48 results about "Vision based systems" patented technology

Aspects of the invention are directed to a visual-based system and method for non-destructively evaluating an uncoated turbine engine component. Aspects of the invention are well suited for high speed, high temperature components. Radiant energy emitted from an uncoated turbine engine component can be captured remotely and converted into a useful form, such as a high resolution image of the component. A plurality of images of the component can be captured over time and evaluated to identify failure modes. The system can also measure and map the temperature and/or radiance of the component. The system can facilitate the non-destructive evaluation of uncoated turbine components during engine operation without disassembly of the engine, thereby providing significant time and cost savings. Further, the system presents data to a user with sufficient context that allows an engine operator can evaluate the information with an increased degree of confidence and certainty.

The invention provides for systems and methods for location-identification and monitoring of objects, such as shipping containers, at a transit terminal using an automated vision based tracking system. Such a system is ideally suited to provide minimal error rates, low cost implementation, real-time data and automatic merging of data with corresponding object identification systems and terminal operating systems. The systems and methods of the present invention provide for location-tracking of objects without the need to retrofit the objects with a tagging or marker device. The vision-based system incorporates the use of multiple imaging devices and a hand-off method for tracking the location of the objects over extended distances.

A method for is provided for creating a shadow-reduced image from a captured image for distinguishing a clear path of travel. Each pixel of a captured input image is plotted according to a two dimensional logarithmic graph. A specific color set relating to an associated color value of a clear path. A linear illumination-invariant axis is determined as a function of the specific color set. An illumination direction for the linear illumination-invariant axis is determined. A log-chromaticity value of each plotted pixel of the specific color set is projected on the axis. Edges in the input image and the illumination-invariant image domain are identified. The identified edges of the input image are compared to identify edges in the illumination-invariant image domain. A determination is made whether a shadow edge is present in response to comparing the edges. A shadow-reduced image is generated for scene analysis by a vehicle vision-based system.

Systems and methods of monitoring solidification quality and automatic correcting any detected error in additive manufacturing are described. The present disclosure includes a build station for manufacturing one or more parts and a controller having one or more computer-vision based system coupled to the build station. One or more camera is provided to obtain a plurality of images of the solidified parts at predetermined settings. The present disclosure introduces a predictive model trained by machine learning algorithm, the predictive model calculates level of solidification quality of a manufactured part and build parameters value to be adjusted. The present disclosure introduces a plurality of validation coupons having various shapes to enhance more accuracy in manufacturing, wherein the validation coupons further include block data which is distributed to electronic ledger system.

A method is provided for removing an illumination generated shadow in a captured image. Each pixel of the captured input image is plotted on a two dimensional logarithmic graph. A linear axis for the plurality of color sets is determined that is substantially orthogonal to a respective illumination direction of each respective color set. A log-chromaticity value of each plotted pixel is projected on the axis. An orientation of the linear axis is selected to minimize an illumination effect and provide optimum separation between each of the respective color sets on the linear axis. Edges in the input image and illumination invariant image domain are identified. The identified edges of the input image are compared to identify edges in the illumination invariant image domain. A determination is made whether a shadow edge is present in response to the comparison. A shadow-reduced image is generated for scene analysis by a vehicle vision-based system.

A mesoscale calibration artifact, also called a hybrid artifact, suitable for hybrid dimensional measurement and the method for make the artifact. The hybrid artifact has structural characteristics that make it suitable for dimensional measurement in both vision-based systems and touch-probe-based systems. The hybrid artifact employs the intersection of bulk-micromachined planes to fabricate edges that are sharp to the nanometer level and intersecting planes with crystal-lattice-defined angles.

A system and method for identifying the start location of the lead thread and the thread profile and quality in a threaded bore in a part, where the system and method can be used for determining the location of the lead thread in a threaded bore in a cylinder head for a spark plug in one non-limiting embodiment. The system includes a moveable table on which the part is mounted. The system also includes a probe having an optical assembly that is inserted in the threaded bore. A camera uses the optical assembly to generate images of the thread bore, where the images are image slices as the probe moves through the threaded bore. The image slices are unwrapped and then joined together to form a planer image to determine a start location of the lead thread, thread count, defects in the threaded bore and thread profile parameters.

A typing off-loading and item separation system to automatically separate different parcel types includes an feed conveyor, receiving conveyor, sorting conveyor, cameras and photoelectric eye. Overhead cameras and/or photoelectric sensors detect the item size and whether it is cubic in nature and type and size of its footprint. An in-line slide sorter having alternating conveyor rollers and pop-up belts pass through to, or divert items from a downstream conveyor. A vison based system may also be used to detect space between articles and insert articles in the unoccupied space to maximize conveyor area, volume, or density by controlling conveyor speed.

A method is provided for removing an illumination generated shadow in a captured image. An image is captured by an image capture device. Each pixel of the captured image is represented by a respective color value in a logarithmic graph. A non-linear illumination-invariant kernel is determined. An illumination direction for each respective color set is determined in the logarithmic graph that is orthogonal to the non-linear illumination-invariant kernel. A log-chromaticity value of each plotted pixel is projected on the non-linear illumination-invariant kernel. Edges are identified in the input image. Edges are identified in the illumination-invariant image domain. The identified edges are compared. A determination is made whether a shadow is present in response to an edge identified in the input image and an absence of a correlating edge in the illumination-invariant image domain. A shadow-reduced image is generated for scene analysis by a vehicle vision-based system.

A typing off-loading and article sorting system to automatically separate different parcel types includes an feed conveyor, receiving conveyor, sorting conveyor, cameras and photoelectric eye. The overhead cameras detect the item size and whether it is cubic in nature and type and size of its footprint. An in-line slide sorter having alternating conveyor rollers and pop-up belts pass through to, or divert articles from, a downstream conveyor. The vison based system may also be used to detect space between articles and insert articles in the unoccupied space.

A system and method for detecting a distress condition of a person in a monitored location. The system is configured to receive an image stream of the monitored location, and detect a human body or body part within the monitored location. The system maintains and updates a list of areas in which the lack of movement is permitted e.g. bed, sofa, chairs. Upon detecting that the person is no longer moving and exists in a new area that is not in the list of areas, the system enters into an acknowledgement session in which the system asks the person to perform a certain action if everything is fine. If the given action is detected within a pre-determined period the system updates the list of areas to add the new area therein, otherwise the system would execute a pre-defined function representing a response to the distress condition e.g. call 911.

The invention relates to a computer-vision-based system and method for detecting the number of pedestrians waiting to cross a crosswalk. The system comprises two charge coupled device (CCD) cameras and a computer image processing system, wherein the computer image processing system is connected with the cameras through interfaces; the two CCD cameras are arranged at two ends of the crosswalk; and field angles of the two CCD cameras cover an opposite pedestrian waiting region and a diagonally opposite vehicle region. The method comprises the following steps of: acquiring an image from a video image; preprocessing the pedestrian waiting region; acquiring a foreground image by using a Gaussian mixed background model method; acquiring a vertical integral projection graph; and processing the vertical integral projection graph, and performing information statistics to obtain the number of the pedestrians waiting to cross the crosswalk. Compared with a conventional pedestrian number detection method, the method has the advantages of simplicity and high efficiency, and can be applied to a complicated situation.

In the primal cutting-up of half carcasses of animals (12), vision systems are known whereby the determination of one or more fix points on the carcasses takes place, and where on the basis of the position of these points a visualization of the ideal cut line is effected. But the primal cutting-up of carcasses (12) has hitherto been carried out with manually-operated saws on the basis of operator evaluation. However, the use of manually-operated saws involves the possibility of deviations in relation to the ideal cut line, and the manual work is very monotonous and fatiguing for the operators. There is thus disclosed a system as well as a laying-down module (2) and a vision-based system for automatic primal cutting-up of half carcasses, comprising a laying-down module with a laying-down conveyor (18), and a laying-down and angle-positioning module (6) with sideways displaceable conveyors for positioning of a relevant carcass (12) for sawing-up in a subsequent saw module (8), and a method for the execution of automatic primal cutting-up of meat items, namely half carcasses of animals.

The invention provides a chute system (C1,C2,C3) for a sorting system arranged for transporting objects, e.g. for use for discharging luggage from a conveyor system. The chute system has one or more chute sections with an inlet (IL) in one end and an outlet (OL) in the opposite end. Displacement means, e.g. a pneumatic actuator, is arranged to adjust an angle of inclination of the one or more chute sections (C1,C2,C3) by displacing the chute section (C1,C2,C3) in a motion comprising pivoting around a pivot point positioned downstream of the inlet (IL). E.G. the pivot point can be positioned at the outlet, e.g. by means of a hinge. The adjustment of the angle of inclination may be controlled by a processor in response to various position and/or speed sensors and/or information about incoming objects from a vision based system or from the associated sorting system, e.g. identification of poly wrapped objects. The angle of inclination can be increased in case an object stops on the chute section, or the angle of inclination can be decreased in case an object moves too fast, even if a simple gravity chute is used. A cascade of two or more chute sections (C1,C2,C3) with adjustable angles of inclination can be used to control batches of objects and to control back pressure of objects on the chute.

The invention relates to a computer vision-based system and a computer-vision based method for automatically measuring the viscosity of colored liquid. The system comprises a BS/U/M miniature suspended level viscometer fixed on a fixed bracket, a BS/U/M miniature suspended level viscometer connected with an exhaust system and a BS/U/M miniature suspended level viscometer connected with a computer vision system. The method comprises the following steps: (a) building a viscometer scale mark position template; (b) performing liquid level detection and tracking; (c) measuring the difference between the time when the liquid level passes through a lower scale mark and the time when the liquid level passes through an upper scale mark; and (d) performing the viscosity calculation to obtain the viscosity of liquid measured. The method performs automatic measurement, overcomes errors of manual measurement, and improves measurement accuracy and measurement efficiency.

An improved vision-based system generates object detection corresponding to different viewing areas based on vehicle speed. At lower vehicle speeds the system covers a wider field of view and a near zone while at higher vehicle speeds the system covers a normal or narrower field of view and a far zone. The system includes a lens package having a movable lens, an image sensor and image transformer. The movable lens is movable between a first position representing a wide angle view and a second position representing a normal angle view. Each of these views generates an image such that a wide angle view generates a wide angle image and a normal angle view generates a normal angle image. The wide angle view is associated with the vehicle's passive safety systems while the normal angle view is associated with the vehicle's active safety systems.

A method, system, and apparatus for transferring dies to respective substrates is described. Conventional techniques include vision-based systems that pick and place dies one at a time onto substrates. The present invention can transfer multiple dies simultaneously or consecutively. Dies are loaded in a channel of a die application device. The dies are moved through the channel using any of a variety of means, such as gravity, air, vibration, a brush, a spring, etc. The die application device dispenses the dies onto respective substrates. In an aspect, the die application device independently dispenses each of the dies. In another aspect, the die application device dispenses multiple dies at a time.

The invention discloses a multi-vision-based system and method for measuring gas-liquid two-phase flow phase fraction of a small channel. The system comprises a high-speed camera, two light sources, a right-angle prism, a small pipeline, a glycerinum groove and a computer. The method comprises the following steps: firstly, simultaneously obtaining gas-liquid two-phase flow flowing image sequences of the small channel from two vertical angles; secondly, carrying out image pretreatment and optical distortion correction and building phase fraction measurement models of four typical flow patterns, namely bubble flow, slug flow, annular flow and wavy flow; thirdly, extracting feature vectors of images and carrying out flow pattern identification; and finally, selecting the phase fraction measurement model of the corresponding flow pattern and calculating the phase fraction. By a multi-vision technology, the phase fraction measurement model is built for each typical flow pattern, the flow pattern information is introduced into the phase fraction measurement model, and thus the measurement accuracy is improved. The corresponding device has the advantages of simplicity in structure, non-contact measurement, visualization and the like.