130 results about "Monocular" patented technology

The invention belongs to crossing field of computer vision and intelligent robots and discloses a variational mechanism-based large-area indoor scene reconstruction method. The method comprises the following steps: step 1, acquiring calibration parameters of a camera, and building an aberration correcting model; step 2, building a camera position and gesture depiction and camera projection model; step 3, utilizing an SFM-based monocular SFM (Space Frequency Modulation) algorithm to realize camera position and gesture estimation; step 4, building a variational mechanism-based depth map estimation model, and performing solving on the model; and step 5, building a key frame selection mechanism to realize three-dimensional scene renewal. According to the invention, an RGB (Red Green Blue) camera is adopted to acquire environmental data, and a variational mechanism-based depth map generation method is proposed through utilizing a high-precision monocular positioning algorithm, so that quick large-area indoor three-dimensional scene reconstruction is realized, and problems of three-dimensional reconstruction algorithm cost and real-time performance are effectively solved.

The invention relates to a monocular multi-perspective machine vision-based online automatic sorting device for steel balls. The online automatic sorting device comprises an assembly line, a monocular multi-perspective machine vision device and a microprocessor, wherein the assembly line is used for automatically detecting and sorting the steel balls, the monocular multi-perspective machine vision device is used for shooting images of the detected steel balls, the microprocessor is used for performing image processing, detection, identification and classification on the images of the detected steel balls and coordinately controlling each actuating mechanism on the assembly line to coordinately move, and the assembly line comprises a feeding actuating mechanism, a transmission mechanism and a sorting actuating mechanism. The invention provides the monocular multi-perspective machine vision-based online automatic sorting device for the steel balls based, which has the advantages of simple mechanism, low manufacturing cost, high sorting efficiency and convenience in operation and maintenance.

The invention discloses a monocular and IMU fused stable motion tracking method and device based on a mobile terminal, belonging to the technical field of AR / VR motion tracking. The method comprises the following steps of: judging whether the number of tracking feature points of a current frame of an image is greater than a pre-set threshold value or not, if so, performing feature point tracking by adopting an optical flow method so as to obtain the current pose of a camera, if not, obtaining feature points by adopting a FAST feature detection operator, and performing feature matching of the image by adopting a BRIEF algorithm calculation descriptor so as to obtain the current pose of the camera; performing Kalman filtering of the current pose of the camera so as to obtain a visual pose; obtaining acceleration and angular speed values generated by an IMU in a three-dimensional space, and performing integral operation of the acceleration and angular speed values so as to obtain the pose of the IMU; and performing Kalman fusion of the visual pose and the pose of the IMU, and performing motion tracking. Compared with the prior art, more stable and rapid motion tracking can be obtained on mobile terminal equipment.

Detection of three dimensional obstacles using a system mountable in a host vehicle including a camera connectible to a processor. Multiple image frames are captured in the field of view of the camera. In the image frames, an imaged feature is detected of an object in the environment of the vehicle. The image frames are portioned locally around the imaged feature to produce imaged portions of the image frames including the imaged feature. The image frames are processed to compute a depth map locally around the detected imaged feature in the image portions. Responsive to the depth map, it is determined if the object is an obstacle to the motion of the vehicle.

A three-dimensional imaging system uses a single primary optical lens along with various configurations of apertures, refocusing facilities, and the like to obtain three offset optical channels each of which can be separately captured with an optical sensor.

The invention relates to a waveguide type integrated imaging three-dimensional display system based on a diffraction optical element. A micro displayer (1) is arranged at the position of the focal length of a holographic microlens array of the surface of the input end of a waveguide (3), a two-dimensional element image passes through the holographic microlens array and is imaged to obtain an image including depth and parallax information, the obtained image is coupled into the transparent waveguide (3) through a holographic lens on the surface of the input end of the waveguide (3), is spread through total reflection and is output in a coupling mode through a holographic lens on the surface of the output end of the waveguide (3), and the image is observed by the human eyes. According to the system, the diffraction optical element is introduced in to overcome the defects that in the technical background, the size is large, the weight is large, and the structure is complex, and integrated monocular three-dimensional displaying is achieved. Meanwhile, the optical element, the waveguide (3), is introduced in, and off-axis large-system pupil sight-thorough monocular three-dimensional displaying with the high transmission rate is achieved. The system can be widely applied to integrated imaging three-dimensional display systems.

A modular night vision assembly comprising a first night vision monocular, a power assembly and a connection assembly. The monocular includes a first monocular housing enclosing a first optic assembly and a first associated electrical assembly. A first contact interface is defined along the exterior of the first monocular housing and is in electrical communication with the first electrical assembly. The first contact interface and the first monocular housing are sealed such that the first monocular assembly is independently sealed. The power assembly includes a power housing enclosing an electrical power source and a second contact interface in communication with the electrical power source. The connection assembly is configured to removably connect the power assembly to the first monocular assembly with the first and second contact interfaces electrically interconnected and sealingly enclosed between the power housing and the first monocular housing.

A support for adjusting the line of sight of a night vision monocular. The support has a shelf that is supported relative to a user's eyes and a flange that is coupled to the shelf and rotatable relative to the shelf. The support also has a shaft supporting the monocular. The shaft is coupled to the flange for tilting the monocular relative to the shelf concurrently with a rotation of the flange. The support also has a tilt control means coupled to the flange for applying an axial force to the flange to control the rotation of the flange and the tilting of the monocular.

The invention relates to a monocular and binocular pose deviation measuring method used for cabin automatic docking, comprising: respectively setting mark points on a cabin head and a cabin body; employing a binocular measuring device to respectively detect three-dimensional coordinates of the mark points of the cabin head and the cabin body in a world coordinate system; respectively obtaining images of the mark points of the cabin head and the cabin body; and calculating pose deviation. The method has the advantages of fast measuring speed, high precision and great practicality.

A holding device holds a camera rearward of an ocular of a glass such as a monocular or binocular to record an image utilizing the camera. The image is made available by the glass. This holding arrangement is usable with many cameras and binoculars or monoculars. A rapid change between the camera positioned forward of the ocular and a cleared ocular is made possible for the direct viewing by the user through the glass (binocular or monocular).

The invention provides a monocular vio (Visual-Inertial Odometry) based mobile terminal AR method, which comprises the steps of performing image acquisition and inertial data acquisition respectivelyby using a camera and an IMU; extracting feature points of each image acquired by the camera, and setting the extracted feature points to be key frames; calculating corresponding IMU position and rotation information of two images in a pre-integration manner; acquiring a tracked feature point in the key frames, and calculating the pose of each key frame according to the feature point; calculatingan external parameter between the camera and the IMU according to a condition that displacement and rotation information acquired by the IMU is equal to displacement and rotation information measuredby the camera between the two frame; initializing the speed, the acceleration and a scale factor of the IMU; acquiring the pose of the camera by using tight coupling nonlinear optimization, and then superimposing a virtual object to achieve an AR effect. The mobile terminal AR method adopts the IMU to make up defects of VSLAM (Virtual Simultaneous Localization and Mapping), and is not affected byenvironmental feature points within a short time; and deviation is prevented by using alignment of the VSLAM and the IMU when the time is long.

The invention discloses a monocular and binocular multiplexed invading object monitoring method and a system which relate to the technical field of computer visions. The method comprises the following steps: shooting a background image; acquiring a monitoring video image in a monitored zone by a first camera; determining whether any invading object enters the monitored zone according to the background image and the monitoring video image acquired by the first camera; controlling to initiate a second camera if such invading object is found; otherwise, repeating the above steps and this step; calculating the spatial three-dimensional coordinate of the invading object in space as well as the three-dimensional coordinate of a protected object in the monitored zone based on the video images acquired by the first camera and the second camera and determining the space distance from the invading object to the protected object and the moving speed of the invading object; and based on the space distance from the invading object to the protected object as well as the moving speed of the invading object, determining the threat grade.

The monocular stereoscopic imaging device according to one aspect of the presently disclosed subject matter includes: an imaging optical system including a zoom lens and a diaphragm; a pupil dividing unit configured to divide a light flux having passed through a imaging optical system into multiple light fluxes; an imaging unit configured to receive the multiple light fluxes, so as to continuously acquire a left-eye image and a right-eye image; and a controlling unit configured to control a zoom lens driving unit to move the zoom lens in accordance with an instruction of changing the focus distance, and configured to control the diaphragm driving unit to maintain at a substantially constant level a stereoscopic effect of the left-eye image and the right-eye image three-dimensionally displayed on a display unit before and after the zoom lens is moved.

This invention comprises an adaptor device for connecting an electronic device having a camera to a range of optical devices, including but not limited to binoculars, monoculars, riflescopes, spotting scopes, telescopes, and microscopes. This adaptor device has a plurality of protrusion that provide a self-centering and fitted connection between the electronic and optical device, so that the optical axes are aligned so that the user may take images or video on their electronic device through the optical device. The structure of the adaptor device allows the adaptor to fit a range of differently sized optical device, denoted by the diameter of the eyepiece end of the optical device.

The invention is a forehead cold light source shooting microscope or magnifier. It belongs to optical instrument field. The invention includes forehead armet, armet perimeter adjusting mechanism, armet embedding degree adjusting mechanism, microscope vertical shift adjusting mechanism, microscope angle adjusting mechanism, forehead illuminating mechanism, and monocular / binocular microscope or amplifier with adjustable pupilla distance. The forehead armet and the armet embedding degree adjusting mechanism are integral, the armet perimeter adjusting mechanism and the forehead armet are connected, the microscope vertical shift adjusting mechanism base is riveted with the forehead armet, the microscope vertical shift adjusting mechanism is connected with the microscope angle adjusting mechanism, the forehead illuminating system light source is embedded in the head of the monocular / binocular microscope or amplifier. The light source uses new source brightening diode cold light source, electricity saving, and the effect is better; the amplifier position can be adjusted in left, right, up and down.

The embodiment of the invention provides a monocular structured light depth imaging method based on a convolutional neural network. The method comprises the following steps: S1, carrying out visual calibration on a monocular structured light imaging hardware system; s2, generating a synthetic training data set; s3, carrying out data augmentation and preprocessing; s4, constructing a convolutionalneural network; s5, determining a loss function; s6, setting an optimizer; s7, training a convolutional neural network; and S8, testing the convolutional neural network. The method provided by the embodiment of the invention is used for training a synthetic training data set of a convolutional neural network, specific optimization and improvement are carried out on face recognition, the imaging effect and the recognition accuracy when monocular structure light depth imaging is adopted for face recognition are improved, the network calculation amount is reduced, and the real-time performance under the imaging quality requirements for high precision and high resolution is improved.

A binocular system includes a first monocular, a second monocular, a first arm coupled to a base plate via a first hinge and coupled to the first monocular, and a second arm coupled to the base plate via a second hinge and coupled to the second monocular. Each of the monoculars rotates about a corresponding one of the hinges along an axis of rotation that is not parallel to an axis of collimation of each of the monoculars. The monoculars are collimated when rotated into a deployed position. The binocular system may also include a mounting bracket coupled to the base plate, a tilt base, interposed between the mounting bracket and the base plate and a tilt lever, having a cam that is operatively engaged with the tilt base, where actuation of the lever causes the base plate to tilt with respect to the mounting bracket.

A monocular eyeglass assembly (10) is suitable for use in applying substances to one eye or areas surrounding one eye while enjoying lens-corrected vision in the other eye. The assembly (10) includes a single temple (16) coupled to a frame (14) holding a lens (12) and a nose bridge (20) coupled to the frame. The assembly (10) enables the lens (12) to be positioned in alignment with one of the weare's eyes while allowing the wearer's other eye and its surrounding area to remain completely unobstructed by the assembly (10).

The invention discloses a monocular RGB-D camera real-time face reconstruction method and device, wherein, that method comprise: detecting the position of the face feature point on the input face RGBimage through an advanced face feature point detection algorithm; Obtaining three-dimensional coordinates of each feature point of the current frame according to the position of the feature points ofthe face; Acquiring the current three-dimensional coordinates of each facial feature point on the key frame; The global rigid motion from the key frame to each frame is obtained according to the three-dimensional coordinates and the current three-dimensional coordinates, so as to obtain the rigid motion result; The result of rigid motion is used as the initialization of ICP to fine-tune the rigidmotion of human face. The rigid motion results are applied to the key frame model to update the TSDF representation of the model. This method effectively removes the depth of non-face region, eliminates the influence of rigid motion, and improves the accuracy of rigid motion estimation by using facial feature points.

A binocular system includes a first monocular, a second monocular, a mounting bracket, a base plate, coupled to the mounting bracket, a first arm coupled to the base plate via a first hinge and coupled to the first monocular via a first guide rail, and a second arm coupled to the base plate via a second hinge and coupled to the second monocular via a second guide rail. The monoculars are independently moveable using the guide rails and the hinges. Collimation of the monoculars is maintained independently of movement of the monoculars side to side and fore and aft on the guiderails.

The invention provides a monocular narrowband multispectral stereoscopic vision system and an application method thereof. The system includes an optical imaging lens with axial chromatic aberration, anarrowband multispectral image sensor with a channel number N (greater than 4), and an image processing unit for processing and analyzing narrowband multispectral images. The system provided by the invention can obtain a plurality of narrowband spectrum images with different focusing resolution values through one exposing operation, wherein the natural calibration of the spatial position of an image plane XY is achieved. The system employs a matched defocusing blurring degree algorithm for obtaining the depth Z information of any spatial position XY of the image, irons out the defects that binocular stereoscopic vision is large in calculation burden and a laser 3D vision system is high in price, and has a high application value for the moving of an intelligent robot, the navigation of anunmanned automobile and the obstacle avoidance.

Detection of three dimensional obstacles using a system mountable in a host vehicle including a camera connectible to a processor. Multiple image frames are captured in the field of view of the camera. In the image frames, an imaged feature is detected of an object in the environment of the vehicle. The image frames are portioned locally around the imaged feature to produce imaged portions of the image frames including the imaged feature. The image frames are processed to compute a depth map locally around the detected imaged feature in the image portions. Responsive to the depth map, it is determined if the object is an obstacle to the motion of the vehicle.

The invention discloses a compact monocular multi-channel configurable multispectral imaging system, which comprises an optical lens interface for fixing the optical imaging lens; a composite beam splitter prism composed of three or more prisms glued together; a optical filter interface provided with three or more interfaces, wherein the interfaces are respectively used for fixing optical filter modules with different spectral bands so as to generate spectral information of different spectral bands; three or more groups of low spatial high spectral resolution sensors and high spatial low spectral resolution sensors used for performing photoelectric conversion on the spectral information to generate an electric signal; and an image acquisition processing system comprising an image processing module, an optical filter identification module, a memory, an information superposition module and an analysis module.

The invention discloses a driving examination system based on CCD monocular distance measurement and belongs to the image processing field. The system comprises an image acquisition module, an image processing module, an illegal determination module and an examination evaluation module. Through acquiring surrounding image information of an examination vehicle, pretreatment is performed on the image information, an examination marker in a pretreatment result is extracted and a distance between the current examination vehicle and the examination marker is determined. According to a size relation between the distance and a preset threshold, information of whether an illegal condition is generated is generated and a examination result is performed according to the information. Compared to the prior art, by using the system of the invention, whether the examination passes can be accurately determined and a defect that the examination result can not be determined because examination vehicle information can not be acquired according to GPS in the prior art is overcome.

A binocular system includes a first monocular, a second monocular, a first arm coupled to a base plate via a first hinge and coupled to the first monocular, and a second arm coupled to the base plate via a second hinge and coupled to the second monocular. Each of the monoculars rotates about a corresponding one of the hinges along an axis of rotation that is not parallel to an axis of collimation of each of the monoculars. The monoculars are collimated when rotated into a deployed position. The binocular system may also include a mounting bracket coupled to the base plate, a tilt base, interposed between the mounting bracket and the base plate and a tilt lever, having a cam that is operatively engaged with the tilt base, where actuation of the lever causes the base plate to tilt with respect to the mounting bracket.

The invention provides a robot monocular stereoscopic vision calibrating system and method. The system comprises an information acquiring module, a camera modeling module, a robot joint axis calibrating module, a calibrating feedback and fitting module and a robot model building module, wherein the calibration feedback and fitting module comprises an actual deviation judging unit, an axis re-fitting unit and an Euler angle calculating unit; the actual deviation judging unit is used for calculating the deviation between data acquired by a high-definition camera and data acquired by an infraredremote sensor; the axis re-fitting unit is used for correcting the data acquired by the high-definition camera; and the Euler angle calculating unit is used for calculating projection data of an actual value projection measured by the infrared remote sensor on three coordinate axes of a three-dimensional world coordinate system, and calculation of a deviation rate is performed. Thus, it is achieved that dependence on definition of the high-definition camera is lowered, cost of the equipment is lowered, the precision of calibrating is improved, and large-area popularizing of a robot is facilitated.

An ophthalmic monocular handheld digital microscope with a slit lamp mainly resolves problems that a slit light spot size adjusting mechanism of an existing monocular handheld microscope with a slit lamp is complex, and processing and assembly are inconvenient. The ophthalmic monocular handheld digital microscope is characterized in that at least one pin (6) is fixed on the outer wall of a projecting mirror (8), a strip-shaped guiding groove (17) is axially arranged on a side wall of a fixing sleeve (12), a first adjusting knob (18) is disposed outside the fixing sleeve (12), a spiral groove (19) is arranged on the inner wall of the first adjusting knob (18), each pin (16) penetrates through the guiding groove (17), and an end of each pin (16) is placed in the spiral groove (19) of the first adjusting knob (18). The ophthalmic monocular handheld digital microscope has the advantages of light weight, simple structure and convenience in adjustment of sizes of slit light spots, further can record digital images, can adjust the directions of the slit light spots and switch different filter discs, and can be flexibly and conveniently used by doctors.