52 results about "Image identification" patented technology

An imaging environment that greatly affects image recognition accuracy is recognized for applications in onboard systems of various sorts including imaging devices. An imaging device for imaging areas around the vehicle is mounted on a vehicle. Before executing image recognition processing, information is acquired on objects and texture, such as traffic signs and pedestrian crossings, present within a field of view of the imaging device. An object or texture present within the field of view is then recognized by an image recognition section. Degrees of distortion and defocus of a shape or texture of the object recognized are calculated based on the shape or texture of the object recognized and information previously acquired on the objects or texture. Imaging environment, such as water droplets or dirt on a lens, and whether fog occurs or not, is then recognized based on the degrees of distortion and defocus calculated from the shape or texture of the object recognized.

A method and apparatus for computing correlating images for image recognition is provided. In particular, the method is used to compare images of a biometric object to authorize an individual or verify whether an individual is the person he claims to be. The biometric objects may include fingerprints, hand or palm prints, and retina scans. The method uses a deviation of symmetry of correlation functions to determine whether the images are of a same object.

A device for detecting insects on substrates such as lettuce and other leaves. The device has a microscope lens which magnifies a portion of the leaf and send an image of the leaf portion to an image recognition system. If the image recognition system detects the presence of an insect—further steps are taken to remove the insect.

The invention discloses a shooting picture display device. The shooting picture display device comprises a first obtaining module, a shooting characteristic information extracting module, and a first display module, wherein the first obtaining module is used for obtaining picture information captured by a camera in real time after a shooting function of the camera is started; the shooting characteristic information extracting module is used for extracting characteristic information of a shooting object from the picture information according to a preset first image recognition algorithm; the first display module is used for displaying a picture according to the characteristic information and a shooting habit model; and the shooting habit model is obtained through machine learning and training. According to the method and the device disclosed by the invention, the purpose of automatically displaying the shooting picture suitable for a shooting habit of the user in shooting is realized.

The invention discloses an Internet two-dimensional code intelligent lock and a using method thereof in hotel management. The Internet two-dimensional code intelligent lock comprises a processor, and a two-dimensional code recognition module, a face recognition device, a wireless communication module, a Bluetooth module, a power module, a clock module, an electric control lock and a recognition error alarming device which are connected with the processor, and further comprises a storage battery connected with the power module, wherein the wireless communication module is connected with a user terminal and a management terminal respectively through a server; the two-dimensional code recognition module comprises an image recognition unit and a power control unit which are connected with each other; the image recognition unit is connected with the processor. The management terminal is matched with locks through the serve and updates unlocking two-dimensional codes, and in different time periods, different locks correspond to only encrypted codes in different time periods. The Internet two-dimensional code intelligent lock can automatically acquire room renting information statistically, and customers can choose rooms by themselves, so that information is transparent and the safety management of a hotel is effectively enhanced.

A camera-based modular electronic exterior mirror system includes a camera assembly and a display assembly, the camera assembly comprises a camera module, a camera support and a camera wire harness. The display assembly comprises a display screen and an image processing unit. The camera module installed in the camera support is connected with the image processing unit through the camera wire harness. The display screen is arranged on the driver side A-pillar or on the right side area of the steering wheel. In application, the camera module transfers the road state image taken by the camera module into the image processing unit through the camera wire harness, and the image processing unit processes the received image to obtain narrow-angle and wide-angle views, and arranges the images up and down on the display screen, and can automatically judge whether there is a foreign object in the blind area through the image recognition software, and an alarm is sent when there has the foreign object. This design not only has good quality of image display and strong effect of rear-view guidance, but also has pedestrian detection function and a wide range of adaptability.

The invention relates to a smoke and fire detection method based on deep learning and image recognition. The method comprises the following steps: step 1, reading a video frame from a to-be-identifiedvideo, and extracting a part of pixel sets in the video frame according to color characteristics of pixels in the video frame and difference characteristics of the pixels between the video frames toform one or more pre-processing areas for identification; Step 2, intercepting the extracted preprocessing area into pictures to serve as input of a smoke and fire detection model; Step 3, extractingfeatures from the picture through the smoke and fire detection model; 4, determining the confidence coefficient of the smoke and fire scene in the picture according to the extracted characteristics; and step 5, if the confidence coefficient exceeds a confidence coefficient threshold, marking an area corresponding to the picture in the video frame.

Methods for correcting for non-centred tool geometry in image data obtained by a conduit inspection tool are disclosed. Embodiments of the invention apply to inspection tools with one or multiple sideview cameras and to inspection tools with downview cameras. The methods include obtaining at least two overlapping images of the internal surface of the conduit using the tool, identifying one or more features common to at least a pair of the overlapping images, determining, based on the positions of the or each common feature, the position of the tool with respect to a longitudinal axis of the conduit, determining a correction function based on the position of the tool and applying the correction function to the image data. Methods for determining the dimension of a feature of interest on the internal surface of the conduit are also disclosed.

The invention provides a vehicle information processing method, device and equipment and a computer readable storage medium. The method comprises the following steps: collecting a pavement image collected by an image collection device; identifying road information in the road surface image; identifying target vehicles in the road information, and determining center point information correspondingto each target vehicle; according to the center point information and a safe driving area, whether the target vehicle drives safely or not is judged, a judgment result is obtained, and the safe driving area is determined according to the center line of the road information and a preset range threshold value. Therefore, traffic factors such as road marker lines and traffic signal lamps in other roads do not need to be adopted for auxiliary calculation, the method can be suitable for traffic scenes of various roads, the recognition operation of whether the vehicle runs safely or not in the traffic scene of a single road is effectively limited, and the traffic safety of the traffic scene of the single road is guaranteed.

The invention discloses a method for detecting an edge sealing effect of a board. The method comprises the following steps: acquiring first board image information through a first image sensor, wherein the first board image information comprises a first board surface image and an edge sealing band area image; acquiring second board image information through a second image sensor, wherein the second board image information comprises a second board surface image, the second board surface image comprises a laser projection line projected on the surface of the board, and first board image information and the second board image information are the image information of the same board; and performing board defect early warning on the acquired image information. The invention further discloses anelectronic device and a computer-readable storage medium. According to the method for detecting the edge sealing effect of the board, by matching laser projection with image identification, the purpose of detecting multiple different defects at the same time can be achieved, and the detection efficiency and the detection effect of the edge sealing effect of the board are greatly improved.

The invention provides a key block dynamic search system and method based on an image recognition technology, and relates to the technical field of geotechnical engineering informatization. The systemcomprises an image acquisition system, a computer operation system, a remote control system and a wireless transmission system. The image acquisition system comprises an image acquisition device, a laser range finder, an auxiliary lighting device and a marker post, wherein the laser range finder is installed on the image acquisition device; And the auxiliary lighting device and the marker post are placed at positions closer to the tunnel face. The computer operating system comprises an image processing module, a block searching module and a key block instability dynamic simulation module, andis used for processing the acquired image and then searching a movable block; The remote control system comprises a data storage module and an abnormal data processing module and is used for storingdata and feeding back information. The wireless transmission system is used for connection between the systems. The device is simple and convenient to use, high in working efficiency and high in practicability.

An image-capturing device having an image identification mechanism is provided. The image-capturing device comprises a first and a second flashlight modules, a processing module and an image-capturing module. The first and the second flashlight modules generate a first and a second color lights respectively according to a first and a second currents. The processing module controls the first and the second flashlight modules to flash light at an object sequentially within a time interval. The image-capturing module generates a first frame according to the object and the first color light and generates a second frame according to the object and the second color light. The processing module subtracts the pixels in the first and the second frames to retrieve a foreground area. A color difference between the first and the second frames for each the pixels in the foreground area is larger than a threshold value.

The invention discloses an anti-counterfeit printing method of a packing box. The method comprises steps as follows: reading image identification information of an anti-counterfeit imprint code, generating a printed anti-counterfeit imprint code script, and storing the anti-counterfeit imprint code script in a printer; reading preview image identification information of the anti-counterfeit imprint code, comparing the preview image identification information with the anti-counterfeit imprint code script, judging whether the preview image identification information and the anti-counterfeit imprint code script are consistent or not, and if yes, printing the anti-counterfeit imprint code to a test packing box by the printer. The printing effect can be improved by comparison of the preview image identification information and the anti-counterfeit imprint code script. The problems of offset and deficiency in the printer are solved, feature point extraction is performed only for preview images without global scanning, so that the calculation speed is higher, and image printing speed is also greatly increased.

The invention provides a traffic monitoring method and a traffic monitoring system based on unmanned aerial vehicle image recognition, and the traffic monitoring method comprises the following steps: S1, providing an unmanned aerial vehicle aerial traffic picture as a sample picture, and carrying out the vehicle marking of the sample picture through image marking software LabelImg, and forming a sample set; s2, preprocessing the sample set by adopting a data enhancement method to form a training set; s3, constructing a YOLO v3 model, training the YOLO v3 model through the training set, and obtaining the trained YOLO v3 model; and S4, receiving an aerial traffic image of the unmanned aerial vehicle in real time, inputting the aerial traffic image into the trained YOLO v3 model to monitor and analyze the vehicle, and calculating to obtain real-time traffic monitoring data. According to the traffic monitoring method and the traffic monitoring system, macroscopic and accurate monitoring data can be obtained in real time, and the traffic situation can be studied, judged and decided in time.

The invention relates to a subcutaneous microvessel segmentation and three-dimensional reconstruction method based on optical coherence tomography. The subcutaneous microvessel segmentation and three-dimensional reconstruction method comprises the following steps of obtaining a two-dimensional image sequence through an FFOCT system and preprocessing; grouping the acquired two-dimensional images, and performing robust principal component analysis on each group of images to obtain an image background and a high-response microvascular region; and carrying out capillary segmentation and three-dimensional reconstruction on the image background and the high-response capillary region in combination with the position relationship between each group of images and the capillary boundary distributionin each group of images. Compared with the prior art, the method has the advantages that the global optical coherence tomography technology is applied to image recognition of venipuncture, the imaging precision is remarkably improved, blood vessel positioning is more accurate, and capillary clear imaging is more reliable.

The inveniton provides a line length correction method for traveling wave fault location. The method comprises the steps of establishing a power transmission line height difference absolute value parameter matrix and a power transmission line span parameter matrix, obtaining the lowest point position of a line in a corresponding span through an image recognition method, constructing a corresponding coefficient k, obtaining an initial value of the corresponding coefficient k according to the corresponding coefficient k and horizontal distances lOA and lOB, finely adjusting the initial value of the corresponding coefficient k to obtain a corrected value of the corresponding coefficient k; obtaining a complete span error parameter matrix through a ratio parameter of a line length error parameter to a height difference absolute value, and then superposing the corrected line lengths of various groups according to the relationship between the error parameter matrix and an actual line length parameter matrix to obtain the actual bus length Lsum of the power transmission line; performing fault position correction through the corresponding relation between the actual bus length Lsum and the horizontal span lsum of the power transmission line, and obtaining the actual fault position Lx away from the measuring end of the power transmission line. The method aims at avoiding the influence of load current and external environment changes on the actual line length and improving the traveling wave fault positioning precision of the power transmission line.

The invention discloses a defect recognition device and system based on an image recognition technology. The defect recognition device comprises a detection system module and a shell; illuminating lamps are fixedly arranged at the four corners of the surface of the front end of the shell in an embedded mode; a CCD camera is fixedly arranged in the middle of the surface of the front end of the shell in an embedded mode, and a power socket and a network socket are sequentially formed in the surface of the right end of the shell from front to back; and a display screen is fixed to the upper end surface of the shell in an embedded mode, a storage battery is fixedly arranged at the bottom in the shell through screws, a driving main board is arranged above the storage battery and fixed to the inner wall of the shell through screws, and a detection system module is fixedly arranged on the upper end surface of the driving main board through welding. The defect recognition device and system based on the image recognition technology have the advantages of being high in image information feature online detection and extraction efficiency and accuracy, high in detection precision, capable of labeling defect positions and convenient to compare and check.

Image identification is disclosed including acquiring N images, N being a natural number greater than 1, extracting target characteristic information from respective ones of the N images to obtain a first data set corresponding to the N images, and determining, using a data model, a category associated with the first data set corresponding to the N images.

The invention provides a display screen defect monitoring system based on image recognition and a detection method thereof, and relates to the technical field of screen defect detection. The display screen defect monitoring system comprises a detection assembly line and a main control computer, and the detection assembly line comprises at least one detection station used for detecting a display screen; the detection station is a darkroom in which a lighting jig for loading a display screen and an image acquisition module are arranged, the main control computer comprises an image processing module, an image comparison module, a good product estimation module and a sample library, and a plurality of illuminating lamps are arranged in the detection station. According to the invention, the camera is used for photographing, the image processing module is used for processing the obtained picture, and the image comparison module is used for comparing the processed picture with a non-defective product pre-estimated picture, so that the defective products in the display screen can be effectively detected, compared with the traditional manual detection, the omission ratio and the false detection ratio are greatly reduced, the detection speed is high, the detection precision is high, and the detection efficiency of the display screen is effectively improved.

The invention provides a memory with image recognition function. The memory comprises a plurality of memory processing units, each unit comprising a mode processing circuit and at least one three-dimensional memory (3D M) array. The 3D-M array is stacked on top of the mode processing circuit and stores user image data and the like. The mode processing circuit performs pattern recognition on the user image data stored in the 3D-M array according to the input image model.

The invention relates to the field of artificial intelligence and digital medical treatment, and provides a skin disease recognition method and device based on image processing, equipment and a storage medium. The method comprises the steps of obtaining a to-be-recognized skin image; performing image preprocessing on the skin image to obtain a target image; performing recognition processing on the target image through a pre-trained image recognition model to obtain a skin disease category probability corresponding to each skin disease category; performing identification processing on the target image through an image identification model to obtain a skin disease part probability corresponding to each skin part; screening the skin parts according to the skin disease part probability to obtain a target skin disease part; according to the skin disease category probability, sorting skin disease categories to generate a candidate skin disease category sequence; and filtering the skin disease category of the candidate skin disease category sequence according to the target skin disease part to obtain a target skin disease category. The method can improve the accuracy of skin disease identification.

The invention discloses an on-off state image recognition method for a high-voltage double-column isolating switch, relates to the technical field of power systems, and solves the technical problem ofrecognizing the oil level of a transformer. The method comprises the steps that a rectangular opening and closing identification area is set in a monitoring image of the double-column type isolationswitch, two calibration areas A and B are defined in the opening and closing identification area, and a movable conductive tube and a static conductive tube of the double-column type isolation switchare both located in the calibration areas A; then, when the double-column isolating switch is closed, an image of an opening and closing identification area is intercepted as a reference image, gray processing is carried out on the reference image, and after fitting calculation, a calibration area A connection percentage value and a calibration area B background percentage value of the reference image are calculated; and identifying the real-time image in the opening and closing identification area by using the connection percentage value of the calibration area A and the background percentagevalue of the calibration area B of the reference image. The method provided by the invention is suitable for the substation configured with the high-voltage double-column isolating switch.

The invention discloses an image processing method and system and a mobile terminal. The image processing method comprises the following steps: receiving a first image of a front camera and a second image of a rear camera; detecting the first image to obtain a first parameter of the first image; the second image is detected, a second parameter of the second image is obtained, and the second parameter is consistent with the first parameter in parameter type; determining a third parameter of the fused image according to the first parameter and the second parameter; adjusting the first image andthe second image according to the third parameter to obtain a third image and a fourth image; identifying a figure object in the third image; and fusing the figure object into the fourth image to forma fused image. According to the invention, the images shot by the front camera and the rear camera at the same time are fused together, and combined display of the figure object and the scenery at the two ends of the mobile terminal is realized.

The invention discloses a vehicle control method and device and an automatic driving vehicle. The method comprises the steps: in the process that a current vehicle runs according to an automatic driving mode, collecting an image in front of the current vehicle in real time; identifying whether traffic lights and parking lines exist in the image; under the condition that the traffic signal lamp and the parking line exist in the image, determining the indication state of the traffic signal lamp and the distance between the current vehicle and the parking line, wherein the parking line and the current vehicle are located on the same side of the traffic signal lamp; and controlling the current running speed of the vehicle according to the indication state of the traffic signal lamp and the distance. The technical problems that when an automatic driving vehicle passes through an intersection provided with a traffic signal lamp, the driving state of the vehicle cannot be controlled according to the indication state of the traffic signal lamp, the risk of traffic accidents may be increased, and the driving safety is poor are solved.