70 results about "Surveillance imaging" patented technology

The invention discloses a multi-scale geometric analysis super-resolution processing method of a video blurred image, belonging to the technical field of intelligent information processing. Single-frame blurred images or multi-frame blurred images are acquired by surveillance videos, the input blurred images are decomposed into low-frequency coefficients and high-frequency coefficients by NSCT, the blurred images are de-noised by an HMT model in the NSCT domain, edge details are enhanced by visual suppression networks, sub-band images with low-frequency coefficients and high-frequency coefficients are interpolated nonlinearly by a HyperBF neural network model, the processed NSCT decompression coefficients are reconstructed by NSCT, and the multi-scale Retinex algorithm is introduced to regulate the image contrast in accordance with human eye visual consciousness. The processing of multi-frame blurred images is based on an image fusion method in the MGT domain and a non-uniform interpolation method in the MGT domain. Without changing the hardware of traditional video surveillance imaging system, the method can effectively restrain common noise in video images and further improve the resolution and the definition of the blurred images.

A wide-angle imaging optical system includes a refractive optical system (3), a reflective optical system, and an image-forming optical system (5). The reflective optical system includes a first reflection surface (1) that directly reflects rays of light from an object, and a second reflection surface (2) that reflects rays of light from the first reflection surface (1). An open portion is provided between the first reflection surface (1) and the second reflection surface (2), and rays of light from the object enter the open portion. A light-transmitting portion (2a) is provided in the second reflection surface (2) and transmits rays of light that have entered the refractive optical system (3). An aperture (1a) is provided in the first reflection surface (1) and allows rays of light from the second reflection surface (2) and the refractive optical system (3) to enter the image-forming optical system (5).

Embodiments of the invention disclose a packaging process monitoring method and system, relates to the technical field of logistics, and aims at rapidly acquiring videos of packaging spots, simplifying the video evidence obtaining process, and decreasing the time and vigor, required in the evidence obtaining process, of consumers. The method comprises the following steps of: obtaining video imagesand recording names and attribute information of the obtained video images, wherein the names of the video images are generated according to package identifier of packages where commodities packagedon stations are located, and the attribute information at least comprises order information, commodity information and logistics information of the commodities packaged on the stations; querying the names and / or attribute information of the obtained video images according to a query request sent by user equipment, so as to obtain a video image corresponding to the query request; and pushing the video image corresponding to the query request to the user equipment. The method and system are suitable for rapidly querying monitoring images in packaging processes.

An active infra-red surveillance illuminator uses a statistically mono-directional micro-diffractive material overlaid on a bank of light emitting diodes (LEDs) to refract light from the LEDs onto a target image. This delivers energy distribution profiles out to a distance to match the aspect ratios of current wide-angle target and wide-angle camera surveillance systems. The distribution of refracted light is elliptical. This distribution can vary by using different diffractive material in conjunction with various numbers, brightness and angles of the LEDs in an LED bank. The effective range of the illuminators is greatly extended with this type of illumination. By limiting infrared (IR) radiation down to a 10 degree vertical window it renders the IR illumination much more effective for surveillance imaging by providing much more effective power on wide, ground-level scenes, and particularly enables multi-lane license plate capture.

Surveilling a subject may include irradiating a portion of the subject with electromagnetic radiation, receiving radiation reflected from the subject, and producing digital image data representative of an image of the portion of the subject. The digital image data may be used as input for computations including image processing and / or analysis, and the result of such processing and / or analysis may be used to make determinations about the subject, such as whether subject is carrying contraband. In some embodiments, the digital image data may be upsampled into expanded digital image data, which may improve the quality and / or effectiveness of downstream image processing and / or analysis.

The invention discloses a construction progress visualization method based on BIM model and monitoring image comparison, and belongs to the technical field of calculation, reckoning or counting. The method comprises the following steps of building a BIM model with precision and granularity meeting construction progress management requirements, and giving recognizable unique codes to the BIM model; hooking construction plan data to the built BIM model; acquiring image data shot by construction monitoring equipment, and identifying a structure under construction and a constructed structure of a construction area; automatically analyzing an identification result and the plan progress, and reflecting the progress state and the progress deviation through different colors of the BIM model. Under the background that more and more engineering projects apply the BIM model and the monitoring equipment, the application path of the BIM model and the monitoring equipment in construction is expanded, and an informatization scheme with excellent intuition and good integrity is provided for construction progress management.

The invention belongs to the field of geological disaster monitoring, and discloses a landslide crack monitoring method based on single-image close-range photogrammetry. The method comprises the following steps: S1, collecting an image of a monitoring region in real time through a camera; S2, comparing the real-time image of the monitoring image with the initial image, respectively acquiring feature points of the real-time image and the initial image by using a SIFI algorithm, and performing feature point matching to obtain homonymous feature points of the real-time image and the initial image; S3, establishing a two-dimensional field displacement vector model based on the homonymous feature points of the initial image and the real-time image, and detecting an active area based on a grayscale image to obtain a landslide fracture area; and S5, calculating to obtain the width of the landslide crack according to the coordinates in the ground photogrammetry coordinate system correspondingto the homonymous feature points in the landslide body area in the initial image and the real-time image. The method has the advantages of high precision, no contact, wide monitoring range, visual monitoring result and the like.

The embodiment of the invention provides a figure tracking method, system and server. The method comprises the steps: each camera group in a region is connected with a figure database; a regional camera monitoring network is established, the locations of a to-be-detected person photographed by a camera groups in the database can be quickly queried through to-be-detected features of the to-be-detected person, and the locations where the camera groups of the to-be-detected person appear are connected in a time sequence, so that the movement track of the to-be-detected person can be quickly obtained. On the other hand, in the embodiment of the invention, a front image and a back image of a to-be-detected person are respectively acquired by using a camera group; any one of a cross-parallel ratio function target detection method, a face recognition embedding method for tracking face detection and a gait similarity matching method is used for matching the characteristics of the person to bedetected with the person in the monitoring image information, and any one of the three methods can realize the function.

This invention in phase homogenization of coherent light from illuminators used for surveillance imaging systems provides a coherent light emitter aligned with a light source ray path along an optical axis with at least two separated microdiffractive diffusers, the microdiffractive diffusers comprising holographically generated surfaces of microdiffractive structure that statistically tend to diffract light at selectable angles or distribution patterns, the microdiffractive diffusers disposed upon a substrate and separated from each other by a distance determined by wavelength phase and irradiance characteristics of the coherent light emitter and by refractive characteristics of at least two microdiffractive diffusers, followed by a homogenized exit ray path in order to produce a diffused pattern of illumination optimized for long distance surveillance imaging.

Diffractive waveplate lenses, mirrors, devices, systems and methods for performing imaging over a broad spectral band in imaging systems, such as but not limited to astronomical imaging, surveillance imaging, and in communication systems, such as laser communication systems. Corrector mirrors are used with a flat diffractive wave diffractive waveplate lens so that chromatic aberrations of the diffractive waveplate lens are reduced with the imaging system.

The invention discloses a method for identifying vehicles entering and exiting parking spaces, and the method comprises the steps: obtaining a monitoring image, and building a two-dimensional coordinate system; determining responsibility parking spaces, wherein each responsibility parking space obtains a corresponding coordinate area; intercepting a field image from the field video every a presetperiod to obtain a vehicle two-dimensional coordinate of each vehicle in each field image; judging whether the two-dimensional coordinates of the vehicle in each field image have intersection points with the parking space coordinate set or not, obtaining a coordinate intersection, and calculating a coordinate intersection area, namely an overlapping area of the vehicle and the parking space; and calculating the overlap ratio of the vehicle and the parking space coordinate set according to the ratio of the coordinate intersection area to the vehicle area, and judging the state of the vehicle according to the change trend of the overlap ratio in the continuous multi-frame images. The method for identifying vehicles entering and exiting parking spaces is completed through a camera and an analysis module, management personnel do not need to be configured on site, manpower management cost can be greatly reduced, and higher identification efficiency is achieved.

The present invention provides a low principal ray incident angle super wide angle optical system and a working method thereof. The system comprises a lens tube and the optical system arranged in thelens tube. The optical system comprises a crescent negative lens L1, a crescent negative lens L2, a biconvex positive lens L3, an aperture light diaphragm S1, a crescent positive lens L4, a bonded lens consisting of a biconvex positive lens L5 and a crescent negative lens L6 and a biconvex positive lens L7 successively arranged along the direction from the position of light incident to an imagingplane. A parallel flat plate P1 is arranged between the imaging plane and the biconvex positive lens L7. The optical lens system has a very large view field angle and is capable of shooting a wide range of scenery, the relative illumination is relatively high, and especially, the incident angle of a principal ray is low under the condition of the large view field angle, so that the system can be well adapted to the current video surveillance imaging chip, and the lens can be used with a 5 million pixel CCD or a CMOS chip.

The invention relates to a transmission conductor online monitoring method and system based on target identification and reconstruction, and the method comprises the following steps: obtaining image information of a space above a tower, recognizing a dangerous region of a conductor based on the image information, and generating early warning information; determining a sampling range and a sampling period of the laser point cloud data based on the early warning information; acquiring a dangerous distance by using the laser point cloud data; when the dangerous distance meets the safety condition, ending the work; and when the danger distance does not meet the safety condition, sending out safety early warning according to the danger coefficient. The real-time performance of a monitoring image is utilized to improve the dangerous object identification speed, and the real-time performance requirement of power transmission line monitoring is met; point cloud data scanned by a laser radar is utilized, the accuracy degree of dangerous distance calculation is improved, and online monitoring and safety early warning of a transmission line are achieved by integrating parameters such as the minimum vertical distance, the minimum clearance distance, the minimum horizontal distance, the dangerous distance, the size of a dangerous target, the height of the dangerous target and the safety guarantee level of the transmission line.

The invention discloses an unmanned aerial vehicle image monitoring control device. The device comprises a camera, an identification unit, a data processing unit, a command conversion unit, an adjustment unit, a database, a sending unit and a display unit; the camera is used for acquiring monitoring of the unmanned aerial vehicle on images in real time, automatically acquiring monitoring image information and transmitting the monitoring image information to the recognition unit; a storage image of a monitored object is stored in the database. According to the invention, through the arrangementof the data processing unit, the data analysis is performed on the identified analysis image information, so the motion position and the related conversion ratio of each part in the object information are calculated; therefore, the actual motion of the object and the deviation value in the image are calculated, the image of the object cannot be obtained after the object moves in the image information for a long time, the accuracy of data analysis is improved, the persuasion of data is improved, the time consumed by analysis is saved, and the working efficiency is improved.

The invention relates to a temperature measurement method and system based on a face recognition and temperature measurement all-in-one machine, and a storage medium. The method comprises the steps of generating a current first compensation amount and a current second compensation amount; acquiring a real-time monitoring image; obtaining a first real-time infrared image and a second real-time infrared image; displaying the real-time monitoring image and the first real-time infrared image on a display screen; generating a first current forehead temperature and a second current forehead temperature; judging whether the difference value of the two exceeds a preset error threshold value or not; if not, obtaining the actual detection temperature according to the first current forehead temperature and the second current forehead temperature; if so, obtaining the latest first compensation amount and the latest second compensation amount; generating a current first correction amount and a current second correction amount; calibrating the first current forehead temperature and the second current forehead temperature; calculating and generating an actual detection temperature according to a calibration result; and comparing and judging the actual detection temperature with a normal body temperature threshold value. The method has the effect of improving the accuracy of the temperature measurement result.

The invention discloses a security monitoring device based on Internet of Things, and relates to the technical field of security and protection of the Internet of Things. The device comprises a monitoring spherical shell, wherein a top-mounted cover used for hanging and mounting is installed at the top of the monitoring spherical shell, a mounting frame mechanism used for being positioned on a wall body is fixedly arranged at one side of the outer surface of the top-mounted cover, and an electric power mechanism for rotating to adjust an angle is installed in the middle of the top of the monitoring spherical shell. According to the monitoring device, intelligent adjustment and monitoring of the Internet of Things can be achieved, the overall horizontal monitoring view angle of a monitoring mechanism can be changed at will according to requirements, the surrounding environment is monitored in an all-around mode, and suspicious objects are clearly recorded and monitored; and mosquitoes around the device are repelled, the mosquitoes are prevented from interfering with monitoring images, intelligent connection between the device and a network is achieved, intelligent omni directional monitoring is achieved, the overall occupation space is small, the monitoring range is wide, dust on the surface of a protective cover can be automatically cleaned, manual cleaning is not needed, and unnecessary maintenance work is reduced.

The invention discloses a monitoring device for timely removing a shelter. The device comprises a box body, wherein the bottom surface of the box body is provided with a transparent sliding block groove, a transparent sliding block is connected in the transparent sliding block groove, right pull ropes are connected to the top surface of the transparent sliding block groove in a front-back symmetric mode, the top surface of the transparent sliding block is connected to the transparent sliding block groove through a first spring, the top wall of the transparent sliding block groove is provided with a first sliding groove, the first sliding groove is internally connected with a sliding rod, the top end of the slide rod is connected to a metal block, the top surface of the sliding rod is connected with the first sliding groove through a second spring, the second spring is connected with the transparent sliding block, eight second sliding grooves are uniformly arranged at the bottom surfaceof the transparent sliding block in a front-back mode, the bottom end of the sliding rod is located in the second sliding groove, transparent clamping blocks are connected in the second sliding grooves, clamping grooves are formed in the right end faces of the transparent clamping blocks, and the top surfaces of the transparent clamping blocks are connected with the second sliding grooves throughthird springs. A shelter in front of a lens can be processed in time to prevent a monitoring image from being blocked, and a camera slowly rotates to expand a monitoring range.

The invention provides a video monitoring image enhancement method based on color migration matching features. The problem of color enhancement under a monitoring video image is solved by using a color migration method according to the characteristics of the monitoring video image and the continuity and stability of the monitoring video image; under the same scene, the color features of the video image with good monitoring image quality are migrated to the video image needing to be enhanced, or the video image color information with more image color information and a block effect is subjected to color migration, so that the video image to be processed is subjected to color enhancement; a Gaussian pyramid is used for extracting feature points of the video image, so that it is guaranteed that the feature points of the videoimage under different scales can be extracted, the videoimage brightness texture is used for restraining the color, the block effect caused by color enhancement of the videoimage is reduced, videoimage information is enhanced while videoimage color enhancement is guaranteed, the image quality of a target person or a vehicle is good, and powerful support is provided for urban comprehensive management.

A surveillance system is presented that aims to improve image quality. The surveillance system comprises a plurality of lighting apparatuses comprising one or more lights; a surveillance imaging device arranged to capture image data of a monitored area illuminated by one or more of the lighting apparatuses; an image processor arranged to receive the image data from the surveillance imaging device, wherein the image data comprises a plurality of frames, and the image processor is arranged to analyse each frame of the image data to obtain an image quality parameter for each frame; and a controller arranged to determine a difference between a value of the image quality parameter for a current frame and a reference value of the image quality parameter, wherein if said difference is greater than a threshold value. The controller is arranged to repeat a process of: 1) controlling a lighting parameter of at least one of the plurality of lighting apparatuses so as to change illumination of the monitored area; and 2) determining a new difference between a value of the image quality parameter for a new current frame and the reference value of the image quality parameter; until said new difference is less than or equal to a threshold value.

A plural-mode, plural-receptor surveillance imaging system and methodology which offer very simple, versatile one-handed control over the operations and viewing orientations of three different surveillance imagers, thus to minimize the tasks involved in controlling the specific surveillance views which are established and presented by these imagers. Provided for allowing such control are a one-hand-operable, intuitive touch-screen and joystick controller structure, and a appropriate computer for translating user control actions accurately into changes in system behavior. This one-handedness characteristic promotes an operational environment in which the larger share of a user / operator's attention can successfully be focused on the received surveillance imagery, per se, rather than upon details of operating a control.

The invention discloses an intelligent visual impaired person service method and system based on vehicle-mounted glass vibration feedback, and the method comprises the steps: controlling a temperaturesensor to obtain the temperature information of a cushion if the feedback starting of a vehicle-mounted terminal is received, and analyzing whether a preset temperature is exceeded in real time, if yes, controlling an eye tracker to acquire human eye movement information of the seat and analyzing whether a human body is a person with visual impairment, and if yes, controlling a monitoring camerato shoot a monitoring image and extracting object information contained in the monitoring image according to an image recognition technology; converting the object information into vibration feedbackinformation, generating sound simulation information corresponding to the object information, controlling a laser transmitter and a laser receiver to obtain touch detection information, and analyzingwhether a human body touches the vehicle-mounted glass; and if yes, controlling the vehicle-mounted glass to enter a real-time tactile vibration feedback state through the vibration feedback equipment, controlling the loudspeaker to play voice information corresponding to the sound simulation information, and controlling the vibration feedback equipment and the loudspeaker to stop after analyzingthat the human body cancels touching the vehicle-mounted glass.

System and method for intelligently monitoring the production line that can monitor an inspected object image captured by an image capturing device, thereby allowing an operating station host to provide a labeling module to reinspect a classification decision of a classifier subsystem, to achieve the purpose of verifying the classification decision or checking whether there are missed inspections. In addition, the classifier subsystem can automatically filter out classification decisions with lower reliability to effectively reduce the number of reinspection. Moreover, a group of inspected object images can be analyzed first to obtain image difference features through comparison, which is suitable for insufficient training samples. Furthermore, the labeling module can simultaneously reinspect highly relevant historical classification decisions. Meanwhile, a second image capturing device is provided, so that the system can automatically label defect positions based on the inspected object image before and after repair, thereby learning to judge whether defects occur.

The invention provides a monitoring method and device, a storage medium and electronic equipment. The method comprises the steps that whether a first image meeting a first condition exists in a monitoring image of a target area or not is determined; under the condition that the first image exists in the monitoring image, whether a second image in the monitoring image meets a second condition or not is determined, and a second moment corresponding to the second image is before a first moment corresponding to the first image; and carrying out early warning under the condition that the second image meets a second condition. According to the method and the device, the monitoring image is played back, and whether early warning is carried out or not is judged again based on the monitoring image content before the first moment corresponding to the first image, so that the early warning accuracy is improved, the situation of frequent early warning caused by single image frame detection is avoided, meanwhile, rapid early warning is realized through detection of the playback content, and the early warning efficiency is improved. The purpose of improving the early warning efficiency is achieved.

The invention discloses an intelligent atmosphere foiling method and system based on information media and athletic contests. The method comprises the steps: if an atmosphere foiling instruction is received, extracting competition field information, the number of required audiences and advertisement information contained in the atmosphere foiling instruction, and controlling a monitoring camera toshoot monitoring images in real time; obtaining competition information and audience information in real time, and analyzing whether the competition field is in a competition state in real time; if so, analyzing whether the number of audiences reaches the required audience number in real time; if not, controlling the pressure sensor to acquire pressure information in real time and extracting auditorium seats where no human bodies sit; controlling corresponding lifting openings to be opened, and controlling a lifting mechanism to drive a simulation mechanism to rise to enter an audience simulation state; and controlling a loudspeaker to play the advertisement information in real time, controlling the display screen to play the advertisement information and analyzing whether people have cheer actions in the auditorium or not in real time; and if so, controlling the microphone to acquire surrounding cheer information and controlling the loudspeaker to synchronously play atmosphere foiling voice information which is the same as the cheer information.

The invention discloses an intelligent storage protection method and system for inclination angle detection. The method comprises the steps that an angular motion detection mechanism is controlled toobtain the angle information of a warehouse shelf in real time according to a protection instruction, and whether the warehouse shelf inclines at a first preset angle or not is analyzed in real time;if yes, the number information of the warehouse shelves inclining by the first preset angle is extracted, the positions of the warehouse shelves are recognized, an inflation air curtain set is controlled to be inflated and popped up to enter an article protection state, a lifting column in driving connection with a lifting mechanism is controlled to stretch out to abut against the warehouse shelves, and whether the warehouse shelves incline by the angle exceeding a second preset angle or not is analyzed in real time; if yes, an abutting mechanism is controlled to drive a supporting column to extend out to abut against the ground of the warehouse, a monitoring camera is controlled to shoot monitoring images in real time, and whether the warehouse goods shelf is supported by the lifting column and the supporting column or not is analyzed in real time; and if so, the warehouse shelf number information and the monitoring image are transmitted to a warehouse management department keeping along connection relationship in real time.

The invention discloses a security detection method. The safety detection method comprises the following steps: acquiring real-time monitoring image data of a door body; recognizing an occurrence-disappearance event of a moving object according to the image data; and under the condition that the occurrence-disappearance event is recognized, the opening and closing state of the door body is detected, and safety detection is carried out. The door body state is detected after the occurrence-disappearance event of the moving object is recognized through the image data, and the state of the door body does not need to be detected in real time all the time. Safety check is started according to the current state of the door body, and the efficiency of identifying abnormal conditions can be improved while a user can be warned that the state of the door body does not conform to the expected state. The invention also discloses a security detection system and a storage medium.

The invention discloses an electric power facility external damage hidden danger supervision method. The method comprises the following steps that an electric power facility alarm is received, and theposition of the electric power facility alarm is obtained according to the received alarm; if the regional power failure occurs in the power facility, the received alarm is set as a first-level alarm, a monitoring device closest to the first-level alarm is obtained, and a monitoring image record of the monitoring device is read to push the alarm; if the regional power failure does not occur in the power facility, the received alarm is set as a second-level alarm, a monitoring device closest to the second-level alarm is obtained, and a monitoring image record is read; and based on an image processing technology, the monitoring image when the second-level alarm is triggered, the monitoring image before the second-level alarm is triggered and the monitoring image after the second-level alarmis triggered are acquired, and the monitoring images are sent to an upstream processing center. According to the electric power facility external damage hidden danger supervision method, by setting different alarm levels, the most direct judgment can be carried out on the power facility alarm, so that the subsequent alarm judgment and feedback operation are facilitated.