247 results about "Camera image" patented technology

This application relates to a robotic method for precise ore sampling in complex mining environments, specifically in the field of ore feature recognition. The method includes: acquiring LiDAR point cloud data and industrial camera image data; after voxelizing the point cloud data, obtaining LiDAR BEV features through an improved SPConv sparse pyramid convolution operator feature extraction network, spatial reconstruction unit, and channel reconstruction unit; extracting semantic features from the image data to generate an image BEV feature map; fusing the two data elements-wise in the BEV space; extracting multi-scale features from the fused BEV feature map using a dual-branch Decoder network; introducing a KA attention mechanism to weight the fused features; and calculating a sampling priority score based on the weighted feature map to determine the optimal sampling point and plan the path. This method can improve ore recognition accuracy in complex mining environments and shorten the decision-making time for the entire process of sampling location determination and path planning.

This application belongs to the field of autonomous driving technology, specifically relating to a multimodal data processing method and apparatus for end-to-end autonomous driving. The method includes: extracting multi-scale features from camera images and LiDAR bird's-eye view images through multiple feature extraction stages of an encoder; performing a feature fusion operation on the image features and LiDAR features of each feature extraction stage after each stage; after the final stage, segmenting at least a first output stream for trajectory prediction from the split LiDAR features; performing a feature enhancement operation on the first output stream and vehicle state features to generate enhanced features; and decoding the enhanced features to generate a sequence of future trajectory points for the vehicle. This application significantly improves inference efficiency and enhances environmental robustness while maintaining perception depth.

A technology capable of suitably correcting a geometric distortion caused by a shape of a curved surface of a screen or the like and obtaining a suitable image easily viewable for a user is provided. A projector is an image display apparatus configured to project an image onto a screen and includes a projection lens arranged at a first position and a camera arranged at a second position. When the screen has a curved surface, a camera image obtained by capturing a first image projected on the screen by the camera is acquired, and a geometric transformation for correcting a geometric distortion caused by the curved surface seen from a first virtual viewpoint position (virtual viewpoint) is performed for an image to be displayed based on information of the camera image, the first position, and the second position, and a post-transformation image is projected onto the screen.

This invention provides a rapid exposure adjustment system and method for high-speed space cameras, belonging to the field of deep space exploration. Combining camera image grayscale statistics and PIN tube metering technology, it integrates the advantages of two traditional exposure time adjustment methods. This system can meet the needs of rapid exposure time adjustment for high-speed cameras in transiently bright scenes, avoiding overexposure of consecutive images due to transient brightness caused by impacts. Simultaneously, it can achieve fine-tuning of exposure time in scenes with gradually changing targets, ensuring imaging effects on sputtering clouds generated by impacts. This invention implements an exposure time adjustment method that combines fast and slow adjustments, as well as coarse and fine adjustments, effectively guaranteeing imaging effects in complex scenes throughout the entire kinetic energy impact process.

Baseline monitoring system (10), comprising: at least one camera (14) mounted in a first motor vehicle (12); at least one waveguide (26) guiding light into the at least one camera (14), with a first coupling grating (28) receiving first light imaging data (30) and transmitting the first light imaging data (30) as a first frequency of light, and a second coupling grating (32) receiving second light imaging data (34) and transmitting the second light imaging data (34) as a second frequency of light; at least one color filter wheel (42) receiving the first frequency of light and the second frequency of light; at least one image sensor (44) of the camera (14) receiving the first frequency of light and the second frequency of light at different times due to a rotation of the at least one color filter wheel (42);and at least a controller (20) that performs a calculation using directions and angles of the first frequency of the light and the second frequency of the light to correct at least one camera image (56).

The application provides a pinhole image splicing true value acquisition and splicing method based on a heterogeneous camera combination. The acquisition method first symmetrically installs two pinhole cameras on a support, and installs an fisheye camera between the two pinhole cameras. Based on a double spherical camera model, the three cameras are calibrated to obtain the internal parameters and external parameters of the three cameras. The left eye pinhole view, the right eye pinhole view and the middle eye fisheye view of the target scene are simultaneously acquired by using the three cameras. The middle eye fisheye view is subjected to equirectangular projection. According to the internal parameters and external parameters of the three cameras, the left eye pinhole view and the right eye pinhole view are projected to the equirectangular projection view plane respectively, multi-camera coordinate system one is completed, and the splicing true value is obtained. The application has the core advantages of the hardware structure design and the heterogeneous camera image registration algorithm, can stably acquire images without seams and time sequence consistency, and provides strong support for the true value reference of the precision verification and model training of subsequent panoramic video splicing.

This application belongs to the field of computer vision and optical measurement technology, specifically disclosing a point cloud stitching method and apparatus based on monocular pose prior marker matching. The method includes: calculating the pose of multiple markers extracted from left and right camera images, determining the normal vector and three-dimensional coordinates of each marker's circular cross-section in its respective camera coordinate system; transforming the three-dimensional coordinates and corresponding normal vectors of each marker in either the left or right camera image to the other camera coordinate system for marker point registration between the left and right camera images; the circular cross-section is a circular cross-section in three-dimensional space with the origin of the camera coordinate system as its vertex, passing through the elliptical curve where the marker is located; and stitching the three-dimensional point cloud of markers based on the marker point registration results of the left and right camera images. This application can significantly improve the accuracy of binocular stereo marker matching and the system's anti-interference capability in complex industrial scenarios.

The invention relates to a sensor assembly (1) comprising a computing unit (6) for evaluating sensor data and a camera sensor (2) for detecting surroundings which comprises at least one image sensor (4), a lens arrangement (3), a housing and at least one means (5) for varying the image plane, wherein the image plane is moved by the at least one means (5) for varying the image plane, wherein during the varying of the image plane a sequence of camera images is recorded.

The application provides a neural network-based cross-camera image matching method and device, wherein the method comprises: constructing first and second image pyramids with N layers of gradually reduced resolution for first and second images respectively; extracting feature vectors of each layer of the second image pyramid using a deep neural network to obtain N reference feature vectors; performing global search on the Nth layer of the first image pyramid according to the Nth reference feature vector to determine an initial matching region; mapping the initial matching region to the N-1th layer of the first image pyramid to obtain a mapping region, and expanding the mapping region according to a preset expansion amount to form a restricted search region; performing local search on the restricted search region according to the N-1th reference feature vector to obtain a matching region of the current layer; repeating the mapping and local search steps until the first layer of the first image pyramid is reached, and outputting the matching result in the first image. The application does not require distortion correction and a large amount of training data.

The application discloses a coal overflow identification system of a coal conveying system based on marker edge detection, which comprises a PLC module, a computing server module, a video monitoring module, a belt module, a display interface module and an emergency rescue module, wherein the six modules are sequentially connected, the PLC module controls the belt operation, the video monitoring module transmits monitoring to the server module, when the server detects that the blockage occurs, the display interface module displays the alarm level, and the emergency rescue module is informed to perform corresponding rescue treatment. The application can process more than 10 camera images by adding only one computer, has low cost and good effect, can realize early warning in a place with clear camera and suitable environment, and can realize synchronous alarm even in a harsh environment due to the use of a certain value of the threshold. The operation personnel can reduce the time and energy spent on monitoring, thereby greatly saving the labor cost of the enterprise.

This invention relates to the technical field of industrial machine vision and collaborative control of swarm robots, and particularly to a quality inspection method for swarm vision robots based on multi-agent reinforcement learning. The method includes: acquiring images of the workpiece to be inspected at a preset sampling period, and writing robot pose identifiers and camera imaging parameter identifiers into each frame of the image to form a quality inspection observation set; performing N forward inferences on the quality inspection observation set under a defect detection network with a random deactivation layer, generating uncertainty prediction values ​​using the defect confidence variance, and calculating a risk score matrix to determine a risk region set; inputting the risk score matrix, the risk region set, and the robot pose identifiers into a multi-agent reinforcement learning model to output a candidate observation action set; acquiring supplementary images based on the candidate observation action set and updating the risk score matrix using weighted voting based on the uncertainty prediction values; writing risk regions that meet the threshold into a review task set and rolling them into the next sampling period.

The application discloses a vehicle-mounted camera image interference stripe elimination method, system and equipment based on an aging state self-adaption, wherein the method comprises the following steps: S1: acquiring real-time image data collected by a camera and converting the real-time image data into a frequency spectrum; S2: periodically collecting a plurality of frequency spectrum and calculating a current interference frequency; S3: calling all historical interference frequency data stored locally by the camera, comparing the current interference frequency with the historical interference frequency through a first threshold value and a second threshold value; and S4: adjusting the parameters of a filter by using the updated interference frequency data and adaptively filtering the real-time image data. According to the application, the filtering characteristics are dynamically adjusted according to environmental changes, the filter is always configured in an optimal working state, the subsequently generated filter parameters can more accurately suppress existing interference, the dynamic changes of the interference have a quick response capability, the robustness of the system is improved, and the stability of the image quality is ensured.

This invention belongs to the field of data processing technology and provides a method and application for automatic time alignment of radar and image data based on target association. The method includes: creating a time search window on the time axis of the image data stream for each frame of radar data in the radar data stream; projecting each radar target in the radar dynamic target list onto the image coordinate system; for each frame of image within the time search window, counting the number of projection points falling into the image detection box to generate a target association score; selecting the radar frame and image frame with the highest target association score as a synchronization frame pair; calculating the timestamp offset based on the timestamp of the synchronization frame pair; and selecting a corresponding time alignment strategy to automatically align the radar data stream and image data stream based on the statistical stability of the calculated timestamp offsets. This invention can solve the problem of timestamp asynchrony between independently recorded millimeter-wave radar point cloud data and camera image data; and can achieve automatic offline time alignment.

The application discloses a kind of non-rigid space mapping-based multi-camera multi-target tracking methods without calibration, it is related to computer vision and intelligent video analysis technical field.The method includes: obtaining the position of target bounding box in each camera and the corresponding appearance feature representation;Extract the effective area that can be used for geometric modeling, generate binary effective area mask;Get dense displacement field and spatial correspondence confidence;Fixed step is constructed on the source camera image Sampling grid, the grid point is screened, and the high-confidence control point set from source view to target view is formed;According to the control point set, establish the cross-camera space mapping relationship under non-calibration condition;The spatial geometric similarity of target bounding box in different cameras is calculated, and the cross-camera target association is carried out by combining the appearance feature similarity, to realize the multi-camera multi-target tracking under non-calibration condition.The method can establish the cross-camera space mapping relationship, realize stable multi-camera multi-target tracking.

The invention relates to a method for seat occupancy detection in a vehicle (1), wherein camera images (KB) of a vehicle interior (1.1) are captured and evaluated by means of an interior camera (2). According to the invention, a camera image (KB) captured during the evaluation is compared with a CAD model (3) of the vehicle interior (1.1), wherein a seat occupancy is detected based on the comparison by means of an electronic processing unit using a background-oriented schlieren method.

The application discloses a kind of unmanned plane omnidirectional obstacle avoidance methods based on millimeter wave radar and binocular laser module, forward binocular laser obstacle avoidance module is set below unmanned plane center disc, and obstacle detection within 40m range is realized by double camera image processing plus laser ranging;Millimeter wave radar module is set in upper, lower, rear, left and right 5 directions below unmanned plane center disc, and obstacle detection within 40m detection distance can be realized.The omnidirectional obstacle avoidance method of unmanned plane of the application adopts omnidirectional detection of obstacle avoidance detection module, whether unmanned plane and obstacle will collide is judged using collision detection algorithm, if collision will be generated or dangerous approach will be generated, unmanned plane route is re-planned using velocity field method and dynamic window method, and omnidirectional obstacle avoidance function is realized.The unmanned plane obstacle avoidance mode of the application can be upgraded, the optimization of unmanned plane omnidirectional obstacle avoidance is realized, the effect of obstacle avoidance is good, safety is high, and omnidirectional obstacle avoidance detection has the advantages of long detection distance, stable detection performance and the like.

The utility model relates to industrial automation equipment vision system protection technical field, concretely relates to a kind of high protection degree industrial camera protection device.The device includes drive unit and protection unit, protection unit is used to cover industrial camera imaging face when protecting state;Drive unit includes drive box, pneumatic mechanism and linear variable rotary motion mechanism are provided in drive box, linear variable rotary motion mechanism includes linear motion piece and rotary motion piece, pneumatic mechanism drives linear motion piece linear motion, linear motion piece drives rotary motion piece rotation, rotary motion piece protection unit is rigidly connected by connecting piece, rotary motion piece swings the protection unit by connecting piece, to open and close industrial camera imaging face.Pneumatic mechanism cooperates linear variable rotary motion mechanism, drives protection unit swing, without complex connecting rod structure, protection unit overturning can be realized, automation drives protection unit cover industrial camera imaging face, without manual opening and closing, ensure operation efficiency.

To perform personal authentication using an image without registering a camera image, the present invention provides a processing apparatus 10 including: an acquisition unit 11 that acquires collation information including a camera image being an image of a collation-target person generated by a camera, or an image being restored from the camera image and representing a three-dimensional shape of a person; a collation unit 12 that collates the collation information with reference person information including an image being restored from a camera image and representing a three-dimensional shape of each of a plurality of reference persons; and an output unit 13 that executes processing depending on a result of the collation.

The application discloses a kind of measuring camera image high dynamic range device and method, it is provided with optical darkroom, wide dynamic light source, lens and host computer, wherein lens is installed at the opening of optical darkroom, wide dynamic light source is installed in optical darkroom inside facing lens, and wide dynamic light source includes LED lamp group and time sequence control circuit module;The target surface of the scientific camera to be measured is connected with lens, and host computer is connected with the scientific camera to be measured to establish control connection and data connection;Host computer starts the scientific camera to be measured and sends measurement start instruction to time sequence control circuit module in wide dynamic light source, time sequence control circuit module starts LED lamp group and controls the light-emitting duration of each LED lamp, after the image is photographed to the scientific camera to be measured, it is uploaded to host computer, and host computer obtains the dynamic range of the scientific camera to be measured by detecting the number of LED light spot in image.This application obtains dynamic range by analyzing the image that the scientific camera to be measured is photographed to wide dynamic light source, effectively improves dynamic ratio measurement range.

This invention relates to a privacy protection method for baby care cameras based on instance segmentation detection, comprising: Step 1, region detection, using an instance segmentation detection algorithm to identify and locate the adult region, the baby region, and the background region; Step 2, background region processing, the identified background region is first reduced in size, then Gaussian blurred, and then enlarged back to its original size to obtain a Gaussian blurred background region, which is then filled back into the original background region. The privacy protection method for baby care cameras based on instance segmentation detection obtained by this invention has the following advantages: the algorithm segments the camera image into adult, baby, and background regions, providing a foundation for subsequent processing; reducing the background region saves computational power required for subsequent processing, improving processing efficiency; and by combining modern image processing technology and artificial intelligence algorithms, it achieves efficient and aesthetically pleasing privacy protection measures.

The application provides a kind of image processing method based on folding screen equipment and folding screen equipment, to improve the display quality of the shooting picture and screen utilization of folding screen equipment in various forms. In the method, when it is detected that the folding screen equipment is in the unfolded state, and in the scene where the main camera is used for shooting, the main camera can be called to shoot to obtain a main camera image, and at the same time, a wide-angle camera can also be called to shoot to obtain a wide-angle image. Then, after aligning the main camera image and the wide-angle image, the target image based on the main camera image and the wide-angle image can be obtained by cropping the wide-angle image based on the height of the main camera image. Compared with only the main camera image, the target image can have a wider viewing angle.

The application provides a shore bridge ship side anti-punching person detection method and system based on machine vision, wherein the method comprises: obtaining a detection frame of a target by using machine vision technology, and transforming a personnel detection frame of a second camera into an image coordinate system of a first camera; calculating an estimated pixel coordinate of a spreader when the spreader is lowered to a personnel height in real time according to a position, a size of a current spreader detection frame and a distance from the spreader to the camera; determining a distance between the spreader and the personnel by using the estimated spreader and the personnel detection frame pixel coordinates; and generating an alarm information when the distance between the spreader and the personnel is less than a safety distance. The application calculates the distance from the personnel and the spreader to the camera by using a depth estimation network and a camera imaging principle, estimates the distance between the spreader and the personnel when the spreader is lowered to the personnel height according to the distance, and generates an alarm information according to the distance value, thereby solving the problem that the automatic spreader anti-punching person alarm judgment cannot be performed due to the change of the height from the ship to the camera.

The application relates to the technical field of submarine cable laying, and particularly discloses a buried plow into plow mouth submarine cable length measurement and control method and system. The submarine cable length measurement method and system adopts a dual-frequency sonar to perform sonar detection on the buried plow into the plow mouth to obtain a sonar image, adopts a turbid water camera to shoot the buried plow into the plow mouth to obtain a camera image, combines the specific size of the submarine cable, performs three-dimensional reconstruction on the sonar image and the camera image, displays a submarine cable three-dimensional graph, and can infer and identify the working state and the length of the submarine cable according to the graph. The submarine cable length control method and system can adjust the cable laying speed of a submarine cable ship in real time according to the real-time predicted submarine cable length of the buried plow into the plow mouth, can keep the length of the submarine cable into the plow mouth constant in the laying of the complex seabed environment, that is, can keep the tension of the submarine cable into the plow mouth constant in the laying of the complex seabed environment and further protect the submarine cable.

This invention discloses a method for extrinsic parameter calibration of a LiDAR and camera based on directional equalization, comprising the following steps: extracting edge feature maps from the camera image and performing Euclidean distance transformation on the edge feature maps to obtain the range field and its gradient; performing voxel downsampling on the LiDAR point cloud and using a region growing algorithm to segment the principal plane from the downsampled LiDAR point cloud; solving for the intersection lines between adjacent principal planes pairwise to obtain LiDAR edge line features; transforming the LiDAR edge line feature points to the camera coordinate system and projecting them onto the image plane, and performing bilinear sampling of the range field and its gradient at the projected pixel positions; constructing a global orientation histogram and calculating the directional equalization weights; constructing a joint objective function that fuses the range field residuals and the directional equalization weights; and iteratively optimizing the joint objective function to solve for the optimal extrinsic parameters between the LiDAR and the camera. The advantage of this invention is that it improves the stability of extrinsic parameter estimation.

A work machine surroundings monitoring system includes a first display image generation unit that generates a first display image indicating surroundings of a work machine on the basis of a camera image of a camera that captures an image of the surroundings of the work machine, a second display image generation unit that generates a second display image in a display mode different from that of the first display image on the basis of camera images of a plurality of cameras that capture images of the surroundings of the work machine, and a display control unit that generates a signal for displaying the first display image on a part of a display screen, displaying the second display image on a part of the display screen, and displaying a boundary image at a boundary between the first display image and the second display image on the display screen.

This invention provides a scanning probe microscope, including a laser, a probe, a position-sensitive detector, a camera, and a liquid lens. The liquid lens is disposed in the optical path between the camera and the probe. When the liquid lens is in a first state, the camera images the probe arm at least through the liquid lens; when the liquid lens is in a second state, the camera images the object under test at least through the liquid lens. This invention integrates the observation optical paths of the probe and the object under test into a single optical element, greatly reducing the size of the device. It enables switching between imaging of the probe arm and the surface under test without moving the optical element, reducing interference with the imaging effect caused by the movement of the optical element. It can quickly switch the imaging object, improving efficiency. The focal length of the liquid lens can be continuously varied, facilitating matching different surfaces under test and probe arm positions, thereby increasing the applicability of the scanning probe microscope.

This remote support system helps reduce the burden on users who use remote support devices for remote vehicle support. [Solution] The remote support system comprises a vehicle and a remote support device. The vehicle includes multiple cameras. The remote support device is a device for communicating with the vehicle and providing remote support to the vehicle. At least one of the vehicle and the remote support device includes an image synthesis device that synthesizes multiple camera images captured by the multiple cameras according to predetermined image synthesis rules. The remote support device includes a display that shows the synthesized image synthesized by the image synthesis device and an adjustment device that adjusts the image synthesis rules according to the user operation of the remote support device.

The application provides a fast exposure adjustment system and method for a space high-speed camera, belongs to the field of deep space exploration, combines camera image gray scale statistics and PIN tube photometry technology, collects the advantages of two traditional exposure time adjustment methods, can meet the fast exposure time adjustment of the high-speed camera in a transient light scene, avoids overexposure of continuous images of the camera due to impact of transient high light, and can also realize fine adjustment of the exposure time in a slowly changing target scene, so as to ensure the imaging effect of a sputtering cloud of sputtering objects generated by impact. The exposure time adjustment method combining fast adjustment with slow adjustment and coarse adjustment with fine adjustment is realized, so that the imaging effect of a complex scene in the whole process of kinetic energy impact can be effectively ensured.