6215 results about "Infrared image" patented technology

A method of visually detecting a leak of a chemical emanating from a component. The method includes: aiming a passive infrared camera system towards the component; filtering an infrared image with an optical bandpass filter, the infrared image being that of the leak; after the infrared image passes through the lens and optical bandpass filter, receiving the filtered infrared image with an infrared sensor device; electronically processing the filtered infrared image received by the infrared sensor device to provide a visible image representing the filtered infrared image; and visually identifying the leak based on the visible image. The passive infrared camera system includes: a lens; a refrigerated portion including therein the infrared sensor device and the optical bandpass filter (located along an optical path between the lens and the infrared sensor device). At least part of a pass band for the optical bandpass filter is within an absorption band for the chemical.

Analysis of a vehicle is performed using multi-dimensional infrared image data acquired for the vehicle. A component of the vehicle can be identified within the infrared image data, and the infrared image data for the component can be analyzed to determine whether any condition(s) are present on the vehicle. One or more actions can be initiated in response to a determination that a particular condition is present. Additionally, visible image data can be used to supplement the infrared image data. Still further, infrared image data for similar components imaged concurrently with the component can be used to identify whether any condition(s) are present on the vehicle. Unlike prior art approaches in the rail industry, the analysis can be performed on rail vehicles within a classification yard.

A real-time thermal imaging apparatus and method includes multiple digital infrared cameras mounted to an automated composite material layup device to record digital infrared images of the composite material surface on a real-time basis during a composite material layup process. The digital infrared cameras are triggered periodically to produce digital images of the composite material. The digital image data is sent to an image analyzer which detects edges of and anomalies in the composite material and generates alarm and other process control signals. The image analyzer also aggregates the digital images from the multiple cameras and the digital images recorded over a sequence in time to produce a continuous virtual digital image of the composite material surface. The digital image data and associated analysis results are saved and may be displayed on a real-time basis or at a later time.

Near infrared imaging using elastic light scattering and tissue autofluorescence are explored for medical applications. The approach involves imaging using cross-polarized elastic light scattering and tissue autofluorescence in the Near Infra-Red (NIR) coupled with image processing and inter-image operations to differentiate human tissue components.

The invention discloses an online monitoring system for infrared thermal imaging of a converting station. The system comprises an online infrared thermal imaging instrument, a view screen monitoring and processing module, an infrared image information processing module and a system management and maintenance module, wherein the view screen monitoring and processing module comprises a communication and control subsystem and an infrared imaging and temperature measuring subsystem; the communication and control subsystem is used for controlling a field online infrared thermal imaging instrument, a visible light CCD (Charge Coupled Device) and a tripod head servo and setting and controlling a data link; the infrared imaging and temperature measuring subsystem comprises a temperature measuring, recording, alarming and short message platform system for realizing temperature measurement, alarming and transmission of alarm information through a short message platform; the infrared image information processing module comprises an infrared image analysis system, a failure auxiliary diagnosis system and an infrared and visible light video processing system; and the system management and maintenance module comprises an equipment thermal failure typical infrared image library management system, a management inquiry, statistic and report system and an interface system for an extant service system. By means of the online monitoring system in the invention, the defects of portable infrared imaging are overcome, artificial detection is combined with system detection, real-time monitoring of electric equipment is realized, and infrared thermal image monitoring of a monitored range or specified target equipment as well as data acquisition and recording, storage and analysis of a temperature field are ensured. The system has the characteristics of automatic routing inspection, automatic pre-warning, accuracy, high speed and remote monitoring.

In accordance with at least one embodiment of the present invention, a portable inspection system is disclosed to capture inspection data, such as for example an infrared image, sound information, and / or electrical measurement information. The inspection data may be securely recorded (e.g., with an encryption algorithm) along with associated information, which may include for example date, time, system settings, operator identification, and location.

The invention provides a device for real time taking and self-adaptive fusion of infrared light images and visible light images, relating to the detection and fusion of the image. A dichroic mirror is installed on a lens position adjusting device, and the dichroic mirror and the lens position adjusting device constitutes an optical splitting system which resolves a target and ambient lights thereof into visible lights and infrared lights; two CCDs with a visible light filter and an infrared light filter respectively obtain the visible light image and the infrared image of the target; a computer is connected with an image grabbing card by a communication line, a light intensity signal detected by an illuminance meter is input into the computer by a video grabbing card; and complete registration of the visible light image and the infrared image can be realized in a mechanical manner, thus realizing the real time taking and self-adaptive fusion of the infrared light image and the visible light image.

A night vision device provides both an amplified visible light image and an infrared image, overlayed upon each other so that they appear to be a single image. A user may select to utilize either an intensified visual image only, an infrared image only, or ratios of both images simultaneously. Dichroic surfaces within the night vision device are utilized first to separate light into visible and infrared portions, and then to recombine the visible and infrared images to a single image.

The invention discloses a calibration method of correlation between a single line laser radar and a CCD (Charge Coupled Device) camera, which is based on the condition that the CCD camera can carry out weak imaging on an infrared light source used by the single line laser radar. The calibration method comprises the steps of: firstly, extracting a virtual control point in a scanning plane under the assistance of a cubic calibration key; and then filtering visible light by using an infrared filter to image infrared light only, carrying out enhancement, binarization treatment and Hough transformation on an infrared image with scanning line information, and extracting two laser scanning lines, wherein the intersection point of the two scanning lines is the image coordinate of the virtual control point in the image. After acquiring multiple groups of corresponding points through the steps, a correlation parameter between the laser radar and the camera can be solved by adopting an optimization method for minimizing a reprojection error. Because the invention acquires the information of the corresponding points directly, the calibration process becomes simpler and the precision is greatly improved with a calibrated angle error smaller than 0.3 degree and a position error smaller than 0.5cm.

An interactive system is disclosed that includes an infrared source assembly for illuminating an exposed interface surface that is exposed to a user with substantially uniform infrared illumination, a diffuser for diffusing infrared illumination, and an infrared detection system for capturing an infrared image of the exposed interface surface through the diffuser. The infrared detection system provides image data that is representative of infrared illumination intensity of the exposed interface surface.

Infrared (IR) camera systems for and a method of obtaining infrared images of target subjects are provided. In one embodiment, an IR camera system (10) includes a lens (12), a number of IR pass filters (14), an optical detector (16), a processor (18) mounted on a circuit board (20), a distance sensor (22), a visible light sensor (24), an IR light sensor (26), an IR illuminator (28), and a number of video outputs (30), all of which may be disposed within an appropriately configured housing (32). The filters (14) are mounted on a juke-box like rack system (34) also included within the housing (32). The processor (18) determines which pass filter is needed in order to optimize the image and sends an electronic signal to the rack system (34) directing the rack system (34) to move the appropriate filter (14) into the optical pathway between the lens (12) and the optical detector (16) and pull all of the other IR filters (14) out of the optical pathway between the lens (12) and the optical detector (16).

The invention relates to a pedestrian recognition and tracking method based on an accelerated area Convolutional Neural Network. Firstly, training and testing data set are preprocessed according to the requirements through a robot with an infrared camera to acquire a training dataset and a testing dataset at night, and then, actual target position labeling is conducted on all training and testing photos and is recorded to a sample file; then, the accelerated area Convolutional Neural Network is constructed, the accelerated area Convolutional Neural Network is trained by using the training dataset, and the final probability belonging to a pedestrian area and a bounding box of the area are calculated out from network output by the usage of a non-maximum suppression algorithm; the accuracy of the network is tested by the usage of the testing dataset, and a network model consistent with the requirements is obtained; photos collected by the robot at night are input to an accelerated area Convolutional Neural Network model, and the probability belonging to the pedestrian area and the bounding box of the area are online output by a model in real time. According to the pedestrian detection and tracking method based on the accelerated area Convolutional Neural Network, a pedestrian in an infrared image can be effectively recognized, and real-time tracking for a pedestrian target in an infrared video can be achieved.

Counterfeit electronic devices are detected by comparing a thermal profile of the counterfeit device and an authentic device under predetermined operating conditions. A thermal profile for an authentic electronic device is recorded executing an instruction set over time, such as with static infrared images at predetermined times, video infrared images over a predetermined time period or temperature measurements made at predetermined locations of the electronic device. In one embodiment, a thermal profile indicates that a processor device has been used in the place of a field programmable grid array device. In an alternative embodiment, an electromagnetic profile is detected instead of or in addition to the thermal profile. The electromagnetic profile of an authentic device is used to create an expected profile for comparison with an electromagnetic profile of electronic devices under test.

The invention discloses a power equipment infrared image fault positioning, identification and prediction method. The power equipment infrared image fault positioning, identification and prediction method comprises the following steps: 1) collecting power equipment infrared thermal image data; 2) classifying the infrared images to form a data set; 3) constructing a convolutional neural network model; 4) separating out faulty power equipment; 5) monitoring faulty power equipment in real time, and longitudinally collecting temperature data; 6) positioning a fault part, segmenting the infrared image of the power equipment, and extracting a fault area; 7) diagnosing a fault area, and judging a fault level; 8) predicting an equipment state trend; 9) uniformly outputting and displaying the information; 10) storing the fault level; 11) making four types of infrared image data sets; 12) building a target detection model and training; 13) directly detecting an infrared image of power equipmentto be detected through a target to obtain a fault position and a fault level; 14) repeating the step (5); 15) repeating the step (8); and 16) repeating the step (9) facilitating positioning of the fault position, fault level judgment and prediction of the fault equipment and giving a maintenance suggestion.

The invention discloses a fire detecting system applied to an unmanned helicopter and a fire detecting method thereof. The system comprises infrared image acquiring equipment and a signal processing flow network, wherein the signal processing flow network comprises an input layer, a middle layer and an output layer; the temperature gradient operator calculation is respectively carried out in the vertical direction, the horizontal direction, the direction of plus 45 degrees and the direction of minus 45 degrees in the center of a suspected area, and a calculation result is a basis of judging fire flame; a differential algorithm adopting interframe time difference as the time change rate is carried out by a method for subtracting absolute values of adjacent interframe pixel gray values, anda calculation result is used as a basis of judging a fire high-risk point. The invention rapidly recognizes the fire flame and the fire high-risk point by a platform with low cost and high efficiencyof the unmanned helicopter through an infrared camera, early warns a fire accurately in time and has the characteristics of manoeuvrability, high efficiency and no dead angle. A fire flame and fire high-risk point detecting algorithm designed by aiming at the detection of an infrared image is efficient, simple, practical and effective.

A camera that can capture a visible light image and an infrared image of a target scene. The camera includes a focusable infrared lens and a display. The display provides the visible light and infrared images in a focus mode or an analysis mode. In the focus mode, the percentage of infrared imagery of the target scene is relatively higher to assist the user in focusing the infrared image. In analysis mode, the percentage of infrared imagery is relatively lower to assist the user in analyzing and visualizing the target scene. The modes may be switched manually or automatically.

Near infra-red images of natural scenes usually have better contrast and contain rich texture details that may not be perceived in visible light photographs. The contrast and rich texture details form a NIR image corresponding to a visible light image are useful for enhancing the visual quality of the visible light image. To enhance the visual quality of a visible light image using its corresponding near infra-red image, a computer-implemented method computes a weight region mask from the visible light image, transfers contrast data and texture data from the near infra-red image to the visible light image guided by the weighted region mask. The contrast data is computed from the low frequency subbands of the visible light image and corresponding infra-red image after a wavelet transform by matching the histogram of gradient magnitude. The texture data is computed from the high frequency subbands of both images after wavelet transform.

The invention discloses a barrier detection method in the vegetation environment based on multispectral and 3D feature fusion. The method comprises that 3D point cloud data is collected, and color and near-infrared images are collected at the same time; 3D point cloud data is registered with multispectral data to obtain multispectral 3D point cloud; a grid map is established, and candidate barrier grids are obtained via a height threshold; the scale of the near-infrared image is adjusted to normalize the infrared light intensity; the near-infrared intensity value and the visible light intensity of RGB color information within the grids are combined and serve as feature information, and 2D feature is obtained via calculation; and the candidates barrier grids are processed and filtered by utilizing a Gaussian mixture model to obtain a final barrier detection result. According to the method, influence caused by change of illumination condition is reduced by normalizing the infrared light intensity, and multispectral 3D features are sued to realize effective barrier detection.

Various embodiments relate to methods and systems for displaying an ultrasound image of a patient's target body portion using a wearable display module. A wearable display module can be mounted on a user's head. A wearable display module can display ultrasound images as a heads up display so that a user can view an ultrasound image while maintaining lines of sight with other viewpoints. Various embodiments relate to methods and systems for displaying both an ultrasound image and a light image (e.g., a near infrared image). A single display can be configured to display the light image and the ultrasound image on a single surface, in close proximity, and at the same time or in sequence. This disclosure provides in some embodiments for the use of wireless communication between various imaging probes, sensors, image processors, and display modules in order to facilitate more effective viewing of images.

The invention relates to data identification, in particular to a bimodal face authentication method with a living body detection function and a system. The authentication method of the invention comprises the following steps: A. establishing a database of visible light training images and near-infrared training images of known faces; and B. simultaneously collecting visible light images and near-infrared images of the heads of people to be authenticated. The invention also provides a bimodal face authentication system with a living body detection function. The invention has the beneficial effects that combined identification with the bimodal characteristics of face near-infrared images and face visible light images is adopted, as a result, the identification and authentication accuracy is improved, identification failure in the case of major changes of faces is avoided; and in addition, a living body detection module is utilized to effectively prevent personators from using photos or models to deceive others.

A digital imaging device is provided with a touch sensitive display screen 10. The screen 10 displays an image 12 captured by the imaging device. Along one side of the screen is a toolbar 14 upon which is provided a plurality of individual icons 16. The icons 16 represent particular control functions that may be selected by a user. Examples of such control functions represented by the icons 16 include but are not limited to save, send, retrieve or discard image; rotate, reflect, crop, resize or edit image; compare images; process image (e.g. sharpen, blur, emboss, edge detect, pixelise, apply filter or similar); or vary image properties (e.g. brightness, colour balance, colour depth, contrast, convert to greyscale / black and white, effective surface temperature displayed (for infrared images) or similar). The user can select icons by touching the screen either directly or more preferably by tapping the screen with a suitable implement such as. a pen, a stylus or similar. Once a user has selected an icon, further icons may be displayed on the screen to allow the user to operate the selected function as desired.

An aspect of the present invention provides a vehicle surroundings monitoring device that includes an object extracting unit configured to extract objects that emit infrared rays from a photographed infrared image, a pedestrian candidate extracting unit configured to extract pedestrian candidates based on the shape of the images of objects extracted by the object extracting unit, and a structure exclusion processing unit configured to exclude structures from the pedestrian candidates based on the gray levels of the images of the pedestrian candidates.

The invention is a video frequency real-time displaying control device for infrared heat imaging image and visible image. The device includes a computer, an infrared heat imaging device, visible camera whose field angle can match with it; there has a video collecting card on the interface slot of the computer, the infrared image device and the visible camera are fixed on the same platform; there stores control, temperature measuring, image processing and displaying procedure model, it can remote control the platform, the infrared heat device and the visible light camera, they can be rotated synchronously, the field angles of the posterior two match, and makes the heat imaging image and the visible light image can coincided with the coordinate of the computer monitor. The invention can carry on real-time memorization, displaying, imaging, and playbacks the heat imaging image and the visible light image, it also can display the temperature valve and position coordinates of the object, it also has merits of infrared imaging and visible light image.

The invention provides an infrared images method for detecting targets at sea, which relates to a method for detecting the targets at sea. The invention aims to provide the method for detecting the targets at sea, which not only can well inhibit sea clutters to obtain reasonable image segmentations, but also can extract out the fractal characteristics at a high speed to remove false targets so as to achieve effective detections. The method comprises the following steps: performing preprocessing on the obtained infrared images; performing self-adapting iteration threshold segmentation; detecting whether the part of a sea-sky line has a region of interest (ROI); extracting the ROI at the background part of the sea-sky line; extracting the ROI at the background part of a non-sea-sky line; and combining the regions of interest to obtain an image of interest to be further processed, and extracting the fractal characteristics of each ROI to perform target detections. The method can quickly and effectively segment out the regions of interest in the infrared images, and not only reduces the amount of calculation to extract out the fractal characteristics at a higher speed because the extracted regions of interest is far smaller than the original images, but also can remove the false targets appearing in the threshold segmentation through the fractal characteristics.

The invention discloses an infrared target instance segmentation method based on feature fusion and a dense connection network, and the method comprises the steps: collecting and constructing an infrared image data set required for instance segmentation, and obtaining an original known infrared tag image; Performing image enhancement preprocessing on the infrared image data set; Processing the preprocessed training set to obtain a classification result, a frame regression result and an instance segmentation mask result graph; Performing back propagation in the convolutional neural network by using a random gradient descent method according to the prediction loss function, and updating parameter values of the convolutional neural network; Selecting a fixed number of infrared image data training sets each time and sending the infrared image data training sets to the network for processing, and repeatedly carrying out iterative updating on the convolutional network parameters until the convolutional network training is completed by the maximum number of iterations; And processing the test set image data to obtain average precision and required time of instance segmentation and a finalinstance segmentation result graph.

The invention discloses a 3D convolutional neural network sign language identification method integrated with multi-modal data. The 3D convolutional neural network sign language identification methodintegrated with multi-modal data includes the steps: constructing a deep neural network, respectively performing characteristic extraction on an infrared image and a contour image of a gesture from the spatial dimension and the time dimension of a video, and integrating two network output based on different data formats to perform final classification of sign language. The 3D convolutional neuralnetwork sign language identification method integrated with multi-modal data can accurately extract the limb movement track information in two different data formats, can effectively reduce the computing complexity of a model, uses a deep learning strategy to integrate the classification results of two networks, and effectively solves the problem that single classifier encounters error classification because of data loss, so as to enable the model to have relatively higher robustness for illumination and background noise of different scenes.

The invention discloses a fusion method of an infrared image and a visible light dynamic image and a fusion device of the infrared image and the visible light dynamic image and belongs to the image processing field. The image fusion method comprises calculating an image registration parameter; collecting the infrared image and the visible light image respectively and carrying out image registration to the infrared image and the visible light image according to the image registration parameter; and carrying out image fusion to the infrared image and the visible light image after the image registration are carried out to the infrared image and the visible light image. Due to the fact that in a image fusion process of the infrared image and the visible light image, the image registration is achieved according to the image registration parameter, the calculated amount of numerical value change is decreased greatly, calculating speed is improved, and further speed of the image fusion is improved, and real-time requirements of image processing are met.