61 results about "Surveillance imaging" patented technology

Provided herein are systems and methods for enhanced marine ship detection. A system includes a mission planning system for generating a set of tasking commands to send to a plurality of satellites in an intersatellite link (ISL) relay layer, a plurality of Earth observation satellites having overlapping accessible swaths, wherein a first satellite collects first sensor data at a first set of coordinates based on a first tasking command and sends the data to the ISL relay layer, and at least a second satellite trailing behind the first satellite collects second sensor data at a second set of coordinates based on the second tasking command and the first sensor data, and sends the second sensor data to the ISL relay layer, and a reception system to receive ship detection data including the first sensor data and the second sensor data and to generate at least one vessel detection report.

The invention relates to a double-spectrum fused intelligent monitoring imaging method and system, and the method comprises the following steps: firstly, synchronously collecting a visible light image and an infrared image of a monitoring scene, and calibrating the pixel coordinates to generate an aligned double-spectrum map; then, extracting the texture features of the visible light image and the temperature gradient of the infrared image from the aligned bispectrogram, and respectively obtaining a texture feature map and a temperature gradient map; feature validity judgment is carried out based on the two images, a bispectrum effective area image is identified, complementary areas are marked, and complementary effective marks are formed; then, carrying out weight assignment on the marks, and constructing a pixel weight table; and finally, fusion calculation and dynamic range compression are performed on the texture feature map and the temperature gradient map by using the weight table, so that a monitoring fusion imaging map is generated, and the technical problem of detail loss caused by sudden illumination change and weak temperature difference due to the lack of adaptive perception capability for scene content in the existing fusion method is solved.

The invention provides a building intelligent monitoring method and system based on the Internet of Things, and the method comprises the steps: carrying out the detection of a mobile terminal based on the Internet of Things in a building, obtaining the dynamic feature information of the mobile terminal in the building, and recognizing an Internet-of-Things communication busy region in the building; based on the Internet of Things communication feature information of the Internet of Things communication busy area, the shooting monitoring state of the shooting device matched with the Internet of Things communication busy area is adjusted to obtain the monitoring image of the Internet of Things communication busy area, and it is ensured that the monitoring image can be rapidly and accurately transmitted under the existing data transmission performance of the Internet of Things. The condition of delayed transmission processing of the monitoring image is avoided; and on-site environment state characteristic information of an Internet of Things communication busy area is obtained through monitoring image recognition, so that whether an abnormal event occurs is judged, the Internet of Things communication state of the mobile terminal in the Internet of Things communication busy area is adjusted, alarm reminding is carried out, and the real-time performance and reliability of building internal monitoring are improved.

The utility model discloses a fixing device of a monitoring image module, relates to the technical field of monitoring, and solves the technical problem that an existing monitoring image module is inconvenient to mount and dismount. The device comprises a base, fixing assemblies are installed on the two sides of the base, and a monitoring image module is installed above the base; the fixing assembly comprises an L-shaped plate, a sliding rod, a limiting block, a pull rod and a spring, one end of the L-shaped plate is fixedly installed on one side of the base, a through hole is formed in the other end of the L-shaped plate, the sliding rod penetrates through the through hole, the limiting block is fixedly installed at the end, close to the base, of the sliding rod, and the pull rod is fixedly installed at the end, away from the base, of the sliding rod; one end of the spring is fixedly connected with the limiting block, the other end of the spring is fixedly connected with the L-shaped plate, and the limiting block is inserted into the monitoring image module. According to the utility model, the fixing and dismounting of the monitoring image module are realized, the flexibility during the installation of the monitoring image module is increased, and the operation is convenient and fast.

The invention relates to the technical field of intelligent driving, and discloses a data processing method and device for a panoramic monitoring image system, and the method comprises the steps: obtaining a preset configuration word when an application of the panoramic monitoring image system is started; determining a target connection link of the panoramic monitoring image system corresponding to the preset configuration word; the target connection link of the panoramic monitoring image system corresponding to the preset configuration word comprises a first connection link connected with a camera of a built-in panoramic monitoring image system corresponding to the preset configuration word, or a second connection link connected with a system box of an external panoramic monitoring image system corresponding to the preset configuration word; acquiring panoramic monitoring image data through the target connection link; generating target image information according to the panoramic monitoring image data; and sending the target image information to the vehicle machine system. According to the invention, when the hardware scheme is changed, the operation of determining the data processing scheme is simple and the efficiency is high.

This invention belongs to the field of power plant information technology and safety supervision, and discloses a method, system, equipment, and readable storage medium for identifying unlicensed operations in thermal power plants. The method for identifying unlicensed operations in thermal power plants includes the following steps: acquiring monitoring image data of the thermal power plant production area through cameras installed in the production area, inputting the data into a pre-trained behavior detection model for detection, and obtaining the probability P of personnel operation behavior appearing in the monitoring image data. 作业 And the corresponding location POS where the operation occurs; the probability P 作业 The results of comparing the results with a preset threshold P0 are used to identify unlicensed operations in thermal power plants. This invention can identify and monitor unlicensed operations, unauthorized expansion of work areas, and other violations, significantly improving the real-time performance, accuracy, and coverage of monitoring.

The invention discloses an image processing method, an electronic device, a vehicle and a computer readable storage medium, and the method comprises the steps: obtaining vehicle-mounted images of at least two adjacent cameras of the vehicle, and projecting foreground region images of the at least two adjacent cameras to a first plane when detecting that a foreground object exists in the vehicle-mounted images, and splicing the foreground area images projected to the first plane to obtain a spliced foreground image. Therefore, the foreground image can be determined on the basis of the projection of the foreground area image on the first plane, so that the situation of defects such as ghosting or dislocation in the foreground image obtained by splicing can be avoided to a certain extent, and the quality of a panoramic image obtained by the foreground image can be guaranteed; and the user experience of the panoramic monitoring image system can be guaranteed.

The invention provides a mining area safety monitoring method and system based on image data, and relates to the technical field of mining area safety monitoring. The method comprises the following steps: collecting historical monitoring image data of a target area in a mining area, constructing a monitoring frame image sequence and extracting a plurality of image quality features, performing quality classification on the monitoring frame image sequence, identifying a plurality of visible sample images to construct a visible image set, determining candidate facility areas in the target area, and determining the candidate facility areas in the target area; cutting out a plurality of facility sub-graphs to construct consensus feature fingerprints of the candidate facility areas, extracting structure disturbance features of each facility sub-graph based on the consensus feature fingerprints, and generating a plurality of reference disturbance modes; and extracting the coverage duration characteristic of each reference disturbance mode, and after collecting the online monitoring image data of the target area, carrying out online safety monitoring on the target area based on the online monitoring image data and the plurality of reference disturbance modes. According to the invention, the detectability and early warning reliability of the potential safety hazard of the mining area can be improved.

A monitoring event analysis system and method are disclosed. The method includes: acquiring monitoring images and multiple operation commands, wherein the multiple operation commands have an operation sequence; capturing multiple operation screens from the monitoring images, wherein each of the multiple operation commands corresponds to a corresponding operation screen; according to the operation sequence, treating the multiple operation commands and the multiple operation screens as multiple operation actions, and comparing the multiple operation actions with a monitoring event; and when the multiple operation actions match the multiple monitoring commands and multiple monitoring screens of the monitoring event, storing the multiple operation actions as a monitoring record. Accordingly, it is possible to quickly and accurately determine whether a predefined monitoring event has occurred.

This utility model discloses a cattle unloading and transfer channel, relating to the technical field of cargo loading and unloading devices. It includes a main channel module, a branch channel module, and a monitoring system. The horizontal section of the main channel module is connected to the ship's suspension ladder via a floating slide rail connector. A branch channel module is connected to the end of the main channel module, and the end of the branch channel module is connected to the loading and unloading vehicle. The monitoring system is installed within the branch channel module. The floating slide rail connector is not rigidly fixed to the suspension ladder; the lateral displacement of the slide rail compensates for the longitudinal height difference caused by tides, adapting to tidal fluctuations and ensuring stable movement of the cattle. Two loading lanes are provided at the end of the branch channel module, allowing multiple vehicles to operate simultaneously, reducing ship waiting time and reducing the time for unloading cattle per transaction to 60% of the traditional method. The monitoring images meet customs quarantine filing requirements and support dispute tracing.

The application relates to a human shape movement monitoring method, a system, a terminal and a storage medium, and belongs to the technical field of monitoring, wherein the method is based on a processing terminal in a monitoring device, the monitoring device further comprises a camera and a driving piece for adjusting the angle of the camera, the method comprises the following steps: acquiring real-time monitoring images; performing image recognition processing on the real-time monitoring images; confirming a target following object and entering a lens following mode after the recognition result meets preset mode switching conditions; and performing the following processing in the lens following mode: identifying the position change trend of the target following object; and generating a control instruction for the driving piece based on the position change trend to adjust the rotation angle of the camera. The application can improve the problem that the monitoring effect on specific objects is poor.

To provide a system for detecting a marine ship.SOLUTION: A system for detecting a marine ship comprises: a mission planning system for generating a set of tasking commands to send to a plurality of satellites in an intersatellite link (ISL) relay layer; a plurality of Earth observation satellites having overlapping accessible swaths, in which a first satellite collects first sensor data at a first set of coordinates based on a first tasking command and sends the data to the ISL relay layer, and at least a second satellite trailing behind the first satellite collects second sensor data at a second set of coordinates based on the second tasking command and the first sensor data, and sends the second sensor data to the ISL relay layer; and a reception system to receive ship detection data including the first sensor data and the second sensor data and to generate at least one vessel detection report.SELECTED DRAWING: Figure 5

The present invention discloses a property safety prevention and control method and system based on artificial intelligence, comprising: first obtaining the current monitoring video, and using a pre-trained target video frame analysis model to extract the image information of the person in the video. Subsequently, based on this information, a local monitoring image containing the person is extracted, and the behavior type is identified through a target park behavior classification model. Once abnormal behavior is identified, the system will automatically send the current monitoring video to a security server and generate an alarm message, thereby realizing intelligent monitoring and early warning of property safety. Such a design improves the monitoring efficiency and response speed of property safety, reduces labor costs, and enhances security.

The invention belongs to the technical field of vehicle production detection, and particularly provides a robot spot welding splash detection method based on visual identification, a terminal and a storage medium, and the method comprises the steps that a visual controller recommends a key monitoring area according to received spot welding position data of each robot, and sends the key monitoring area to a visual sensor; the vision sensor monitors the key monitoring area according to the received position information of the key monitoring area and a preset detection period until a spot welding ending signal of the robot is received; the visual sensor transmits monitoring image data back to the visual controller after receiving a spot welding ending signal; the visual controller analyzes the received monitoring image data and judges whether the spot welding splashing phenomenon occurs in the monitoring image data or not; the automatic detection process reduces the workload of manual statistics and improves the detection efficiency; a visual sensor and an intelligent analysis algorithm are used for accurately recognizing the splashing phenomenon, and the welding quality is ensured.

The invention discloses a method for distinguishing and determining the number of individuals according to South China subtype field video monitoring images of Chinese pangolin, and relates to the technical field of wild animal infrared camera video monitoring. According to the invention, high-definition video monitoring equipment is arranged in the South China subtype activity area of the Chinese pangolin, so that the activity image of the pangolin can be clearly captured. The video equipment has a night vision function so as to adapt to the night activity habit of the pangolin. In addition, the collected video images are preprocessed, including denoising, contrast enhancement, color correction and the like, so that the image quality is improved, and subsequent analysis is facilitated. According to the invention, a machine learning or deep learning algorithm is used to carry out individual identification on the preprocessed video image. This generally involves the extraction and analysis of appearance features (such as scale pattern, body size, color, etc.) of pangolin to differentiate different individuals. On the basis of individual identification, the number of pangolin individuals appearing in the video is counted. The method can be realized through an automatic counting algorithm, and can also be combined with manual auditing to improve the statistical accuracy. According to the method, individual identification is carried out through video monitoring, the population quantity monitoring efficiency is greatly improved, and the quantity statistics accuracy is also improved. The movement information of the pangolin can be obtained in real time, and timely data support is provided for protection work.

The invention provides a data acquisition system and a data acquisition method. The data acquisition system comprises a photographing device, a storage device, a host device and a server. The host device is coupled to the photographing device and the storage device, and is used for obtaining the monitoring image through the photographing device and backing up the monitoring image to the storage device. The server is coupled to the host device and the storage device, and is used for reading the monitoring image from the host device or the storage device, and obtaining the monitoring data from the monitoring image according to a preset identification frame. The server executes the target detection module to identify a numerical value in the monitoring data, and the server determines whether the confidence of the numerical value is greater than or equal to a first confidence threshold. When the server judges that the confidence coefficient of the numerical value is greater than or equal to a first confidence coefficient threshold value, the server judges whether the numerical value is within a safety range or not; and when the server judges that the numerical value is not in the safety range, the server generates an abnormal notification. The data acquisition system and the data acquisition method can provide a data acquisition function.

The present application relates to the technical field of image processing analysis, especially to the adaptive visibility detection system of expressway, the present application obtains the monitoring image, driving data of expressway through information acquisition module, and generates visibility description rule text for different specifications of vehicles in monitoring image; through image feature extraction module, the feature salience time domain is determined, different feature clustering sets are divided according to the text matching result; according to the driving data comparison result of feature salience time domain in different feature clustering sets, whether the current visibility broadcast information of monitoring section is searched is determined through the search comparison module; through the detection correction module, according to the comparison result of image extraction information and visibility broadcast information, whether the visibility broadcast information is corrected is determined. Further, the adaptive correction of visibility broadcast is realized according to the specification difference of vehicle using time domain dynamic information, and the demand of timely and safe management and control of expressway is met.

The invention relates to a night infrared monitoring imaging enhancement method and device, and the method comprises the following steps: obtaining an original infrared image of a night scene through infrared monitoring equipment, carrying out the noise suppression, obtaining a denoised infrared image, and carrying out the contrast enhancement of the image, and generating an enhanced contrast image. Performing target area initial positioning on the original image based on the image to form an initial positioning target frame, and determining an effective target frame through area gray analysis; detail sharpening processing is carried out on the contrast-enhanced image for the frame, a sharpened target image is generated, and then a target contour is extracted to obtain clear target contour information. And finally, performing feature annotation on the contour map to generate a target feature annotation map, and performing background weakening processing on the map to finally obtain an enhanced imaging map which highlights a target and has a soft background, thereby solving the technical problems of fuzzy details and serious noise interference generally existing in the existing infrared monitoring image.

Provided herein are systems and methods for enhanced marine ship detection. A system includes a mission planning system for generating a set of tasking commands to send to a plurality of satellites in an intersatellite link (ISL) relay layer, a plurality of Earth observation satellites having overlapping accessible swaths, wherein a first satellite collects first sensor data at a first set of coordinates based on a first tasking command and sends the data to the ISL relay layer, and at least a second satellite trailing behind the first satellite collects second sensor data at a second set of coordinates based on the second tasking command and the first sensor data, and sends the second sensor data to the ISL relay layer, and a reception system to receive ship detection data including the first sensor data and the second sensor data and to generate at least one vessel detection report.

The present invention relates to the field of data processing technology, and in particular to an intelligent management system based on massive image data, comprising: a receiver, a cloud database and a retrieval engine; the receiver obtains the monitoring image data interaction authority of the monitoring device, and after obtaining the monitoring image data interaction authority, receives the monitoring image data of the monitoring device in real time and sends it to the cloud database in real time; the cloud database obtains the monitoring image data fed back by the receiver in real time, identifies the monitoring parameters of the monitoring device from which the monitoring image data comes, and the present invention realizes the centralized reception of monitoring image data of multiple monitoring devices by obtaining the monitoring device authority, and further simplifies a large amount of monitoring image data into image data by setting and filtering logic of monitoring image data. Therefore, when the system end user has a tracking demand, based on the system, the retrieval target trend can be quickly retrieved in the massive image data according to the retrieval target uploaded by the system end user.

The invention relates to the technical field of monitoring image transmission, in particular to an intelligent traffic monitoring image transmission method and system based on the 5G technology, and the method specifically comprises the steps: calculating the content key coefficient of each image block through the synchronous analysis of the traffic road condition and traffic jam condition of an intelligent traffic monitoring image video frame, determining the transmission priority of each image block in the same video frame; the method comprises the following steps of: constructing time slot interference in the transmission process of each uplink channel according to signal interference caused by cross time slot interference generated among different base stations and channel occupancy rate overlapping conditions in the transmission process of a 5G uplink channel, wherein the signal interference is caused by the traffic monitoring image video data packet due to the cross time slot interference generated among the different base stations; and the uploading sequence of the video frame content in the intelligent traffic monitoring image is adjusted based on the transmission priority and the time slot interference, so that the delay jitter and packet loss condition aggravation risk of the traffic monitoring image in the 5G transmission process is effectively reduced, and the 5G transmission quality of the intelligent traffic monitoring image is guaranteed.

The invention relates to a detection machine head of welding spot detection equipment, which is provided with an XYZ three-degree-of-freedom movement mechanism, the XYZ three-degree-of-freedom movement mechanism is arranged on a rack, a lifting seat is arranged at the movement tail end of the XYZ three-degree-of-freedom movement mechanism, an image capturing device and a force control shifting device are arranged on the lifting seat, and the force control shifting device is arranged on the lifting seat. The lifting seat drives the image capturing device and the force control shifting device to lift synchronously; the force control shifting device is used for shifting a welding spot, and the image capturing device is at least used for obtaining a welding spot image and a monitoring image of the shifting dynamic state of the force control shifting device and transmitting the images to the computer for detection. According to the invention, not only can image detection be carried out, but also cold solder and insufficient solder online toggle detection can be carried out, welding spot online integrated visual detection and toggle detection can be realized, the technical problem that cold solder and insufficient solder cannot be judged through pure visual detection is solved, the structure is compact, the automation degree is high, and the detection efficiency and speed are improved.

The invention discloses an intelligent calibration method and device for a large-scale outdoor monitoring camera based on a single camera. The calibration method comprises the following steps: controlling the calibration device to move in a space of the outdoor monitoring camera and acquiring an image with pose information; acquiring an outdoor monitoring camera image, and performing homonymy point matching on the outdoor monitoring camera image and an image from the calibration equipment; according to a homonymy point matching result, calculating relative external parameters between the monitoring image and the streetscape image based on a motion structure recovery algorithm, and calculating a plurality of rough pose results of the monitoring camera; and finally, calculating the pose initial value of the monitoring camera through outlier elimination and weighted average, optimizing the pose result based on a multi-view consistency principle, and estimating the spatial position and azimuth angle of each monitoring camera. According to the invention, large-scale monitoring camera pose calibration can be realized.

The present invention discloses a method, system, device and medium for restoring a damaged license plate image, relating to the technical field of image processing. The method includes: extracting a damaged license plate image from a real-time monitoring video; inputting the damaged license plate image into a pre-trained restoration model to obtain a restored license plate image; the pre-trained restoration model is trained in the following manner: generating an incomplete license plate image dataset according to a random segmentation of a complete license plate image dataset; constructing a first generator for generating a complete license plate image from an incomplete license plate image and a second generator for generating an incomplete license plate image from a complete license plate image; training the pre-trained restoration model according to the first generator and the second generator in combination with a generation loss, a cycle consistency loss and a license plate loss. The present invention combines a complete license plate image dataset and an incomplete license plate image dataset, greatly improving the accuracy and authenticity of the model output results.

The invention discloses a monitoring image quality evaluation method based on multi-scale structure fidelity, and belongs to the field of image quality evaluation. The invention aims to solve the technical problem of providing the monitoring image quality evaluation method based on the multi-scale structure fidelity, and the method measures the distortion degree of an image contour and an edge by calculating and fusing the gradient amplitude fidelity of multiple scales so as to deduce an image quality score. Structural information is extracted from an original image and a distorted image by using a gradient operator with efficient calculation, and the image processing mode of a human vision system is simulated, so that an evaluation result is more in line with the perception habit of human beings. Mutual information is adopted to measure the amount of information extracted when a human visual system senses an external input signal, and a new view angle is provided for image quality evaluation, that is, the image quality is evaluated from the view of information transmission. And the quality score of the image is predicted by fusing the multi-scale gradient amplitude fidelity.

The utility model provides a construction site video monitoring AI analysis system, and relates to the technical field of building construction. And the adjusting assembly comprises a mounting frame, the bottom of the mounting frame is fixedly connected with the top of the bottom plate, and an electric telescopic rod is arranged at the inner bottom of the mounting frame. When the monitoring device is used, the bottom plate, the battery rack, the battery pack, the adjusting assembly and the monitoring assembly are matched for use, so that the whole monitoring device can be moved to any place of a construction site to work according to requirements, and a built-in AI of the monitoring device analyzes and sends an adjusting instruction, so that the height, the horizontal angle and the pitching angle of the monitoring device are adjusted; according to the construction site monitoring system, personnel and objects in the surrounding environment of a construction site are monitored, a monitoring blind area is avoided, monitoring images are transmitted to a terminal in real time through a wireless transmission module, mutual verification with terminal operators is carried out to assess the safety of the construction site, and potential safety hazards of the construction site are reduced.

The application relates to the technical field of community security management, and discloses a floating population intelligent monitoring method, system and equipment. The method comprises the following steps: determining floating population data flow according to behavior event information in monitoring image data of a preset monitoring area collected; obtaining personal trajectory data of the floating population data flow by dynamically tracking the floating population data flow based on a preset trajectory algorithm; analyzing the personal trajectory data by a preset outlier detection abnormal behavior algorithm to obtain abnormal behavior data of the floating population data flow; and pushing early warning information when the abnormal behavior data meets an abnormal behavior early warning threshold. In the application, the monitoring video of the area where the floating population is located can be analyzed, the activity trajectory of the floating population can be recorded, the dynamic trajectory can be described, the personal trajectory data can be analyzed and counted for abnormal behavior by the preset outlier detection abnormal behavior algorithm, and early warning can be performed when the early warning threshold is exceeded, so that early warning can be timely and accurately sent out.

The invention relates to an adaptive image monitoring method and a method for updating a region of interest thereof, which are used for solving the problem that important object information cannot be provided by a region of interest in a known monitoring method. The method comprises the following steps of: identifying at least one object and a category corresponding to the object from a monitoring image; calculating an evaluation score of each of the at least one object, and defining an object corresponding to the maximum evaluation score as a maximum score object; determining a region of interest from one of a plurality of sub-regions in the monitoring image, wherein the region of interest has the object with the maximum score; the sum of the evaluation scores of the objects in the region of interest is not less than the sum of the evaluation scores of the objects in other sub-regions containing the object with the maximum score. The driving safety can be improved.