sub-region in a flight region; determining an actual shooting range of the unmanned aerial vehicle for each sub-region according to the view angle range; determining a surrounding rectangle where the flight area is located; determining a first center point according to the surrounding rectangle and the standby position of the unmanned aerial vehicle; determining a plurality of circular trajectories of the unmanned aerial vehicle for the flight area according to the actual shooting range, the visual angle range and the first center point; and determining a flight route of the unmanned aerial vehicle for the flight area according to the plurality of circular trajectories. The method can reasonably plan the flight route according to the terrain, effectively shortens the route distance under the condition of ensuring the coverage rate, and effectively reduces the energy consumption of the unmanned aerial vehicle.

The invention discloses a light weapon shooting training intelligent target range data processing method and system, and relates to the technical field of target range data processing, and the method comprises the following steps: constructing a nanosecond-level unified time baseline, and carrying out the synchronous collection of multi-source sensing signals of a shooting training target range through a high-resolution optical array and an acoustic sensing matrix, and performing time synchronization and delay compensation on each sensing signal through a phase alignment mechanism to form a unified sensing base plane for multi-target recognition. According to the method, high-precision synchronous acquisition and interference feature stripping are realized by constructing a nanosecond-level unified time base line and fusing multi-source sensing, and the target distinguishing and recognition precision under a complex background is remarkably improved; and meanwhile, a space-time coupling identification and anti-fact playback mechanism is combined, a dynamic credibility map is generated, phase conjugate regulation and control are implemented, an identification and correction closed loop is formed, misjudgment and drift are effectively reduced, and stable tracking and continuous identification in a multi-target scene are ensured.

The invention relates to the field of high-altitude object throwing detection and early warning, and discloses a high-altitude object throwing prevention detection and early warning system based on an intelligent building, and the system comprises a data collection and processing module which obtains a physical structure factor, a behavior mode factor and an environment state factor through collection and calculation; the risk early-warning module is used for eliminating abnormal values of the risk data, calculating risk early-warning values, comparing the risk early-warning values with a threshold value, dividing risk levels, executing an early-warning strategy according to the risk levels, analyzing and optimizing the data by using a model, and dynamically correcting the early-warning values; the dynamic optimization module is used for smoothing short-term fluctuation through a calibration formula by using a historical risk early warning value; calculating an early warning accuracy rate, and if the early warning accuracy rate is lower than a threshold value, dynamically adjusting a preset proportionality coefficient to minimize an early warning error rate; and the privacy processing module is used for guaranteeing the privacy of the resident in a whole process by adjusting the shooting range of the camera, utilizing an image data set training model, carrying out anonymization encryption on acquired data, uploading aggregation parameters and combining the training model and fuzzy position information during early warning.

The invention discloses a hosiery machine sock moving anti-jamming detection device and a detection method thereof, and relates to the technical field of hosiery machines, the hosiery machine sock moving anti-jamming detection device specifically comprises a hosiery machine body, a control panel and an alarm device, the hosiery machine body is fixedly connected with a needle cylinder, and the outer surface of the hosiery machine body is rotatably connected with a sewing device; a support is fixedly connected to the upper surface of the hosiery knitter body, a camera shooting assembly is installed on the upper surface of the support, a mechanical arm is installed between the camera shooting assembly and a needle cylinder, a background calibration plate is arranged below the camera shooting assembly, and the background calibration plate is located within the shooting range of the camera shooting assembly; according to the device, images in the sock transferring process are collected through the camera shooting assembly, a region of interest is formed through multiple steps such as gray level conversion, whether the socks are stuck or not is judged by comparing current images with background images through a frame difference method in combination with the design of the rectangular background calibration plate, and the problem that the infrared technology is not sensitive to detection of dark or semitransparent socks is solved.

The utility model provides automatic tin soldering judgment equipment for a brush carrier, and belongs to the technical field of automobile accessories. According to the utility model, the overturning platform provided with the overturning assembly and the clamping station is arranged on the carrying platform, the clamping station is installed on the overturning assembly, the visual camera is arranged above the clamping station, the shooting range of the visual camera covers the clamping station, the brush carrier to be detected is placed through the clamping station, 180-degree overturning is realized through the overturning assembly, and meanwhile, the visual camera is arranged on the carrying platform. The visual camera is used for shooting, comparing and judging, whether soldering tin on the two faces of the brush carrier to be detected meets the machining requirement or not is judged, automatic detection is achieved, detection efficiency is improved, labor cost is reduced, in addition, detection standards are unified, detection accuracy is guaranteed, the problem of misjudgment caused by subjective judgment factors in manual detection is solved, and the product quality is improved. Therefore, the problem that defective products flow out due to misjudgment is prevented, the quality of the window lifting motor is ensured, and the application of the window lifting motor is facilitated.

The invention discloses a target range-oriented data acquisition and analysis method and system and a storage medium. The method comprises the following steps: acquiring action posture information, physiological state information, environment state information and shooting hit information of a trainer; training effect analysis is conducted on the obtained action posture information, physiological state information, environment state information and shooting hit information, and evaluation indexes are generated; and through a large language model technology, a personalized automatic evaluation report is generated based on the evaluation indexes. According to the method, the trainee can obtain accurate feedback in real time in the training process, meanwhile, training effect analysis greatly improves the shooting training efficiency and individuation level, various information data in the shooting training process can be comprehensively collected and analyzed, the trainee is helped to know the training state, progress and defects of the trainee in real time, and the training effect is improved. And a personalized automatic evaluation report is provided according to an analysis result, so that a more efficient shooting training effect is finally realized.

The embodiment of the invention discloses a camera adjusting method, system and device. A target shooting parameter of a conference room space is acquired; based on the target shooting parameters, determining a target shooting range which needs to be covered by the at least two first cameras in the conference room space; determining a lens adjustment angle corresponding to each first camera according to the target shooting range and the current shooting range of each first camera; and based on the lens adjustment angle, adjusting the at least two first cameras, so that the shooting ranges of the adjusted first cameras jointly cover the target shooting range. Therefore, the target shooting range, which needs to be covered by the first camera in the conference room space, is determined according to the target shooting parameter of the conference room space, so that the angle of the first camera is adjusted according to the target shooting range, and the shooting angle of the camera in the conference room space can be automatically adjusted in accordance with a conference room scene; the definition of picture output is ensured under the condition of covering a conference room scene.

The invention relates to detection equipment and detection method for a large sealing ring, and the equipment comprises an operation mechanism which comprises a first transmission wheel and a second transmission wheel, and is used for connecting with the sealing ring and moving the sealing ring in a preset direction, so that all positions of the sealing ring pass through a detection position in sequence in the moving process; the detection mechanism is used for acquiring an image of a local colloid of the sealing ring in a detection position for detection, the detection mechanism comprises a plurality of cameras and a light source assembly, the shooting range of the plurality of cameras corresponds to the detection position, the moving distance of the sealing ring each time is matched with the shooting range, and the light source assembly is used for detecting the local colloid of the sealing ring in the detection position. The plurality of cameras are arranged at intervals along the circumferential direction of the detection position; the light source assembly comprises a cover body structure and a body structure which are both provided with light sources, the cover body structure is movably connected with the body structure, and the cover body structure is used for opening or covering the detection position. The method has the effects of improving the detection efficiency and avoiding missing detection.

The utility model discloses a vehicle-mounted video monitoring fixing frame, which relates to the field of vehicle-mounted video monitoring and is technically characterized by comprising a mounting plate, the lower end of the mounting plate is fixedly connected with a fixing column, a supporting plate is arranged in the fixing column, the lower end of the supporting plate is rotatably connected with a first rotating rod, and the other end of the first rotating rod is rotatably connected with a fixing plate. The vehicle-mounted video monitoring device comprises a fixing plate, a supporting plate is arranged on the fixing plate, one side wall of the fixing plate is fixedly connected with a monitoring body, the fixing column and the supporting plate are jointly provided with a first adjusting mechanism, and the supporting plate and the fixing plate are jointly provided with a second adjusting mechanism. The problem that a view blind area exists due to the fact that the monitoring shooting range is limited due to the fact that the angle of vehicle-mounted video monitoring cannot be adjusted is effectively solved, and the overall efficiency of vehicle monitoring in the aspects of safety guarantee and management is improved.

The present invention relates to an overheating prevention device and a heating system, comprising: an infrared imaging device (300) provided at a position separated from a heating unit (21) above the heating unit (21) such that the heating unit (21) and a user enter an imaging range; a temperature calculation unit (7) that calculates the temperature of the object to be heated on the basis of the thermal image obtained from the infrared imaging device (300); a person detection unit (6) that detects the presence of a user on the basis of the thermal image; and a control unit (2) that controls the operation of the heating unit (21) via the communication unit (4) on the basis of the information relating to the operation of the user obtained from the heating device (200) via the communication unit (4), the detection result of the user obtained from the person detection unit (6), and the temperature information of the object to be heated obtained from the temperature calculation unit (7).

This enables proper fuel supply control. [Solution] The refueling system includes: a first image acquisition unit that acquires first image information of at least a portion of a first vehicle parked in a first refueling lane among a plurality of refueling lanes; a second image acquisition unit that acquires second image information of at least a portion of the first vehicle in a different shooting range than the first image information; a first determination unit that makes a determination regarding refueling in the first refueling lane based on the first image information; a second determination unit that makes a determination regarding refueling the first vehicle in the first refueling lane based on the second image information; and an execution information output unit that outputs first refueling execution information regarding the execution of refueling the first vehicle in the first refueling lane based on the result of the determination by the first determination unit and the result of the determination by the second determination unit.

This specification discloses a control method and device for unmanned equipment, which is applied to the field of unmanned driving. First, image data containing a target object collected by the unmanned equipment is obtained. Secondly, the observation position corresponding to the target object is determined based on the image data. Then, according to the lighting information of the environment in which the unmanned equipment is located when collecting image data and the observation position, a tracking path for the unmanned equipment to track the target object is planned. Finally, the unmanned equipment is controlled according to the tracking path. This method can plan the tracking path based on the lighting information of the environment in which the unmanned equipment is located when collecting image data and the observation position, thereby increasing the shooting range of the unmanned equipment for collecting image data, allowing the unmanned equipment to collect image data with higher image quality, and then better identify the target object in the image data, thereby better tracking the target object or accurately docking at the location of the target object.

This application discloses a ray interaction method, apparatus, device, medium, and product for virtual scenes. The method includes: receiving element configuration operations in the virtual scene; wherein the ray attributes include one or more of ray color and ray intensity; displaying a first incident ray received by a ray propagation element; and displaying a first outgoing ray emitted from the ray propagation element, wherein the first outgoing ray is a ray satisfying the first ray attribute obtained by adjusting a second ray attribute of the first incident ray. This allows ray propagation elements to be assigned ray attributes such as ray color and ray intensity, thereby allowing for richer adjustment of the incident ray received by the ray propagation element through the corresponding first ray attribute, to display a first outgoing ray satisfying the first ray attribute, enriching the ray interaction effects in the virtual scene. This application can be applied to various scenarios such as multiplayer battle games and virtual shooting scenarios.

The invention provides a CT device, a working method of the CT device and a working program product of the CT device. The CT apparatus of the present invention outputs projection data including the entire subject even when the amount of output data of projection data output to a console is reduced. A CT device (11) sets a subject region in an imaging range of a radiographic image using information relating to a subject, and calculates a region around the subject region prior to actual imaging of the subject. The present invention estimates the size of a peripheral region in a range other than a subject region beyond the subject region due to body movement of a subject as the margin size with respect to the subject region, and estimates the size of the peripheral region in the range other than the subject region as the margin size with respect to the subject region. Projection data of a channel corresponding to a range of an enlarged subject region obtained by adding a peripheral region to the subject region is output to a console (17).

This application provides a clothing processing device, including: a housing; a door cover; an outer cylinder; an inner cylinder with a clothing processing cavity formed inside; lifting ribs; a camera for acquiring images of the clothing processing cavity, the camera's shooting range including the lifting ribs; a motor for driving the inner cylinder to rotate; a downlight; and a control unit configured to: after the clothing processing program finishes running, if the door cover is detected to have opened and then closed, control the downlight to turn on and control the camera to capture a first image; determine whether clothing exists in the clothing processing cavity based on the first image; if the determination is negative, control the motor to drive the inner cylinder to rotate in a first direction, and control the camera to capture a second image after the inner cylinder stops rotating; and determine whether clothing exists in the clothing processing cavity based on the second image. This application can accurately detect leftover clothing to prevent clothing from remaining in the clothing processing cavity, which could lead to clothing mold and spoilage.

The utility model discloses a rotary mirror reflection double shooting automobile data recorder which comprises a shell, a first lens, a second lens, a reflection structure and a motor, the first lens, the second lens, the reflection structure and the motor are located in the shell, the first lens is used for shooting the front of an automobile, the second lens is located on a reflection light path of the reflection structure, and the reflection structure is used for reflecting external light to the second lens. The motor is connected with the reflection structure and used for driving the reflection structure to rotate so as to adjust the shooting range of the second lens. According to the rotary mirror reflection double-shooting automobile data recorder, the first lens is arranged to shoot the front of the automobile, the second lens is located on the reflection light path of the reflection structure, the reflection structure is driven by the motor to rotate, the shooting range of the second lens is adjusted, the second lens supplementarily shoots the area which cannot be shot by the first lens, and the shooting efficiency is improved. Various shooting visual angles are provided, the first lens always shoots the front of the vehicle in the process of adjusting the shooting range of the second lens, and it is ensured that images of the front visual angles of the vehicle cannot be lost.

The embodiment of the invention discloses a video acquisition method and device, intelligent equipment and a storage medium. A portrait target in a target space is positioned and subjected to posture detection through a first camera and a microphone array of the intelligent equipment, calibration is completed in the target space through a plurality of external pan-tilt cameras, and the shooting range of each pan-tilt camera in the target space can be confirmed according to equipment parameter information. According to the embodiment of the invention, the target camera which can obtain a good picture effect by performing video acquisition on the portrait target and the target control parameters required for confirming the good picture effect are confirmed from the plurality of pan-tilt cameras, and when video shooting is performed through the plurality of pan-tilt cameras, the shooting result of the target camera under the target control parameters is directly obtained. The scheme can adapt to rich changes of the communication core person in a communication site, ensures that the communication core person is well presented to a remote user, and improves the communication experience based on the video data.

The safety helmet for the elevator operation comprises a safety helmet body, the top of the safety helmet body is connected with a sliding ring through a plurality of connecting rods, and sliding grooves are formed in the upper side and the lower side of the sliding ring respectively. Sliding blocks are installed on the two sides of the inner end face of a sliding sleeve, the outer end face of a sliding ring is sleeved with the sliding sleeve in a sliding mode, and the sliding blocks on the two sides are located in sliding grooves in the two sides in a sliding mode respectively. A plurality of clamping grooves distributed in an annular array mode are formed in the upper sliding groove, and a plurality of abutting assemblies matched with the clamping grooves are installed on the upper sliding block. Comprising a hinge piece, a mounting shell is mounted on the side, away from the sliding sleeve, of the hinge piece, and a camera body is clamped in the mounting shell. According to the utility model, on the premise that the protection performance is guaranteed, the camera body can move along the sliding ring, so that the flexibility and the shooting range of the camera body are improved.

The utility model discloses a bed load collecting device, which relates to the technical field of sediment testing and comprises a water tank, a gripping device mounting area is arranged on the side wall of the water tank, a gripping device and a visual identification mechanism are arranged on the gripping device mounting area, and the visual identification mechanism comprises a fixed light supplementing camera and a laser profile measuring head. The grabbing range of the grabbing device is located in the shooting range of the fixed light supplementing camera and the measuring range of the laser profile measuring head, and the volume, the approximate orientation and the approximate shape of the bed load can be calculated through a volumetric method according to images, shot by the fixed light supplementing camera, of the bed load. Then, the outline of the bed load is measured through the laser outline measuring head, so that the overall outline size and the accurate form of the bed load are obtained, accurate grabbing information is provided for the grabbing device, the grabbing precision is improved, and the defect that the size of the bed load is difficult to clearly know through a camera device in a sediment-carrying basin is overcome.

The utility model relates to the technical field of telescopic rods, in particular to a telescopic rod assembly, a selfie rod and an umbrella rod device, which comprises a driving rod, unit rods are sequentially connected to form telescopic matching, a telescopic pipe fitting is sleeved outside the driving rod and is formed by sequentially connecting unit pipes, and linear limiting parts are arranged on the unit pipes. The adjacent unit pipes are in linear telescopic fit through linear limiting parts, the driving thread pieces are located on the unit rods correspondingly, holes are formed in the pipe walls of the unit pipes and spirally extend in the pipe length direction of the unit pipes, the driving thread pieces are matched with the unit pipes correspondingly, thread protrusions are arranged outside the driving thread pieces, and the driving thread pieces are matched with the unit pipes. According to the telescopic rod assembly, the threaded protrusion is matched with the hole of the unit pipe, the driving rod rotates, telescopic driving of the telescopic pipe fitting is implemented by driving the threaded piece, the telescopic rod assembly can achieve telescopic rod design of more stages more easily, when a larger shooting range and higher flexibility are pursued, the requirement can be met by reasonably increasing the telescopic stages, and better expansibility is achieved.

A system and method for recovery of undamaged frangible aerial targets at shooting ranges includes a net positioned horizontally above ground level to cover a target fall zone. The net has mesh openings sized to retain undamaged frangible aerial targets while allowing damaged targets to pass through. The net forms a closed loop around parallel elongated front and rear rollers supported above ground by a plurality of fixed caster assemblies. A motor operatively coupled to at least one roller drives the net in a conveyor-like motion. Undamaged targets landing on the net are transported by the net to a collection area positioned adjacent to the front roller. The system may include friction strips on the rollers to enhance traction and a protective barrier shielding the collection area from stray shotgun pellets, thereby enabling recovery and reuse of targets that would otherwise break upon ground impact.

To enable stable person re-identification in a multi-camera object tracking system or the like, and to accurately track a tracking target across the imaging ranges of a plurality of cameras. [Solution] Images of at least the approximately front side and the approximately back side of a person to be tracked, taken synchronously by two or more cameras installed at the starting point of multi-camera object tracking, or image feature quantities of these images, and an identification ID of the person to be tracked are registered in a tracked person registration DB (S5), and the person to be tracked is tracked across the shooting ranges of the multiple cameras based on the registered images of at least the approximately front side and the approximately back side of the person to be tracked, or image feature quantities of these images. This allows matching of the images of at least the approximately front side and the approximately back side of the person to be tracked, or image feature quantities, with images or image feature quantities taken by other cameras, thereby enabling stable person re-identification.

The utility model provides a wireless solar fisheye binocular curbstone machine. The wireless solar fisheye binocular curbstone machine comprises a shell, detection radars, fisheye lenses and a transmission module, wherein the detection radars are oppositely arranged on the two sides of the shell and can detect two berths respectively; the fisheye lenses are arranged on a camera and can enable the camera to shoot the berths on the two sides respectively; by the adoption of the technical scheme, the two detection radars are arranged to detect the vehicle states of the two berths respectively, then the large-angle fisheye lens is adopted, the shooting range of the camera is enlarged, the single camera in the shell can give consideration to the scenes of the two berths, the function that the single camera shoots multiple berths is achieved, and the shooting efficiency is improved. And the equipment cost is reduced to a great extent.