150 results about "Active vision" patented technology

The invention discloses an active vision human face tracking method and tracking system of a robot; the tracking method comprises the steps that: (1) the mobile robot acquires an environment information image and detects a human face target through an active camera; and (2) after the human face target is detected, the robot tracks the human face target, and maintains the human face target in the center of the image through the active camera and the movement of the robot. The tracking system comprises the active camera, an image tracking module, a movement tracking module, a hierarchy buffer module and a state feedback module. The invention realizes the automatic human face detection and tracking by the robot, overcomes the limitation of a smaller image vision angle and establishes a perception-movement ring of the mobile robot based on active vision by combining the image tracking with the movement tracking, so that the movement scope for human face tracking is expanded to 360 degrees, the all-sided expansion of the tracking scope is ensured. A two-layer buffer region ensures the tracking continuity, so that the human face target is always maintained in the center of the image.

An imaging method includes obtaining an image with a first field of view and first effective resolution and the analyzing the image with a visual attention algorithm to one identify one or more areas of interest in the first field of view. A subsequent image is then obtained for each area of interest with a second field of view and a second effective resolution, the second field of view being smaller than the first field of view and the second effective resolution being greater than the first effective resolution.

A thermal control system (11) for a light source (46) of a vision system (10) includes a cooling assembly (61) that has a cooling device (62) and is thermally coupled to the light source (46). A thermal sensor (60) is thermally coupled to the light source (46) and generates a light source temperature signal. A control circuit (50) is coupled to the cooling assembly (61) and to the thermal sensor (60) and operates the cooling device (62) when the light source temperature signal is above a minimum temperature limit.

A mobile terminal iris recognition device having a human-computer interaction mechanism, the device includes a human-computer interaction module, an image acquisition module, an iris image analysis and processing module, a feedback control module and a power supply module. Also provided is an iris recognition method utilizing the device. Compared with the related art, the method has great improvement in such aspects as miniaturization, mobility and usability, is provided with a mobile terminal iris recognition function with an active visual, tactile and auditory interaction mechanism, and also has the advantages of high accuracy of iris recognition, low power consumption, reasonable structural layout, strong interaction functions and the like.

A method for stabilizing the reconstruction of an imaged volume is presented. The method includes the steps of performing an analysis of the reliability of reconstruction of a radioactive-emission density distribution of the volume from radiation detected over a specified set of views, and defining modifications to the reconstruction process and / or data collection process to improve the reliability of reconstruction, in accordance with the analysis.

The invention relates to a ward visit service robot system and a target searching method thereof. In the method, a way for searching a target by combining the Bayesian theory with multi-mode target expression and priori knowledge is put forward, and a mechanism for actively searching a target in the complex environment of a ward by a method for combining active vision, characteristic extraction and characteristic verification is provided. By using body vision of a robot and RFID (Radio Frequency Identification Device) information, active robot ward visit is realized. A robot positioning system is obtained by a StarGazer system through Kalman filtering; a robot control system expresses an expression target through multiple modes of a target by using the Bayesian theory and controls the robot in combination with the priori knowledge; a target position is obtained while the pose of the robot is controlled, so that the target is positioned by a method for using active vision and combination characteristic; and a camera is controlled by a partition logic method, and a shot picture is sent to a server side for displaying and storing.

A method for stabilizing the reconstruction of an imaged volume is presented. The method includes the steps of performing an analysis of the reliability of reconstruction of a radioactive-emission density distribution of the volume from radiation detected over a specified set of views, and defining modifications to the reconstruction process and / or data collection process to improve the reliability of reconstruction, in accordance with the analysis.

Provided is a miniaturization iris identification module adopting active vision feedback, which independently completes collection of eye iris images and process function, and can be used as a miniaturization module with independent iris identification function embedded into and connected to other devices, e.g. a safe box (a safe case), a lock, a finance safety-deposit box, a fire-arm storage box, a bag storage cabinet, a ATM, a POS, a work attendance machine, a gate inhibition controller, a channel controller, a lift controller, a radio set, a copier, a electrograph, a telephone, a printer, a mouse, a computer, a household electrical appliance, a cable TV remoter, a toy, a digital camera, a moving device, a car, a motor, a motor-assisted bicycle and the like, thereby upgrading to a product with iris identification and authentication function.

A method for stabilizing the reconstruction of an imaged volume is presented. The method includes the steps of performing an analysis of the reliability of reconstruction of a radioactive-emission density distribution of the volume from radiation detected over a specified set of views, and defining modifications to the reconstruction process and / or data collection process to improve the reliability of reconstruction, in accordance with the analysis.

The process of obtaining 3D model of object quickly based on active vision includes calibrating the light planar equation of the grating planes of the projector under reference coordinate system and the projecting transformation matrix from the reference coordinate system to the camera; taking one frame of object picture with grating and one frame with grains only; inputting the images into computer; extracting the edges of grating from the image automatically or via man-machine interaction and clustering; finding out the 3D coordinates of all the grating edge points of object in the reference coordinate system via reverse projection to obtain the 3D model of the visible object surfaces; performing triangular decomposition of 3D points on object surface and mapping the grain information onto the 3D model; rotating the object in certain angle before repeating the said steps to obtain one other 3D model of other side; and data fusion to obtain complete 3D model of the object.

A visual display of a panoramic region is provided in which a static context display is provided for an active display displayed in a mobile display window. Active images are sequentially generated and displayed from temporally sequential frames of visual data that each represent an image defining a region within a larger panoramic region such that at least two of the images define regions that do not coincide. Each displayed image is positioned on a display screen with respect to the position of other displayed images on the display screen in accordance with the spatial relationship in the panoramic region of the content of the displayed image to the content of the other displayed images. At some time during the visual display, one or more context images (a context display) is displayed while an active image is displayed. Each context image is at least part of an image represented by a frame of the set of temporally sequential frames of visual data. Context images can be automatically displayed in a predetermined manner. For example, after each image is displayed as the active image, the image can be retained, in whole or in part, on the display screen as a context image, i.e., the active image leaves a trail of context images. Images can also be designated as context images by a user. In particular, as active images are displayed, the user can designate particular active images as context images.

An active vision based method and system for video capturing is provided herein. The method may include the following steps: illuminating a stationary outdoor scene containing objects, with a structured light exhibiting a specified pattern, at a first angle; capturing reflections from the objects in the stationary scene, in a second angle, the reflections exhibiting distortions of the specified pattern; analyzing the reflected distortions of the specified pattern, to yield a three dimensional model of the stationary scene containing the objects, wherein the specified pattern may include temporal and spatial modulation.

The invention relates to a binocular initiative vision monitoring device for precision machining. The feature is that it fixes three supports on base, and sliding rails are installed in the three supports and plumbing to bottom plane, sliding blocks are installed in the sliding rail, the round guiding rail connecting to the three sliding blocks, two dollies installed on the round guiding rail, each dollies having a cradle head that is installed a video camera. The base line and location between the two video cameras would be adjusted by sliding on the guiding rail. The vision system could flexibly adjust the observing anger. It has the advantages of parallel structure, simple moving mode and simple vision computing mode.

A multi-viewpoints gesture estimate and self-demarcate method for three-dimensional initiative vision sensor belongs to three-dimensional figure imaging and sculpting technology. The said sensor is made up with numeric projector and camera. Collect object vein picture; project a set of orthogonal list map to object early or late and collect corresponding coding list picture; count the two-dimensional coordinate of characteristic point to vein picture and phase value to coding list picture. Use transforming arithmetic from phase position to coordinate to seek the corresponding relationship of diagnostic point of object between the project plane to numeric projector and the imaging plane to camera. Change viewpoint and repeat the said steps by using polar ray geometry restriction element to base optimization equation to automatically estimate multi-viewpoint location gesture and self-demarcate three-dimensional initiative vision sensor. It is veracious, automatic and special to locale multi-viewpoints gesture estimate and self-demarcate of vision sensor.

The invention relates to a gear measuring apparatus and measuring method based on active vision, and belongs to the technical field of high precision detection. The measuring apparatus comprises a base; a three-dimensional moving platform is arranged on the base; the three-dimensional moving platform comprises X, Y and Z axis guide rails which are perpendicular to each other; and a raster displacement sensor is arranged on the guide rail in each axis; the Z-axis guide rail is slidably provided with a carriage; an industrial camera and a lens which are connected are arranged on the carriage; an output end of the industrial camera is connected to a host computer; a background light source is fixed on the base; each displacement sensor is connected with a controller for calculating the positioning information of the three-dimensional moving platform; the controller is connected with the host computer; and the host computer realizes the motion control and positioning information acquisition of the three-dimensional platform through sending commands to the controller. The gear measuring apparatus and measuring method of the invention can effectively realize high-precision non-contact measurement of gears in the effective dimension scope of 50mm-500mm to reach an effect of reducing cost.

The invention discloses an active visual technology-based monitoring system used for crane remote operation. The monitoring system comprises a main control computer and camera shooting equipment. The main control computer is provided with an image processing software, and is cooperatively connected to a server through a data I / O interface; the camera shooting equipment is used for taking images of a container loading and unloading scene, and is controlled by the main control computer to process obtained images of key procedures of each operation step, and to transfer the images of the key procedures to a display device for displaying, wherein the key procedures need attention; and then operators can control the crane to complete loading and unloading operations of containers remotely in an operation room according to the image displayed by the display device. Advantages of the monitoring system are that: remote monitoring and operating of each operation step can be realized by using the active visual technology, by taking images of the container loading and unloading scene with the camera shooting equipment, by processing obtained images of key procedures of each operation step, and by displaying the images with the display device. Investment cost of the monitoring system is low, maintenance is simple, and the monitoring system is capable of realizing all-weather operations.

The invention discloses a method for measuring simulated seabed terrain based on an active stereo vision technology and measuring equipment. By the stereo vision technology, a binocular camera is arranged on the outside of an experimental trough, and seabed terrain changes are measured contactlessly through glass sidewalls of the experimental trough. Partial flow field will not be disturbed, and synchronous acquisition of the whole simulated seabed terrain can be realized. According to the invention, the active vision technology is used in underwater measurement. That is to say, by the utilization of auxiliary structured light irradiating underwater terrain through the glass sidewalls of the experimental trough, dense structured textures or dot arrays are formed on the terrain such that the camera can distinguish more easily. Meanwhile, quantity of terrain characteristic points is also increased. With the combination of the high-resolution camera, high-precision terrain data can be obtained. By the adoption of the method provided by the invention, noncontact, synchronous and high-precision measurement of the simulated seabed terrain can be realized, and corresponding problems existing in the prior art are solved.

The invention provides an active vision non-contact servo mechanism parameter measuring device, consisting of a measuring screen, a servo mechanism mounting platform, an image acquiring and processing system, and a red light laser light source, wherein a servo mechanism to be detected is provided with the red light laser light source which is positioned on the servo mechanism mounting platform and is arranged in front of the measuring screen, a digital camera is arranged behind the measuring screen to image on the screen. Firstly, the device shoots a picture of a gridiron pattern on the measuring screen by the camera which is demarcated; secondly, the servo mechanism controls a main frame to give a command so as to control the rotation of the servo mechanism to be detected, a computer extracts laser point coordinates of the image, the rotational angle at each moment of the servo mechanism to be detected is calculated and recorded in real time, the motion parameters of the servo mechanism to be detected such as the angular velocity, the pointing accuracy, and the overshoot are calculated by the rotational angle; the measuring method is simple, convenient and flexible, and the device and the measuring method realize the measurement in real time and with high accuracy of the movement parameters of a biaxial servo mechanism through the non-contact way.

The invention discloses an underwater wet welding tracking system based on active vision. A front end cover of a sealed box body is matched with a pressing cover, a threaded hole is formed in a rear end cover and is matched with a base, and a threaded hole is formed in one side outside the sealed box body; an arc blocking plate is installed and fixed between a welding torque and a sensor, an external sealing connector of a cable is connected with the sealed box body, a supporting structure is designed to be a T-type plate, a transverse plate is fastened to the rear end cover of the sealed box body, a CCD and a steering gear are installed and fixed to the two faces of a vertical plate respectively, and a laser is installed on the steering gear. According to the system, the sensor is sealed well, and the structure is portable. The interior structure is made to be compact due to the design of the T-type plate, and all the components are convenient to disassemble and assemble. The external sealing connector of the cable makes weak sealing links sealed well. The image acquisition effect is remarkably enhanced due to the design of the arc blocking plate. The laser can be regulated automatically due to the fact that the steering gear is installed and can be regulated conveniently and accurately.

The invention discloses an interactive projection method and system based on active vision. The method includes the steps that frames needing interaction are projected onto any plane by a projector, information of operation on the projected interaction frames carried out by a user is collected through a shooting device, the shot information is transmitted to a processing unit to be analyzed and processed, and thus corresponding operation of the user is acquired so as to achieve human-computer interaction. An offline training mode is adopted for the processing unit, and thus the detection efficiency is promoted. When data are trained, a new training mechanism is provided, and thus a large amount of manual operation is reduced. In the detection process, a model which is updated in real time is adopted, namely, a current skin color model is only relevant to the last several frames of skin colors, and thus influences of illumination on the skin colors can be effectively eliminated, the algorithm efficiency is effectively improved, and the real time requirement can be totally met.

The invention discloses a real-time monitoring device for a welding robot welding process. The device comprises a welding gun, an image collection mechanism, a laser transmitting mechanism and a temperature collection mechanism. The image collection mechanism and the laser transmitting mechanism are fixedly arranged on the welding gun. The image collection mechanism comprises a U-shaped support and a charge coupled device (CCD) camera, an aluminum sleeve is arranged on the outside of a machine body of the CCD camera, and a copper foil is coated on the inner lateral wall of the aluminum sleeve. A copper sleeve is arranged on the outside of a lens, and a plastic filler is arranged between the lens and the copper sleeve. The laser transmitting mechanism comprises an aluminum column and an end cover. A laser light-emitting diode is arranged in the aluminum column. The temperature collection mechanism comprises a plurality of thermocouples arranged evenly at intervals and a data collection module. The data collection module and the CCD camera are connected onto an industrial personal computer through universal serial bus (USB) transmission lines respectively. By means of a laser beam transmitted by the laser light-emitting diode and the CCD camera, active vision sensing can be achieved, and fusion processing and monitoring of collection data of temperature and subjective vision are achieved through the industrial personal computer.

The invention provides an image depth calculating method. The image depth calculating method is based on an active visual pattern of structure light and adopts a block matching motion estimation method so as to improve matching accuracy. High-resolution depth information of a target object is acquired through the laser trigonometry or a table lookup method, and the image depth calculating method avoids a complicated depth calculating formula, achieves rapid and accurate acquisition of the depth information, simplifies a hardware structure, is easy to achieve, and facilitates large-scale popularization.

The invention relates to an underwater active vision tracking method applied to a bionic robot fish, which comprises embedded visual system based active target identification and target positioning. The method comprises the steps of S1, acquiring a digital underwater image by a digital camera; S2, carrying out target identification based on one of color features, shape features and contour features, and acquiring an underwater target region of one of the color features, the shape features and the contour features; and S3, carrying out feature description on the target on the underwater target region of one of the color features, the shape features and the contour features by adopting a weighted color histogram, and realizing positioning for the underwater target according to the target feature description. The underwater active vision tracking method provided by the invention does not need to carry out preprocessing on the image, is small in calculation amount, good in real-time performance, accurate in positioning and applicable to scenes in which system resources are limited and the environment is relatively simple; and the underwater active vision tracking method is also applicable to active vision tracking under different environments and particularly to embedded visual applications on the bionic robot fish.

A system and method for active visual measurement and servo control using laterally sampled white light interferometry (L-SWLI) for real-time visual tracking of six-degree-of-freedom (6 DOF) rigid body motion with near-nanometer precision. The visual tracking system is integrated with a 6 DOF motion stage to realize an ultra precision six-axis visual servo control system. Use of L-SWLI obtains the complete pose of the target object from a single image frame to enable real-time tracking. Six-degree-of-freedom motions are obtained by measuring the fringe pattern on multiple surfaces of the object or from a single surface with additional information gained from conventional image processing techniques.

The invention relates to an active visual attention monitoring video significant event intelligent detection and early warning method. The method includes the steps of establishing a quick extracting method of visual attention primary information from bottom to top, and constructing an active detection module of a dynamic target; then actively tracking a significant target by particle swarm optimization, and meanwhile, establishing an active early warning model for a significant event in a monitoring video and thus realizing a monitoring video significant event intelligent detection and early warning system based on a visual attention model. The experiment shows that the method of the invention is high in operating efficiency and has good robustness in terms of altitude and shape change, partial shielding, quick movement and illumination change.

The invention relates to a trinocular vision device used for the remote operation of a floatation mechanical arm, which belongs to the technical field of space robots. In the device, a high-pressure air cylinder is arranged in a floatation platform, and an air foot is arranged below the floatation platform, is connected with the high-pressure air cylinder by an air pipe and supports the floatation platform by a supporting column. A six-freedom-degree mechanical arm is fixed on the floatation platform. An installation bracket is arranged at the end part of the six-freedom-degree mechanical arm. Three cameras are arranged at the upper part of the installation bracket. A paw is arranged at the lower part of the installation bracket by a paw bracket. The device adds an active vision function, enables the cameras on the platform to track a target object in a self-adapting way and enhances the efficiency of the remote operation; a trinocular vision scheme is adopted, the target object is observed in a multi-azimuth way, and the invention is beneficial for a remote operator to learn about a far-end environment in the operational process, avoids the occurrence of accidents, such as impact and the like, and provides guarantee to the successful completion of the task of the remote operation.

The invention provides a scale factor determination method in monocular vision reconstruction based on dot structured light ranging. The scale factor determination method comprises the steps of positioning a center of a light spot centroid, fitting space straight lines, carrying out RANSAC rejection, calculating three-dimensional space point coordinates of the light spot and calculating a scale factor. Aiming at the fact that most of the traditional monocular vision three-dimensional reconstruction methods based on image sequences can only achieve three-dimensional reconstruction at a projective scale or affine scale, the invention provides the Euclidean three-dimensional reconstruction method utilizing dot structured light to achieve monocular vision in an assisted mode, so that the scale of a three-dimensional scene reconstructed by utilizing the image sequences is consistent with that of a real world scene. The scale factor determination method has the technical characteristics of: (1) achieving Euclidean three-dimensional reconstruction by introducing structured light active vision into monocular reconstruction, (2) positioning the light spot by using a centroid method, (3) adding an RANSAC rejecting mechanism into laser ray equation fitting, (4) positioning a spatial point of the light spot in back-projection optimization, (5) and being free of restrictions in Euclidean reconstruction by adopting various kinds of methods in monocular reconstruction.

The invention discloses a welding appearance quality detection robot and a detection method thereof. The welding appearance quality detection robot comprises a welding detection robot unit, a controlcabinet and a clamping tool. The welding detection robot unit carries a laser active vision assembly and an ultrasonic signal detection assembly to autonomously identify and detect the quality of inner and outer surfaces of a workpiece to be detected; the control cabinet is used for carrying out image and ultrasonic signal processing on the information detected by the welding detection robot unit,generating a welding seam quality detection report and controlling the welding detection robot to move; and the clamping tool is used for clamping the workpiece to be detected. Welding workpiece detection flexibility, accuracy and detection efficiency are improved; and the missing detection rate is greatly improved.

The invention discloses a structural light vision sensor and a rapid calibration method. Light spots in light bars are extracted at a time on two planes, and by use of a singular value decomposition (SVD) method, fitting is performed on the obtained light spots, so light plane parameters of structural light are obtained. According to the invention, the step of additionally introducing a precisionmeasurement instrument or carrying out fitting in multiple target positions to solve intersection points is removed; multiple rapidly acquired light points are used as fitting points to carry out fitting, so the whole process is simple and easy. By rapidly obtaining light plane parameters of structural light, the relation position of an application camera and a laser in the following vision measurement process is unchanged, i.e., the surface of unknown morphological feature is measured by use of a laser triangulation method; by use of the active vision method, contactless lossless measurementis achieved in an industrial place; and requirements on onsite online measurement are met.