522 results about "Vision processing" patented technology

A plug-in hybrid electric vehicle (PHEV) is an automobile which can use either electricity or gasoline. With high gasoline prices, electricity is becoming a promising alternative to power next generation automobiles. One advantage of the PHEV and the BEV (battery electric vehicle) is that charging can be done at home. However, the small battery capacity of PHEV's may require recharging the batteries almost daily. It would be convenient for an owner of a car with batteries to not have to plug in the battery each and every day that charging is required. Our invention is a system that plugs the power automatically into the vehicle with minimal human intervention using an automated docking system. The system is composed of a robotic manipulator with a camera and a processing unit. The system uses the camera and vision processing to identify the vehicle's position, and consequently, the location of the vehicle's charging receptacle. The robotic manipulator then directs the charging cord's plug into the receptacle of the vehicle. Once charging is complete, the robotic manipulator removes the plug from the vehicle.

In some embodiments, a display system comprising a head-mountable, augmented reality display is configured to perform a neurological analysis and to provide a perception aid based on an environmental trigger associated with the neurological condition. Performing the neurological analysis may include determining a reaction to a stimulus by receiving data from the one or more inwardly-directed sensors; and identifying a neurological condition associated with the reaction. In some embodiments, the perception aid may include a reminder, an alert, or virtual content that changes a property, e.g. a color, of a real object. The augmented reality display may be configured to display virtual content by outputting light with variable wavefront divergence, and to provide an accommodation-vergence mismatch of less than 0.5 diopters, including less than 0.25 diopters.

A closed-loop vision system is disclosed that utilizes a concept known as Dynamically Reconfigurable Vision (DRV), which is adaptive image sensing driven by a computer or human operator's response to changing scenery. The system reduces the amount of irrelevant video information sensed and thus achieves more effective bandwidth and computational resource utilization, as compared to traditional vision systems. One or more reconfigurable photodetector arrays sensitive to either visible, infrared or ultraviolet radiation are present in the DRV system. These photodetector arrays feature on-chip means for spatial and temporal data reduction implemented through multiple independently controllable, time-correlated, frequently overlapping windows on the photodetector array that may be programmed according to their size, location, resolution, integration time, and frame rate. All photodetector array windows are dynamically reconfigurable in real time on a frame-by-frame basis. Furthermore, a DRV system is constructed in a client-server architecture in which a vision processor client passes window request command messages to the reconfigurable photodetector array server, which in turn delivers the requested video back to the client processor. The ability to simultaneously reconfigure, integrate, process, and readout multiple photodetector array video windows is an important characteristic of the DRV system.

Information from execution of a vision processing module may be used to control a 3D vision system.

An automated inspection system particularly adapted for detection and discrimination of surface irregularities of specularly reflecting and other materials, such as are employed in laminate chip carriers and printed circuit boards, includes an area scan image sensor allowing illumination sources to surround an area of a surface being inspected. The illumination source preferably provides either or both bright field and dark field illumination of the surface; developing generally complementary images of surface irregularities. A self-registering rules-driven process for developing inspection masks reduces alignment operations and improves performance. Image enhancement and morphological operations to detect surface irregularities are performed by digital signal processing, preferably using a dedicated vision processor. Masks screen potential defects to critical mounting and bonding surfaces accurately without requiring alignment of data or reference images to acquired images. Since potential defects are copied from acquired images and stored, verification of defects may be performed without further access to the inspected part and without removal of the part to another specialized apparatus, simplifying processing and increasing throughput and operator efficiency.

A field-of-vision processing and filtering system for eliminating glare from mobile and transient light sources and reflective surfaces, using image recording, eye-position detection, and a active matrix screen functioning as a dynamically controllable visor, for modifying the field of vision appropriately. The system filters out high light intensity points from the field of vision, without seriously affecting the relevant parts of the field of vision. One embodiment of the system can be used by drivers for filtering glare from oncoming headlight at night, as well as during day time to block glare from the sun. Another embodiment of the system can be used for protection from glare of welding iron in a machine shop.

A home intelligent service robot for recognizing a user and following the motion of a user and a method thereof are provided. The home intelligent service robot includes a driver, a vision processor, and a robot controller. The driver moves an intelligent service robot according to an input moving instruction. The vision processor captures images through at least two or more cameras in response to a capturing instruction for following a target object, minimizes the information amount of the captured image, and discriminates objects in the image into the target object and obstacles. The robot controller provides the capturing instruction for following the target object in a direction of collecting instruction information to the vision processor when the instruction information is collected from outside, and controls the intelligent service robot to follow and move the target object while avoiding obstacles based on the discriminating information from the vision processor.

A system for identifying test tube types and properties in a sample handling machine using visual information automatically obtained by an optical imager and then processed using vision processing methods. The system includes an optical imager positioned to capture images containing one or more test tubes in a rack and a microcontroller programmed to extract predetermined regions of interest and interpret the optical information in the image to decipher the dimension of the test tubes, determine the presence or absence of caps on the test tubes, decode any encoded data, and interpret custom symbologies. The system may then determine the nature of the test tubes or other containers presented before the image and provide that information to the sample handling machine to assist with processing of samples.

Information from execution of a vision processing module may be used to control a 3D vision system.

The automated cage cleaning system is comprised of a pair of robotic arms, a soil side robot and a clean side robot. The soil side robot is utilized for removing the dirty cage bottoms from a cart, rack, pallet, or fixture, emptying soiled bedding from the cage bottoms, and placing the cage bottoms on a conveyer leading to the tunnel washing equipment. The clean side robot is used to grip the clean cage bottoms, and place the cage bottoms on a cart, rack, pallet, or fixture. Additionally, the present invention comprises an optical arranger robot with vision processing for detecting, and moving skewed cage bottoms to a re-grip station. From the re-grip station, the clean side robot places the cage bottoms on a rack, pallet, fixture, or any other device suitable for holding a plurality of cage bottoms.

This invention provides a system and method for determining position of a viewed object in three dimensions by employing 2D machine vision processes on each of a plurality of planar faces of the object, and thereby refining the location of the object. First a rough pose estimate of the object is derived. This rough pose estimate can be based upon predetermined pose data, or can be derived by acquiring a plurality of planar face poses of the object (using, for example multiple cameras) and correlating the corners of the trained image pattern, which have known coordinates relative to the origin, to the acquired patterns. Once the rough pose is achieved, this is refined by defining the pose as a quaternion (a, b, c and d) for rotation and a three variables (x, y, z) for translation and employing an iterative weighted, least squares error calculation to minimize the error between the edgelets of trained model image and the acquired runtime edgelets. The overall, refined / optimized pose estimate incorporates data from each of the cameras' acquired images. Thereby, the estimate minimizes the total error between the edgelets of each camera's / view's trained model image and the associated camera's / view's acquired runtime edgelets. A final transformation of trained features relative to the runtime features is derived from the iterative error computation.

The present invention is embodied in a system and method for rectifying two dimensional images of three dimensional (3D) objects for stereo vision processing. In general, the system and method of the present invention computes 2D projective transforms or homographies derived from specialized projective and affine transforms or components. The affine transform is comprised of a first transform and an optional second transform for image rectification. During image rectification of the present invention, optimization techniques are used for reducing the distortion.

A stereo vision system includes an image pre-processing unit for pre-processing the right and left images, and a stereo matching unit for carrying out stereo matching of the right and left images to acquire low-resolution distance information of the right and left images and high-resolution distance information of the right and left images upon detection of an object within a distance range through the low-resolution distance information.

The invention provides an unmanned aerial vehicle fixed-point flight control system based on visual positioning. The system comprises an UAV airborne module, a positioning marker, a ground monitoring module and a communication module. According to the system, through the cooperation with a visual processing algorithm, the UAV fixed-point flight is made by identification information, the disadvantages of low GPS fixed-point flight precision is made up, and the control system uses an open source operating system and a general UAV communication protocol and has good scalability and compatibility. The system can be applied to the UAV logistics, UAV monitoring and other directions.

In order to inhibit artifacts (even when a special image has been input) a visual processing device is provided with a spatial processing portion extracting surrounding image information US from an input image signal IS, and a special image detection portion outputting a special image effect adjustment signal DS according to a degree of a statistical bias of the image signal IS. The visual processing device also includes a continuous changing portion outputting an effect adjustment signal MOD in which the special image effect adjustment signal DS is continuously changed between frames, an effect adjustment portion outputting a synthesized signal MUS in which the effect of the visual processing differs depending on the effect adjustment signal MOD, and a visual processing portion outputting a processed signal OS obtained by visually processing the image signal IS based on the image signal IS and the synthesized signal MUS.

The invention discloses a welding quality analysis device based on infrared vision and an analysis method thereof. The analysis device comprises an infrared vision collecting system that is adjustably and fixedly connected to a welding facility, a vision processing system, in which welding defect intelligent recognition algorithm is embedded, and a feed control system, which can evaluate the welding quality, give an alarm, and adjust the parameters of the welding facility. The analysis method comprises the following steps: (1) collecting the infrared vision information of a molten pool or an area near a molten pool in real time through infrared sensing; (2) processing the infrared vision information by the welding defect intelligent recognition algorithm so as to obtain the weld seam positions and welding defect characteristics; (3) evaluating the welding quality in real time, and controlling the welding facility and giving an alarm aiming at different welding defects. According to the provided intelligent analysis device and intelligent analysis method, the welding process can be monitored in real time, the welding defects can be recognized, the welding seam position can be traced, the welding quality can be evaluated, the welding loss can be reduced, and the finished product yield rate can be increased.

The invention discloses a mobile vehicle-mounted intelligent taking-off and landing system of an unmanned aerial vehicle. The system comprises a taking-off and landing platform device and an unmannedaerial vehicle fixing and automatic charging device. Firstly, four universal balls are additionally arranged at the bottom of an undercarriage of the unmanned aerial vehicle so that the unmanned aerial vehicle can automatically slide into a groove of a landing platform through rotation of the universal balls when landing on the smooth landing platform; then, a conductive ring is additionally arranged in the fixed position of each vehicle foot of the undercarriage of the unmanned aerial vehicle, the conductive rings of the unmanned aerial vehicle and a charging guide rail in the groove are located on the same plane after the unmanned aerial vehicle lands, and every two adjacent vehicle feet form an electrode connected with a battery of the unmanned aerial vehicle; and finally, a visual processing module with an embedded chip is arranged on the unmanned aerial vehicle. The visual processing module is composed of two types of sensors of a GPS module and a visual camera module, and the unmanned aerial vehicle is precisely located through algorithm control. By the adoption of the system, the unmanned aerial vehicle can conveniently take off and be collected in the field environment andcan be autonomously charged.

The 3D active real-time positioning system based on binocular vision and laser ranging consists of three parts of vision processing subsystem, control subsystem and mechanical mechanism. The target image the video camera under the control of image acquisition card obtains is processed in the vision processing computer to obtain the 2D position information in image coordinate sent to the public memory area. Then, the control computer obtains the position information from the public memory area, performs coordinate conversion and real-time programming, outputs via D / A converter board to the driver to drive the motor and controls the laser via the angle encoder feedback loop to irradiate the target accurately. Finally, the depth information the range finder measures is fed back to the vision computer to obtain the 3D position information of the target. The system has the advantages of high distance precision, high activity, high real-time performance, low cost, etc.

The present invention is embodied in a system and method for computing rectifying homographies for stereo vision processing of three dimensional (3D) objects. In general, the system and method of the present invention computes 2D projective transforms or homographies derived from specialized projective and affine transforms or components. The affine transform is comprised of a similarity transform and an optional shearing transform for image rectification. During image rectification of the present invention, optimization techniques are used for reducing the distortion.

The invention provides a visual processing device that has a hardware configuration that does not depend on the visual processing to be achieved. A visual processing device 1 is provided with a spatial processing portion 2 and a visual processing portion 3. The spatial processing portion 2 performs predetermined processing with respect to an input signal IS that has been received as input, and outputs the result as an unsharp signal US. The visual processing portion 3 outputs an output signal OS, which is the input signal IS after visual processing, based on a two-dimensional LUT 4 that lists the relationship between the input signal IS that has been received as input and the unsharp signal US, and the output signal OS.

A stereo vision system includes an image pre-processing unit for pre-processing the right and left images, and a stereo matching unit for carrying out stereo matching of the right and left images to acquire low-resolution distance information of the right and left images and high-resolution distance information of the right and left images upon detection of an object within a distance range through the low-resolution distance information.

The invention provides a fluorescent powder coating surface defect detecting system and a detecting method based on machine vision. The system comprises a laser emitter, an image collecting terminal, an image sensor servo motor adjusting module, and an upper position personal computer (PC). The image collecting terminal comprises an image sensor, a vision processing and controlling module, and an interface module, wherein the image sensor, the vision processing and controlling module, and the interface module are connected in succession, the upper position PC is connected with the vision processing and controlling module through the interface module, the image sensor servo motor adjusting module is respectively connected with the vision processing and controlling module and the image sensor, and the laser emitter is connected with the vision handling and controlling module. A laser triangulation method is adopted to detect the defects that a fluorescent powder coating is too thick and too thin, and thickness is not even. The system collects fluorescent powder coating images which are coated to be compared with a standard image template, and therefore the defects that the fluorescent powder coating is irregular, stuck with glue and foreign matters and the like are detected. The system is simple in structure, low in cost, high in detection speed, and high in detection precision.

An apparatus for measuring jaw motion has a pair of fixed marker attached to both sides of face of patient, a pair of movable markers disposed to face the fixed marker in a spaced distance and to move in unison with the movement of the lower jaw of patient, four cameras recording the three-dimensional movement of the movable marker relative to the fixed marker, as lower jaw moves, and personal computer for receiving and processing the image signals fed from connected cameras. The apparatus can accurately measure the location of the center of patient's jaw motion and the moving track thereof with stereo vision processing of the image signals obtained from camera.

The invention discloses a LED lamp light scene control system and control method thereof. The control system comprises a video frequency acquiring sub system, a vision processing sub system, a lamp light decision making sub system and a group of illuminating sub systems connected with the lamp light decision making sub system. the vision processing sub system is connected with the video frequency acquiring sub system for receiving image information and performing vision identification; the lamp light decision making sub system receives the vision identification processing signal and generates decision control signal; and the illuminating sub systems lights up the scene lamps according to the decision control signal. The control method comprises: acquiring the action information of the lamp light director; performing vision identification and processing; generating relative decision control signal; sending to the LED array and lighting up the lamp light scene. The invention can make the art light scene after lighting up the LED array more intelligent and more evident in effect; the art effect of the LED array can be showed in larger range, for example all the outer wall of a building group; and the coloring effect of the vision effect of the light scene is improved.

This invention provides a vision system with an exchangeable illumination assembly that allows for increased versatility in the type and configuration of illumination supplied to the system without altering the underlying optics, sensor, vision processor, or the associated housing. The vision system housing includes a front plate that optionally includes a plurality of mounting bases for accepting different types of lenses, and a connector that allows removable interconnection with the illustrative illumination assembly. The illumination assembly includes a cover that is light transmissive. The cover encloses an illumination component that can include a plurality of lighting elements that surround an aperture through which received light rays from the imaged scene pass through to the lens. The arrangement of lighting elements is highly variable and the user can be supplied with an illumination assembly that best suits its needs without need to change the vision system processor, sensor or housing.

The invention belongs to the field of computer vision, and aims at achieving the accurate filling of a pixel row and column loss image. The technical scheme employed in the invention is that a row and column loss image filling method based on low-rank matrix reconstruction and sparse representation comprises the steps: introducing low-rank priori to carry out the constraining of a potential image based on the low-rank matrix reconstruction theory; introducing a separable two-dimensional sparse priori based on the sparse representation theory with the consideration to a condition that the sparse representation of each column of a row loss image can be achieved through a column dictionary and the sparse representation of each row of a column loss image can be achieved through a row dictionary; specifically describing a filling problem of an image with the row and column loss into a solving problem of a constraint optimization equation based on the above combined low-rank and separable two-dimensional sparse priori, thereby achieving the filling of the row and column loss image. The method is mainly used for a computer vision processing occasion.

The invention provides a route navigation system and method. The route navigation system comprises instruction input equipment, a navigation device, a vision acquirer and a vision processor, wherein the instruction input equipment is used for receiving a navigation instruction input by a user, and used for transmitting the navigation instruction to the navigation device; the navigation device is used for acquiring current position information of the user, and used for generating a navigation route according to the current position information and the input navigation instruction; the vision acquirer is used for acquiring an image of a road in front of the navigation route, and used for transmitting the image to the vision processor; the vision processor is used for acquiring obstacle information in the image, and used for transmitting the obstacle information to the navigation device; the obstacle information is output by the navigation device. By adopting the route navigation system and the route navigation method, the image of the road in front of the navigation route acquired by the vision acquirer is processed by the vision processor, and obstacle information in the image is extracted, so that the image does not need to be transmitted to a server to be processed remotely, and problems of image information deficiency, image transmission delay, image transmission distortion and the like caused by relatively slow transmission speed because of a network and the like can be avoided.