501 results about "Image storage" patented technology

The invention discloses a cut workpiece defect detection method and system based on image feature feedback, and relates to the technical field of image processing.The method comprises the steps that cut workpiece technological characteristics are obtained, a preset defect type library is constructed, a hardware system is built, and parameters are initialized; synchronously acquiring a multi-view original image, and storing and associating annotation information; de-noising the original image, enhancing the contrast, and extracting a region of interest ROI; extracting texture, shape, edge and gray features from the ROI, and screening through a Relief-F algorithm to obtain an optimal feature subset; inputting into an SVM (Support Vector Machine) model for reasoning, and screening to obtain an effective defect detection result; and calculating an evaluation index and generating a feedback signal, and performing iterative optimization after adjusting parameters. The system comprises an acquisition module, a master control module, a data processing module and a display module. Through the precise design and closed-loop feedback of the whole process, the precision, efficiency and long-term adaptability of defect detection of the complex cutting workpiece are improved, and the industrial quality management and control requirements are met.

An augmented reality device for obtaining three-dimensional (3D) position information of a plurality of hand joints of a user includes a plurality of cameras configured to photograph the user's hand and obtain images; memory storing instructions; and at least one processor; the instructions, when executed, may cause the device to recognize the plurality of hand joints from the images; obtain two-dimensional (2D) joint coordinate values for feature points corresponding to the hand joints; retrieve, from a look up table (LUT), 3D position coordinate values corresponding to distortion model parameters of the cameras, a positional relationship between the cameras, and the 2D joint coordinate values; and output the 3D position information of the plurality of hand joints based on the 3D position coordinate values.

An information processing device includes an instruction information acquisition unit configured to acquire instruction information input as voice by a user, a storage control unit configured to, when the acquired instruction information is registration instruction information, cause a storage to store a printed image as a favorite image, and a print control unit configured to, when the acquired instruction information is second print instruction information for instructing to print the favorite image, cause an image forming device to execute printing of the image stored as the favorite image.

The invention discloses a distributed medical image retrieval and hierarchical storage management system and method. The system comprises an interface processing module, a distributed image storage cluster, a routing forwarding module, a metadata management module and a storage management module. The interface processing module receives the image retrieval request, generates a routing identifier for positioning the storage position of a target medical image file and sends the routing identifier to the routing forwarding module; and the routing forwarding module queries a mapping relationship between the medical image file and the storage node and / or the storage hierarchy based on the routing identifier, determines a first storage node and forwards the request, so that the first storage node returns a target medical image file. And the storage management module obtains the access statistical information, determines a target storage level and / or a target storage node, migrates the medical image file, and triggers updating of the mapping relation after migration is completed. Therefore, cross-node accurate positioning and unified retrieval are realized, positioning consistency is kept after file migration, and hierarchical storage management based on access conditions is supported.

An occupant state monitoring apparatus includes an imager, a storage, and a calculation controller. The imager is configured to capture an image of an occupant who is in a vehicle. The storage is configured to store vehicle member coordinates that are position information of a vehicle member of the vehicle. The calculation controller is configured to calculate, based on the image, gaze coordinates representing a position at which the occupant gazes, and determine a state of the occupant based on the gaze coordinates and the vehicle member coordinates.

The invention provides a method and device for determining the oscillation mode of plasma, electronic equipment and a medium, and relates to the field of plasma diagnos.The method comprises the steps that video data, collected by a low-frame-rate camera, of the plasma generation process of a Hall thruster are obtained; processing the video data by adopting the trained image frame processing network to obtain an image frame sequence arranged according to a time sequence; and processing the state information of the plasma in each image frame in the image frame sequence by adopting a configured POD algorithm to obtain energy ratios of different types of oscillation modes. According to the method, the neural network is introduced, a high-frame-rate image is generated by learning a large amount of historical image data, capturing nonlinear behaviors of plasma oscillation optical characteristics and carrying out frame processing on the low-frame-rate image, the performance requirement for an image acquisition system, the image processing time cost and the image storage cost are reduced, and the image acquisition efficiency is improved. And the data processing efficiency is greatly improved.

The invention provides an image processing method and device, electronic equipment, a storage medium and a program product, the method is applied to an image processing module running in target equipment, the target equipment further comprises a virtual machine, and the method comprises the steps that in response to starting of the virtual machine in the target equipment, according to a physical address corresponding to a virtual frame buffer area, the virtual frame buffer area is obtained; determining a physical storage area corresponding to the virtual frame buffer area; the physical storage area is determined as an image storage area, and the image storage area is a storage area which can be accessed by the image processing module; and under the condition that the virtual machine stores image frame data to the virtual frame buffer area, reading the image frame data from the image storage area so as to render and display the image frame data. According to the embodiment of the invention, the efficiency of displaying the image frame data can be improved.

A warehouse management system and a method of using such a system are disclosed. A data gathering apparatus including lidar and visual image capture devices is attached to a vehicle such as a forklift. The data gathering apparatus gathers lidar and visual image data as it moves around a warehouse with storage locations such as shelves. The lidar and visual image data are processed to produce processed data in the form of a digital twin representing the storage area and accessible using a computer device to provide information about the storage locations and information about products stored on the shelves. In particular that information includes product information, visual images, percentage volume of the stored location filled and percentage of product present compared to a previous quantity.

A method to quickly generate a preview thumbnail preview thumbnail and a mobile electronic device are provided. The mobile electronic device includes an image capture component, a processing device and a storage device. The method to quickly generate a preview thumbnail includes: the image capture component captures multiple frames of images according to a photographing command; the processing device optimizes the frames of images and transmits the optimized images to a camera application; the camera application selects one frame from the frames of images as a preview thumbnail; and the camera application synthesizes the frames of images to output a final image, and the final image is stored in the storage device.

The invention discloses an image data reading method, system and device, electronic equipment and a computer readable storage medium, the method is applied to a request processor, the request processor is connected with an image display controller and an image memory through a bus, and the method comprises the following steps: receiving an image data reading request sent by the image display controller; determining a target cache region corresponding to the image data reading request, and storing the image data reading request to the target cache region; when the number of the image data reading requests in the target cache region reaches a preset threshold value, packaging the image data reading requests according to a preset unit transmission quantity to obtain a reading request packet; and sending the reading request packet to an image memory, so that the image memory feeds back an image data packet corresponding to the reading request packet to an image display controller. By applying the technical scheme provided by the invention, unnecessary bus resource occupation can be reduced while the timeliness and continuity of image data reading can be effectively ensured.

An apparatus and method for training a machine learning model to augment signal data and image data. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive a signal data. The memory instructs the processor to generate a digital image, wherein the digital image comprises the signal data. The memory instructs the processor to transmit the digital image to an image processing module, wherein the image processing module produces an augmented image. The memory instructs the processor to transmit the signal data to a signal processing module, wherein the signal processing module produces the augmented image. The memory instructs the processor to train a machine learning model using the augmented image.

The invention discloses a safety monitoring system and method based on construction site AI. The system comprises an edge end, a transmission layer and a cloud platform. The edge end comprises an image acquisition module, a lightweight reasoning module and a local alarm module; the transmission layer encrypts and compresses the preprocessed image and the alarm information output by the edge end and transmits the preprocessed image and the alarm information to the cloud platform; the cloud platform comprises an image storage module, a depth reasoning module, a visual management module and a database. According to the method, the lightweight model is fixedly deployed on the edge side and is responsible for real-time target and posture recognition, and first-time response to potential safety hazards is ensured; complex analysis tasks such as an SORT trajectory tracking algorithm and the like are placed in the cloud, and deep behavior analysis is carried out on continuous image frames. The response of the system to the real-time requirement is guaranteed, frequent switching and maintenance of special models in multiple stages are avoided, and the overall stability and execution efficiency of the system are improved.

The invention belongs to the technical field of intelligent environmental sanitation and unmanned sweeper operation quality monitoring, and discloses an environmental sanitation event monitoring method and system in outdoor unmanned sweeper operation, and the system comprises an unmanned sweeper camera terminal, a communication module, an image storage module, a garbage recognition module, an environmental sanitation event management module and a scheduling and supplementary sweeping task module. During cleaning operation, acquiring operation result images of a cleaned road section and an obstacle avoiding road section, synchronously recording longitude and latitude, time and a line number, performing garbage detection and classification after uploading, and generating an environmental sanitation event record carrying position and operation information; and the event priority is calculated according to the road section event statistics and the road section weight, a supplementary scanning task work order is generated and issued to the unmanned sweeper terminal, the event processing state is updated in combination with the supplementary scanning result image, and automatic discovery and closed-loop management of the outdoor unmanned sanitation operation result are realized.

An image storage system includes: an acquisition unit that acquires a captured image of a surrounding environment and three-dimensional information; a derivation unit that detects the face of a subject included in the captured image and derives the orientation of the detected face of the subject from the three-dimensional information; an image processing unit that masks the face of the subject included in the captured image and generates a processed image obtained by adding information indicating the orientation of the face to data of the captured image; and a storage unit that stores data of the processed image generated by the image processing unit.

The invention relates to the technical field of image processing, and discloses a tobacco sundry image set construction method, which comprises the following steps: S1, collecting tobacco shred sundry images; s2, gray correction and noise suppression are carried out on the tobacco shred sundry image, a sundry main body and a sundry background of the tobacco shred sundry image are separated, and an independent sundry image with a transparent background is generated; s3, repeatedly executing the steps S1 to S2, and storing the impurity independent images to form a sample set; s4, constructing a tobacco shred sundry training set, and obtaining a plurality of tobacco shred sundry-free image samples; s5, superposing the tobacco shred sundry-free image and the multiple sundry independent images to form a fusion image set; s6, dividing the fused image set into a training set, a verification set and a test set according to the proportion of 8: 1: 1; and S7, obtaining an anchor frame set for tobacco shred impurity detection through a clustering algorithm. Tobacco shred background interference is removed, training data generated through follow-up fusion can force the model to focus on learning of visual features of sundries, and the generalization ability of the detection model is improved.

An image display control device for a vehicle is provided with: an interface circuit (11) that acquires a viewpoint change operation by a user with respect to a viewpoint operation device (3) and a captured image from a camera (1) that captures an image of the surroundings of the vehicle; a memory (12) storing a vehicle model; and a calculation circuit (13) that, on the basis of the changed viewpoint position of the vehicle by the viewpoint change operation, constitutes a bird's-eye view image from the changed viewpoint position from the captured image and a vehicle image based on the vehicle model, and displays the constituted bird's-eye view image on a display (4). In the overhead image, a first transmittance is achieved as the transmittance of the captured image through the vehicle image in a part of a portion where the vehicle image overlaps the captured image, and a second transmittance higher than the first transmittance is achieved as the transmittance of the captured image through the vehicle image in the other portion. The range of the two-dimensional position coordinates occupied by the portion that achieves the first and second transmittance in the bird's-eye view image is varied in accordance with the changed viewpoint position.

A method, computer program product, and computer system are provided for storing images and / or other data on an edge computing device in an edge computing environment. Data is received from one or more sensors operatively coupled to the edge computing device. One or more features and metadata are extracted from the received data. The extracted features and metadata are compared to a pre-defined tolerance range and one or more exogenous variables. The received data is caused to be stored on either the edge computing device or a second edge computing device based on a determination that the compared features and metadata falls within the tolerance range or outside of the tolerance range, respectively.

The present disclosure provides a vehicle-mounted cabin driving integrated image processing system and a vehicle. The system comprises a driving domain image signal input module, a cabin domain image signal input module, a driving domain image signal processing module, a cabin domain image signal processing module and a memory. The driving domain image signal input module is used for storing driving domain image signals to the memory. The cabin domain image signal input module is used for storing cabin domain image signals to the memory. The driving domain image signal processing module is used for reading driving domain image signals from the memory and processing to obtain driving domain images, and storing the driving domain images to the memory. The cabin domain image signal processing module is used for reading cabin domain image signals from the memory and processing to obtain cabin domain images, and storing the cabin domain images to the memory. The system occupies less space, has shorter data transmission delay, lower cost, avoids data transmission interference caused by too long lines, and data transmission errors caused by line faults.

An electronic terminal (TL2) comprising: an application processor (AP1); a secure processor (SP1) comprising encryption calculation means; at least one display device (D3); a selection device (TPD) enabling a user to select all or part of an image displayed on the display device by the application processor or by the secure processor; the terminal being configured to perform a copy function of copying data (ADD) selected by the user from an image displayed by the application processor into a secure clipboard memory (CB2), the copy function comprising the steps of: copying an image (IMG1) displayed on the display device by the application processor into an image memory (FBUF2) of the secure processor, displaying the copied image on the display device, selecting an image (ADD) specified by the selection device (TMD) from the copied image, and storing the selected image in the secure clipboard memory.

A system for determining when an occupant in a motor vehicle seat and restrained by a seat belt restraint system has an incorrect body posture, the system comprising: a seatbelt buckle sensor for detecting the presence of a seatbelt buckle locking plate in the seatbelt buckle to determine whether the seatbelt is fastened; a seat belt dispensing sensor for detecting a first seat belt dispensing length and for detecting a second seat belt dispensing length; an occupant posture sensor for capturing an image of an occupant on the vehicle seat; a control module in communication with the seat belt buckle sensor, the seat belt release sensor, and the occupant posture sensor, the control module having executable code to: Determine the presence of the seat belt locking plate in the seat belt buckle; Determining whether the difference between the first seat belt output length when the seat belt buckle is present in the seat belt buckle and the second seat belt output length is greater than a seat belt output length change threshold; Comparing the image of the occupant captured by the occupant posture sensor with at least one stored image and posture zone if the difference between the first seatbelt output length and the second seatbelt output length is greater than the seatbelt output length change threshold; and Determine whether the occupant has an incorrect posture by comparing the captured image of the occupant with at least one of the stored images and the posture zone. wherein the occupant posture sensor is an ultrasonic sensor, wherein the stored image is at least one of a reference posture image and an actual initial posture image, wherein the posture zone is at least one of a reference posture zone and an actual initial posture zone, where the actual initial posture zone is determined from an actual initial posture image, wherein the control module further comprises executable code for storing the first seatbelt output length within at least a first time window and a second time window, wherein the reference posture image is selected based on the image of the occupant detected by the occupant posture sensor, wherein the reference posture zone is selected from a plurality of stored reference posture images based on a shape of the occupant determined from the captured image of the occupant, wherein the control module further comprises executable code for comparing the image of the occupant captured by the occupant posture sensor with a stored image, further comprising executable code for capturing an image of an occupant on the vehicle seat within at least a first time window or a second time window and storing the image as the stored image, wherein the control module further comprises executable code to determine whether the occupant has an incorrect posture based on the comparison of the captured image of the occupant and the stored image and / or the posture zone, and the posture zone further comprises executable code to determine whether a head, a torso, or a leg of the occupant exceeds a posture threshold.

A multispectral image storage device and a method for manufacturing the same are disclosed. The multispectral image storage device includes: a substrate; an infrared image storage layer including: an amorphous GST (Ge2Sb2Te5) thin-film disposed on the substrate; and at least one crystalline GST thin-film received in the amorphous GST thin-film and having a first thickness from an upper surface of the amorphous GST thin-film, wherein the at least one crystalline GST thin-film has a shape corresponding to a first image; and a visible image storage layer including at least one semiconductor pattern disposed on the infrared image storage layer so as to generate a second image based on light of a visible light wavelength.

A video encoder or a video decoder is disclosed which uses Intra Block Copy (IntraBC) mode. If IntraBC mode is enabled and a loop filter is not used for a current picture, a current decoded reference picture for the current picture is marked as a long-term reference picture before and during the decoding of the current picture. The current decoded reference picture is assigned to a reference picture list construction for IntraBC reference of the current picture, and by considering a buffer which stores only one reference picture, a buffer storage degree of a decoded picture buffer is calculated before starting to decode the current picture. According to another method, if a maximum decoded picture buffer size is 1, a variable or a syntax element is set to a target value to limit to use only one picture storage buffer in the decoded picture buffer to store a reference picture for encoding or decoding the current picture.

The invention discloses a portable handheld endoscope which comprises a handheld control part, a rigid endoscope tube and a light source illumination module, wherein the rigid endoscope tube and the light source illumination module are detachably connected; the handheld control part is integrated with an image acquisition module, a main control board, an image display module, a key operation module and an image storage module; the device is small in size and portable, and can be independently and effectively used in scenes such as field combat without fixed medical facilities for clinical experiment and preliminary diagnosis.

This invention belongs to the field of image storage technology and solves the technical problem of video discontinuity caused by existing storage methods that transfer real-time video images from different folders to SD cards. It provides a method, apparatus, electronic device, and medium for step-by-step video data storage. The method includes transferring video images from the cache queue to the memory area using a first thread, and then transferring the video files from the memory area to a storage device such as an SD card using a second thread. This ensures that the processes of storing video images from the cache queue into the memory area and further transferring them to the SD card are independent. The first thread continuously creates files in the memory area to write the cached video images to the cache queue, while the second thread performs a second transfer of temporary video from the memory area. This controls the time interval between closing the current file and creating the next file in the memory area, preventing data frames corresponding to previously cached images from overflowing and being lost, thus ensuring video continuity.

The utility model relates to the technical field of image storage, in particular to a medical image storage device which comprises a storage box, a storage cavity is arranged in the storage box, an extraction structure is arranged in the storage cavity, connecting structures used for splicing are arranged on the two sides of the storage cavity, a movable cover plate is movably installed on one side of the storage box, and the movable cover plate is arranged on the other side of the storage box. A magnetic block is arranged on one side of the storage box and magnetically attached to the movable cover plate, a user opens the movable cover plate and pushes a film into the storage cavity, the film is conveniently protected, when the user extracts the film, the user pulls an extraction frame, the extraction frame drives an extraction rod to move, and the film can be conveniently extracted. And an extraction rod drives a moving block to move along a guide rod through a sliding block, a reset spring is compressed, the moving block drives a push strip to move in a storage cavity, the film can be pushed out of the storage cavity, and the film can be extracted conveniently.

To provide an imaging device capable of maintaining security while suppressing a processing time.SOLUTION: An imaging device includes an imaging unit that images a subject, a temporary storage unit that temporarily stores an image obtained by imaging with the imaging unit, a storage unit that stores the image in a storage medium, a transfer unit that transfers the image to an external device, a setting unit that sets a security mode, and a control unit that, when the security mode is set to a first mode with a high level of security, stores the image only in the temporary storage unit without storing it in the storage medium, and deletes the image from the temporary storage unit when the transfer of the image to the external device is successful or fails.SELECTED DRAWING: Figure 1

The invention discloses a vehicle collector shoe detection method, device and equipment and a storage medium, is applied to vehicle collector shoe detection equipment comprising a collector shoe acquisition unit, a collector shoe image storage and recognition unit and data transmission equipment, and relates to the technical field of automatic detection. Comprising the following steps: generating a pulse signal by using magnetic steel in a collector shoe acquisition unit when a vehicle passes, and sending the pulse signal to an area-array camera in the collector shoe acquisition unit to acquire an image of a collector shoe to obtain a target collector shoe image; transmitting and storing the target collector shoe image to a collector shoe image storage and identification unit by using data transmission equipment; a deep neural network classifier in the collector shoe image storage and recognition unit is used for carrying out component positioning on the target collector shoe image to obtain a component positioning result, geometric dimension, inclination angle and surface defect detection is carried out on the component positioning result in sequence, and an abrasion value detection result, a crack detection result and a notch anomaly detection result are obtained; the efficiency of detecting the collector shoe is improved.

The application discloses an image anomaly detection method and device, a computer device and a storage medium. The image anomaly detection method comprises the following steps: acquiring a to-be-detected image; detecting the to-be-detected image by using a preset general image detection mode to determine whether the to-be-detected image is an abnormal image; detecting the to-be-detected image by using a preset special image detection mode to determine whether the to-be-detected image is an abnormal image; and determining that the to-be-detected image is an abnormal image when at least one general image detection mode in the preset general detection mode determines that the to-be-detected image is an abnormal image or at least one special image detection mode in the preset special detection mode determines that the to-be-detected image is an abnormal image. The application can reduce the storage space occupied by abnormal images, improve the utilization rate of normal images, improve the detection efficiency of abnormal images, meet the requirements of different scenes, and has wide applicability.

An image-based optical scanner utilizes methods to provide unique actions, such as notifications or other indications for specific results of checks on GS1 label application data. A scanning device may include an imager configured to capture images of items passing through a field of view, a memory having rules stored thereon associated with actions to be taken based on decoded GS1 label application data, and a processor operably coupled to the imager and the memory, the processor configured to generate unique actions for specific results of checks on GS1 label application data decoded from a GS1 Digital Link label on the item.