33 results about "Stereo camera" patented technology

Methods, systems, mobile devices, and non-transitory computer-readable mediums for determining a scale of an object with a mobile device. The mobile device includes at least one object-facing camera (e.g., a monocular camera) and an away-facing stereo camera system. Information captured using the away-facing stereo camera system is used to estimate relative pose information for determining the scale of the object in images captured by the object-facing camera. The proposed system leverages the scene images surrounding the mobile device to resolve scale ambiguity and calculate the absolute scale.

The invention relates to a robotic lawnmower (10) comprising: - a sealed main housing (60) for receiving a control or regulation unit (110), in particular comprising a main circuit board (111); - a sealed sensor module (20) for environmental detection, in particular a camera module (112), preferably a stereo camera module (21); - wherein a seal between the main housing (60) and the sensor module (20) is provided by a common cable-guiding sealing element (33).

An imaging apparatus has a plurality of cameras, each including: an imaging device in which unit pixels are periodically arranged, the unit pixels including high sensitivity sub-pixels that output a first output value for a certain exposure amount and low sensitivity sub-pixels that output a second output value lower than the first output value for a certain exposure amount; a composition section that selects and outputs an output of the high sensitivity sub-pixels and an output of the low sensitivity sub-pixels when the exposure amount is smaller or larger than the predetermined exposure value, respectively; and an amplification section that amplifies and outputs an output of the composition section, and so that image signals of the high and low sensitivity sub-pixels in the same predetermined exposure values become the same between the plurality of cameras, corrects the image signals of the high and low sensitivity sub-pixels.

The invention relates to a test system for testing a LIDAR device (1), comprising a controller (5) for generating LIDAR information relating to a simulated LIDAR object based on a real object to be reproduced for a test process, wherein the LIDAR information includes at least one item of two-dimensional contour information and an item of depth information relating to a virtual distance of the simulated LIDAR object; comprising a LIDAR image generation device (6) for generating the simulated LIDAR object based on the LIDAR information; and comprising a LIDAR projection device (7) for projecting the simulated LIDAR object (9) onto a projection surface (8). The depth information is determined on the basis of a time component between the projection surface (8) and the LIDAR device (1) to be tested, which is defined by the controller (5). In one embodiment, a video image generation device can be provided, in order to generate a visible video image of at least one real object on the projection surface. The IR image which is not visible for people and which is projected by the LIDAR projection device is overlayed in a synchronised manner with a video image that is visible for people. In a variant, the test system is suitable for also testing a stereo camera, in addition to the LIDAR device, e.g. which is integrated in a vehicle to be checked, but can also be provided independently, yet in combination with the LIDAR device.

A system for providing situational awareness to a cyclist or other user of a micromobility vehicle comprises a stereo camera assembly and processing logic configured to determine, based on images acquired by the stereo camera assembly, a distance between the cyclist and an object of interest (e.g., a vehicle). The system is configured to determine a threat level of the object based one or more factors such as, e.g., a speed of the object and / or a category of the object. In some examples, the system includes a display and / or an audio indicator to convey information to the cyclist about detected threats. In some examples, the system is configured to produce an audio indication in response to a threat exceeding a threshold threat level. A software platform may be configured to store and / or process micromobility data gathered from one or more users.

A camera calibration method for calibrating a camera that captures an image through a windshield includes acquiring a calibration image associated with a calibration object by imaging by the camera. A calibration object has a linear portion extending in one direction intersecting an optical axis of the camera through the windshield, and the calibration object is a wire or a bar. The method further includes extracting a first linear portion image corresponding to the linear portion from the calibration image. The method further includes correcting distortion of the calibration image by comparing the first linear portion image with a second linear portion image captured when the linear portion is imaged by the camera not through the windshield.

The invention relates to a camera-based service robot (1), in particular a robotic lawnmower (10), with a first camera module (112), in particular a front camera module (112a), preferably a stereo camera module (113). It is proposed that a second camera module (112), in particular a rear camera module (112b), preferably a stereo camera module (113), is structurally identical to the first camera module (112) and / or that the height (hv, hr) of the lenses (23a, 23b) of the camera modules (112) above a mounting or standing plane (104) of the service robot (1) is essentially the same, and / or that a camera module (112), preferably the front camera module (112a), is arranged in particular directly above a control or regulating unit (110) and / or that a camera module (112), preferably the rear camera module (112b), is arranged in particular directly above a battery pack compartment (12).

The invention discloses a device for guiding a six-axis collaborative robot to move through a three-dimensional camera and a laser, and the device comprises the six-axis collaborative robot (10) and a three-dimensional camera and laser combined device (20) which are installed on a support (1). The three-dimensional camera and laser combination device (20) further comprises a three-dimensional camera (2), a laser mounting rack (3) and at least two lasers. The three-dimensional camera (2) is rotatably mounted on the support (1) through a first multi-angle indexing table (5), the laser mounting rack (3) is rotatably mounted on the support (1) through a second multi-angle indexing table (6), and the laser is rotatably mounted on the laser mounting rack (3) through a multi-angle rotating table (7). The device provided by the invention can guide the robot to operate through real-time three-dimensional modeling, more accurately detect or calibrate an object, realize visibility and remote control, and is wide in application.

A work information projection system for estimating a position in a work site. The work information projection system includes a camera (13), a stereo camera (14), and a control device. The camera (13) is disposed toward a first direction, and acquires first environment information that is information of an object disposed in the first direction and around. The stereo camera (14) is disposed toward a second direction, and acquires second environment information that is information of an object disposed in the second direction and around. In a case where it is determined that the second environment information cannot be acquired, the control device estimates a position in a first coordinate system based on the first environment information.

1. Name of the product in this design: Housing and main body of a binocular camera. 2. Purpose of this design: The overall purpose of the product is to serve as the main body of a stereo camera, supporting the output of data such as RGB images, infrared images, and / or depth images; the partial purpose of the product is to serve as the housing of the stereo camera, used to cover the internal structure of the stereo camera, serving both protective and decorative functions. 3. The key design feature of this product is its shape. 4. The picture or photo that best illustrates the key design points: Design 1 3D diagram 1. 5. Design 1 is designated as the basic design. 6. Other matters requiring explanation: The area shown by the dashed lines in the product view of this design is not claimed for protection.

An ultrasonic diagnostic apparatus that assists an insertion task of a puncture needle into a subject is provided. The ultrasonic diagnostic apparatus includes: an ultrasonic probe that acquires an ultrasonic image of an inside of the subject by transmitting and receiving ultrasonic waves; first and second optical cameras attached to the ultrasonic probe and capturing the puncture needle at the insertion task; and a hardware processor. The hardware processor performs image analysis on first and second images generated by the first and second optical cameras, respectively, and detects an insertion angle of the puncture needle relative to a body surface of the subject using a stereo camera principle. The hardware processor calculates a predicted arrival position of the puncture needle from the insertion angle, and displays a guide image indicating the predicted arrival position on a monitor so as to be superimposed on the ultrasonic image.

An image processing device of a person detection system suppresses a decrease in detection accuracy of a person. The person detection system is installed in a forklift. The person detection system includes a stereo camera and the image processing device. The image processing device acquires first image data and second image data from the stereo camera. The image processing device detects a rectangular region in which an obstacle is present from the first image data. The image processing device estimates a barycentric position of the obstacle included in the rectangular region in the first image data, and performs barycentric region width adjustment processing of adjusting a width of the rectangular region according to the barycentric position. The image processing device determines whether the obstacle present in the rectangular region is a person by comparing an adjusted region after the barycentric region width adjustment processing is performed with dictionary data. The dictionary data is data of a feature quantity extracted from image data in which a person is present.

The present disclosure provides a processing device that detects a setting deviation of a camera with respect to a marker caused by a setting deviation of a vehicle or a mounting deviation of the camera when a monocular camera or a stereo camera is mounted to the vehicle to take a shot of the marker for calibration, corrects an image deviation caused by glass in a manner that is not affected by the factor, and thereby accurately measures a distance. The processing device of the present disclosure acquires a setting deviation of a vehicle-mounted camera based on images taken of a plurality of markers (101, 102, 103) that differ in distance from the vehicle-mounted camera (stereo camera (104)) and data of a window (front windshield (112)) of a modeled vehicle (111), and uses the setting deviation to change correction data for correcting images of the vehicle-mounted camera. The setting deviation is a positional deviation with respect to a position at which a card of the marker (101, 102, 103) should be disposed.

This invention discloses a shipborne intelligent fish box, relating to the fields of artificial intelligence and fisheries information technology. It includes a fish box shell, a Jetson embedded main control module, a ZED stereo camera, an electronic scale module, a light source control module, a network communication module, and a cloud data platform. After the user presses the weighing button, the camera acquires RGB and depth images of the fish. The main control module identifies the fish species using the YOLOv11 algorithm, outputs key point coordinates, and calculates the fish length and width using 3D back projection combined with camera intrinsic parameters. The electronic scale simultaneously measures the weight. All data is encapsulated as structured information, displayed on a local screen, and then uploaded to the cloud via the network. The device achieves fully automated integration of fish identification, measurement, weighing, recording, and uploading, adapting to complex shipborne environments, ensuring data consistency and traceability, and is suitable for scenarios such as nearshore catch monitoring, aquaculture sampling, and compliance traceability.

To prevent contact with obstacles located on the opposite side of the direction of travel. [Solution] The industrial vehicle 10 comprises a vehicle body 11 and an obstacle detection unit. The obstacle detection unit comprises one stereo camera, two side cameras, and a detection device. The detection device uses images acquired from the stereo camera to detect obstacles in the rear range behind the vehicle body 11. The detection device uses images acquired from the side cameras to detect obstacles in the lateral range to the sides of the industrial vehicle 10. The control device changes the starting restriction area A according to the direction of travel and steering angle of the industrial vehicle. The control device restricts the starting of the industrial vehicle 10 when an obstacle is located in the starting restriction area A.

An obstacle detection device (30) is mounted on a forklift (10). The obstacle detection device (30) includes a stereo camera (31) for detecting an obstacle and a position detection device (41) for detecting a position of the obstacle based on a detection result of the stereo camera (31). A non-detection area (NA1, NA2) is set in advance in a detectable area (CA). The non-detection area (NA1, NA2) is set at a position where a counterweight (15) of the forklift (10) exists. The position detection device (41) determines that there is no obstacle in the non-detection area (NA1, NA2). The position detection device (41) detects a position of an obstacle existing in a detection area (DA) that is an area different from the non-detection area (NA1, NA2) in the detectable area (CA).

The purpose of the present invention is to provide an image processing device capable of accurately calculating the distance to an object serving as a light source on the basis of a normal exposure image captured by a stereo camera. To this end, an image processing device (100) is provided with: a stereo camera (10) that captures a first image (P1); a normal shutter image processing unit (102) that detects first object information from the first image (P1); an object information acquisition device (10) that acquires second object information; a distance correction unit (109) that corrects a first distance included in the first object information; and a distance correction value calculation unit (108) that calculates a correction value for the first distance, the distance correction value calculation unit (108) learning a correlation between a spot light amount of the object in the first image (P1) and a difference between the first distance and a second distance included in the second object information; the correction value is calculated on the basis of the correlation and the spot light amount, and a distance correction unit (109) corrects the first distance by subtracting the correction value from the first distance.

The invention provides a binocular camera automatic exposure adjusting method and system based on a depth map. The method comprises the following steps: initializing image control parameters of the binocular camera; starting parameter primary correction based on the image control parameter, and generating a primary exposure parameter of the binocular camera; starting parameter secondary correction by taking the primary exposure parameter as a current exposure parameter, and generating a secondary exposure parameter of the binocular camera; and outputting the secondary exposure parameter meeting a preset dimming condition as a final exposure parameter, and controlling exposure setting of the binocular camera based on the final exposure parameter to realize brightness adjustment of a binocular visual image. The method can adapt to complex scenes with non-uniform illumination and large tissue reflectivity difference in the cavity, the brightness consistency and stereo matching precision of binocular vision images are remarkably improved, and stable and reliable image input is provided for subsequent three-dimensional reconstruction and diagnostic analysis.

An extended reality-based fire training method includes: (a) acquiring each object in a real space acquired through a stereo camera and depth information on each object; (b) reconstructing each object into a 3D mesh object based on each object and the depth information on each object; (c) simulating a virtual fire suppression training augmented reality environment after generating a virtual fire in at least one of the reconstructed 3D mesh objects, and transmitting the simulated virtual fire suppression training augmented reality environment to a head-mounted display device; and (d) operating a virtual fire extinguisher object in a virtual fire suppression training augmented reality environment according to a user manipulation of a real fire extinguisher, and extinguishing a virtual fire object by firing a virtual powder object toward the virtual fire object according to the operation of the virtual fire extinguisher object.

This invention provides a large depth-of-field digital imaging stereoscopic endoscope system, including an endoscope catheter, a binocular digital imaging miniature stereoscopic camera, a control and calculation subsystem, and a stereoscopic image electronic display. The control and calculation subsystem includes: an image acquisition and correction calculation module, which performs manufacturing parameter consistency calculations on the acquired raw binocular digital image data to obtain a parameter-consistent image; an image projection and posture correction calculation module, which corrects the phase angle tilt projection of the left and right images and the installation posture error to obtain a corrected image; and an image rearrangement and image output calculation module, which rearranges the corrected image to obtain a correctly projected image, and then outputs the final stereoscopic image. This invention solves the problems of flattened depth of field and viewing dizziness associated with stereoscopic images, improves the technical performance of the equipment, and lowers the technical threshold for the precision manufacturing and maintenance of 3D electronic endoscopes.

This invention provides a method for calibrating a stereo camera in different regions, including image acquisition and calibration processes. The working area is divided into multiple sub-regions for separate calibration. Different calibration parameters are used for coordinate calculation in different sub-regions. During calibration, corner points are first retrieved, followed by single-target calibration, and then dual-target calibration is performed considering camera distortion. After calibration, the data is saved, and the calibration results are used for practical applications. The calibration method provided by this invention overcomes the problem of significant differences in measurement accuracy of a single calibration parameter in different regions.

The application provides a self-encoder training method, system and a deep image generation method. The self-encoder training method comprises: obtaining a stereo image in vehicle operation, wherein the stereo image comprises a left image and a right image; generating a stereo disparity map according to the left image; generating a predicted right image according to the left image and the stereo disparity map; and calculating a first mean square error between the predicted right image and the right image. The self-encoder can be trained according to the image collected by a stereo camera, and the trained self-encoder can output a depth image according to the image of a monocular camera.

Systems, methods, and apparatus that can save power and provide improved lidar images. An example can save power by limiting received photon accumulation to a range of bins corresponding to a range of distances where a position of an object has been predetermined. By not accumulating or binning photon data over an entire range, the amount of data stored each laser cycle can be reduced, and other power saving measures can be realized. By limiting a range over which photon data is accumulated, the resolution of each bin can be increased, thereby improving a resulting lidar image. The position of an object can be predetermined using a stereo camera that can be coupled to, or included as part of, a lidar system. The stereo camera can acquire a pair of images offset by a spacing, and from the pair of images can generate stereo depth estimates. The depth estimates can be mapped to corresponding lidar pixels. The depth estimates can be converted to time intervals, which can be provided to the lidar system. The lidar system can use this to narrow the range over which photon data is collected for one or more pixels.

An image processing device includes: an image comparison unit that compares a first image detected by a first image sensor built in a first camera with a second image detected by a second image sensor built in a second camera, the first image and the second image being inputted from a stereo camera, and that calculates a correction process coefficient for correcting the second image, based on a difference between the first image and the second image in a second direction different from the first direction; andan image processing unit that corrects the second image, using the correction process coefficient calculated by the image comparison unit.

An image-based floating marine object detection and distance measurement system for a small vessel of less than 10 tons is disclosed. The system comprises: an infrared stereo camera and an IR projector provided on a vessel; and an image display system which is connected to the infrared stereo camera and the IR projector through a control API, includes an image correction filter for correcting blurriness due to light reflection, shadow, and sea fog, detects the floating marine object (a discarded fishing net, a rope, a buoy, and marine litter) by a deep learning-based object detection model on the basis of pre-training data of the floating marine object, measures a distance between a camera of a vessel of less than 10 tons and the floating marine object, and displays an image to prevent vessel collision, damage to a propulsion shafting system, and an accident of entanglement between a vessel and floating marine debris through a forward hazard situation alert and a corresponding response. The system uses an infrared stereo camera and an IR projector provided on a small vessel of less than 10 tons in which hull motion, sea fog, and light reflection due to wind and wave heights exist on the sea, so as to detect a floating marine object posing a hazard during vessel navigation, by a vision recognition technology using a floating marine object recognition distance measurement algorithm and a deep learning-based floating marine object recognition model using an AI technology, prevents vessel collision, damage to a propulsion shafting system, and an accident of entanglement between a vessel and floating marine debris through a hazard situation alert and a corresponding response, monitors marine litter, and is used as a marine safe navigation assistance system for a small vessel that is vulnerable to the floating marine object.

In many embodiments of the invention, a video monitoring system for construction sites includes one or more stereoscopic cameras configured to capture image data from multiple viewpoints over time, one or more 360-degree cameras configured to capture 360-degree image data, an edge device configured to receive the image data from the stereoscopic cameras and the 360-degree cameras, generate three-dimensional point clouds from the image data, recognize fiducial markers within the image data, identify objects and estimate movement of the objects in the point clouds using a plurality of machine learning models, and generate alerts based on the identified movement of the objects, and one or more client devices configured to receive the alerts from the edge device.

The invention discloses a three-dimensional (3D) measurement method based on end-to-end deep learning for speckle projection. First, the speckle pattern was projected by the projector and collected simultaneously by the stereo camera. The speckle images after stereo rectification are fed into the stereo matching network. A feature extraction sub-network based on shared weights processes the speckle images to obtain a series of low-resolution 3D feature tensors. The feature tensor is fed into the saliency object detection sub-network to detect foreground information in the speckle images, producing a full-resolution valid mask map. A 4D matching cost volume is generated using the feature tensor of both views based on the candidate disparity range, filtered by a series of 3D convolutional layers to achieve cost aggregation, so that the initial disparity map is obtained by disparity regression. The final disparity map is obtained by combining the mask map and the initial disparity map to achieve a single-frame, robust, and absolute 3D shape measurement. The invention achieves a single-frame, robust, and absolute 3D shape measurement by projecting a single speckle pattern.

Embodiments disclose a real-time surgery method and apparatus for displaying a stereoscopic augmented view of a patient from a static or dynamic viewpoint of the surgeon, which employs real-time three-dimensional surface reconstruction for preoperative and intraoperative image registration. Stereoscopic cameras provide real-time images of the scene including the patient. A stereoscopic video display is used by the surgeon, who sees a graphical representation of the preoperative or intraoperative images blended with the video images in a stereoscopic manner through a see-through display.

This invention provides a point cloud pose estimation method and system based on a stereo camera and a genetic algorithm. The method inputs a single RGB image into a pre-trained depth estimation neural network to generate a colored point cloud, which is then downsampled using a voxel grid. The sampled point cloud and stereo camera parameters are loaded, and the genetic algorithm is initialized with individual encodings containing position, rotation, and scaling parameters to achieve simultaneous estimation of pose and size. The genetic algorithm is executed, calculating color matching degree through point cloud projection, occlusion point detection, and expanded point generation to determine fitness. Through elite retention and dynamic adjustment of the search range, iterative processes continue until a termination condition is met, outputting the optimal pose parameters. This invention solves the problem of size uncertainty caused by unknown shooting distance, and can simultaneously estimate target position, pose, and size, improving the practicality and accuracy of pose estimation.