66 results about "Contour tracing" patented technology

A fully automated package identification and measuring system, in which an omni-directional holographic scanning tunnel is used to read bar codes on packages entering the tunnel, while a package dimensioning subsystem is used to capture information about the package prior to entry into the tunnel. Mathematical models are created on a real-time basis for the geometry of the package and the position of the laser scanning beam used to read the bar code symbol thereon. The mathematical models are analyzed to determine if collected and queued package identification data is spatially and/or temporally correlated with package measurement data using vector-based ray-tracing methods, homogeneous transformations, and object-oriented decision logic so as to enable simultaneous tracking of multiple packages being transported through the scanning tunnel.

The invention relates to the technical field of navicular identification, in particular to a method and system for navicular identification based on interest target regions and SUSAN (Small Univalue Segment Assimilating Nucleus) edge detection. The navicular identification method comprises the following steps: S1, converting an image to be identified into a gray level image; S2, extracting an interest target region from the gray level image; S3, utilizing a SUSAN operator to perform edge detection on the interest target region to obtain edge information, and performing target contour tracing on the edge information to form an shape of the target to be identified; S4, obtaining shape context of the shape of the target to be identified; S5, matching the shape context of the shape of the target to be identified with shape context of the shape of a template, and determining whether the target to be identified is the navicular identification. The method solves the problems of identification of a navicular object on an ocean surface scene and difficulty in navicular identification for on-board cargo, and can be widely applied to monitoring of exploitation of marine resource, thereby satisfying the requirements of fishery administration.

The invention discloses a non-contact type automatic blood pressure measuring system. Blood pressure of a measured person is measured by video recording. The non-contact type automatic blood pressure measuring system comprises a video acquiring module, an ROI extracting module, a pulse wave signal generating module, a filtering and noise reduction module, a waveform analyzing module and a blood pressure value calculating module. An automatic blood pressure measuring method comprises the following steps of acquiring a video of a finger tip; positioning the position of a tracked finger by using contour tracing of the finger tip; acquiring images of the finger; performing primary color separation and ROI segmentation on the images of the finger; respectively taking all pixel mean values of the filtered images as feature values to generate two time-varying pulse wave signal waveforms; performing comparison analysis on the two pulse wave waveforms to obtain transmission time of pulse; calculating the wave velocity of the pulse waves along an artery according to an image center distance d; and calculating a blood pressure value by using a conversion relation between pulse wave velocity and blood pressure. By using a noninvasive and non-contact type remote physiological signal detecting method, interference of motion artifact in a video record is overcome, the measuring precision is high, and blood pressure of a plurality of persons can be measured simultaneously.

A contour detector detects the contour of a specific tissue based on ultrasonic image data having been acquired in a predetermined time phase. A contour tracking part obtains the position of each of points composing the contour of a specific tissue in ultrasonic image data having been acquired in each time phase, by pattern matching for each time phase. A computing part obtains motion information indicating the motion state of a specific tissue in each time phase, based on the position of each of points composing the contour in each time phase. A display controller controls a display to display an ultrasonic image based on ultrasonic image data having been acquired in each time phase, for each time phase. Furthermore, the display controller controls the display to display the motion information in each time phase, on each occasion of each time phase.

Provided are a gradient wear-resistant coating and a method for preparing the same. Co50+0.15% CeO2 powder, Co50+0.25% CeO2+6% Ni/Wc powder and Co50+0.4% CeO2+12% Ni/WC powder are used for preparing the gradient wear-resistant coating with the structure of a bottom layer, a transition layer and a wear-resistant layer on the surface of a workpiece in a coaxial powder supply manner and a laser cladding manner, and the wear resisting performance of the work surface of a part is improved. An ultrasonic vibration device and a contour tracing electromagnetic induction heating device are adopted in the cladding process. Ultrasonic oscillation of a certain degree is applied to the area close to a cladded area of the workpiece, the grain size of a cladding layer can be remarkably refined, residual stress can be remarkably eliminated, and therefore generated cracks are reduced, and a cladding layer structure with good performance is obtained. The contour tracing electromagnetic induction heating device can be utilized for effectively reducing thermal stress brought by the temperature gradient of the cladding layer and relieving the cracking tendency. According to the technological parameters of the ultrasonic vibration device, the work frequency ranges from 10 kHz to 20 kHz, the maximum output power is 1,000 W, and the pneumatic pressure ranges from 0.3 MPa to 0.6 MPa. According to the technological parameters of the contour tracing electromagnetic induction heating device, the voltage is 380 V, the frequency is 60 Hz, and the heating temperature ranges from 150 DEG C to 1,000 DEG C.

The invention relates to an automatic registering method of visible lights and infrared images based on polygon approximation of a contour, belonging to the field of multi-source image registration. The method mainly comprises the following five steps: I, applying an edge detection operator and contour tracing algorithm to extract a main contour of an image; II, carrying out polygon approximation on the extracted contour; III, matching the fitted contour and selecting control points; IV, selecting an image transformation model and estimating transformation parameters; and V, carrying out corresponding transformation and interpolation operation to input images according to the transformation parameters. The method provided by the invention is high in registering precision and fast in speed and can effectively solve the automatic registering problem of visible lights and infrared images under rigid body transformation.

The invention discloses an active contour tracing method based on superpixel. The method comprises the following steps of carrying out the superpixel segmentation on a training image to obtain a training sample pool of a target and a background, adopting a measuring learning method to obtain a distance measuring projection matrix according to a training sample, establishing a judgment-type appearance model, carrying out the superpiexel segmentation on each frame of test image of a sequence image, obtaining a confidence diagram corresponding to the test image according to the established judgment-type appearance model, obtaining a speed field of the test image, substituting the speed field into an evolution equation of a level set method, and obtaining a contour trace result of the test image. Compared with the prior art, the contour evolution efficiency of each frame of test image can be improved, and the tracing accuracy and tracing efficiency of the sequence image can be improved.

The invention discloses a TR element locating and defect detecting method based on vision and relates to a TR element vision locating and defect detecting method based on the vision. The TR element locating and defect detecting method based on the vision solves the problems that in the prior art personal errors exist, the precision is low, the real-time performance is poor, and the calculation result is sensitive to illumination. The TR element locating and defect detecting method based on the vision is achieved through the steps that an area image is binarized, an outer boundary point set is extracted, an effective boundary point set is searched, a minimum enclosing rectangle is searched, the effective boundary point set is classified, affine transformation is conducted on the binary image, the type of the TR element is checked, the effective boundary point set is classified again and numbered, a pin straight line is fitted, a pin foot straight line is fitted, TR element detailed information is determined, and the defect of the pin of the TR element is checked. The method comprises multiple technologies including grey value filtering, four-field rapid contour tracing, the dual axial rotation method searching the minimum enclosing rectangle and other innovative technologies. The TR element locating and defect detecting method based on the vision is mainly applied to element locating and detection fields in a chip mounter vision system.

The invention discloses an image processing-based bottled liquid impurity detection system and a detection method thereof. The detection system consists of a mechanical part and a machine vision part; the mechanical part comprises a step motor, a conveyer belt, a fixed pulley and a mechanical clamping device; the machine vision part comprises a camera obscura, a related internal structure, a FPGA (Field Programmable Gate Array) board, a serial communication port, a display module, an alarm module and upper computer software. The detection method of the system is as follows: an image is acquired; the image is segmented from the background by the seed fill algorithm; salt and pepper noises and interference pixels are filtered by fuzzy processing; contrast is increased by binarization processing; the image is connected completely by erosion and dilation operation to remove tiny noise, so that impurities become visible; finally, contour tracing and extraction are carried out to obtain the number, shapes and positions of the impurities. The invention increases image acquisition and processing speed, consequently, manual detection can be replaced, and the purpose of increasing detection speed, quality and production benefit is achieved.

A charged insulator string icing bridging degree intelligent image analysis method comprises the steps of converting an original image from an RGB color space into an HIS color space, and describing color features thereof; acquiring double-umbrella insulator segmented images; determining an insulator icing region, and acquiring a color feature, a gray feature and a texture feature of an icing insulator; constructing a multi-class SVM classifier, and using the multi-class SVM classifier for training sample classification; automatically detecting disc diameter endpoints of a double-umbrella insulator by combining a defect compensation algorithm and a redundant point deletion algorithm; automatically matching the disc diameter endpoints of the double-umbrella insulator; and screening the disc diameter endpoints of the double-umbrella, determining a contour tracing starting point, and completing the calculation of icing bridging percentage of the double-umbrella insulator. Through the icing bridging percentage intelligent analysis of a double-umbrella suspension insulator image, the invention effectively overcomes the defect of the loss of effective information due to traditional image segmentation.

The invention discloses a pointer type instrument number reading and recognition method and a system. The pointer type instrument number reading and recognition method comprises steps of adjusting relative positions of an image collection recognition device and the instrument to be read, obtaining an accuracy current image of a dial plate area of the instrument to be read, and determining the dial plate area on the collected image without using the complicated image analysis technology like the contour tracing. The invention reduces the calculated amount, and improves the recognition efficiency. Furthermore, the invention performs recognition processing on the collected current image through the recognition module of the image collection recognition device without transmitting the collected image to the computer to process, eliminates the data transmission time and further improves the recognition efficiency.

There is provided a method of processing an ultrasound spectrum image. According to such method, a spectrum image is formed based on ultrasound data and then the noise is removed from the spectrum image. The noise-removed spectrum image is matched with one or more spectrum models representing specific spectrum types. Then, whether or not the noise-removed spectrum image contains an aliasing is checked. If the noise-removed spectrum image contains the aliasing, then the aliasing is removed from the noise-removed spectrum image to provide a noise-removed spectrum image without the aliasing. Thereafter, contour tracing is performed on the noise-removed spectrum image without the aliasing to detect contour points. Further, peak tracing is performed on the noise-removed spectrum image without the aliasing to detect peaks.

The invention provides an anti-interference contour tracing method based on prior model constraint. The method comprises the following steps: establishing an initial prior model of a video image to be traced as a target model by using an SLIC algorithm and a mean shift clustering algorithm; carrying out level set evolution on a current frame of image by target feature distribution of the target model; determining a target region of the current frame of image by the SLIC algorithm and the mean shift clustering algorithm; and updating the prior model according to an occlusion condition of the current image. By the method, interference of non-target information in the image in an image tracing process is removed, so that description of the prior model to a target is accurate. Accuracy of the model is guaranteed.

The invention discloses a method for realizing clothes style identification and recommendation based on clothes contour and shape tracking. The method comprises the following steps: 1) through an pictures recognition color separation dictionary, carrying out color marking processing on clothes pictures to obtain processed clothes filled pictures; 2) through the pictures recognition color separation dictionary, carrying out recognition processing on the clothes pictures processed in the step 1) to realize corresponding marking of the clothes types; 3) carrying out contour tracing on the clothes pictures processed in the step 2) to obtain contour feature values of the clothes; and 4) according to contour match, carrying out clothes recommendation on the clothes pictures processed in the step 3) and the clothes type marks obtained in the step 2) based on association rules. For the defects in the smart costume matching field, the method can realize costume matching recommendation from the perspective of clothes type and clothes version joint analysis, thereby realizing intelligent recommendation without manual intervention.

The invention provides a method for colorizing a vehicle-mounted infrared video quickly, which obtains contour regions of object categories in each frame by tracing contour feature points, and transfers colors to each region by category feature colors. The method comprises the steps of: first constructing a feature color collection of scenery samples by the feature color of each scenery category represented in a natural color image; next clustering infrared key frames by an improved and effective method of K-Means to obtain segmenting regions and to extract contour feature points; then tracing the feature points through a KLT algorithm to obtain locations of the feature points in the next frame and to correct at the same time, and restoring the contour by adopting a technique of B-spline interpolation to obtain the contour regions of each category of the frame; and finally endowing the distinguished category regions of each frame with the feature colors according to the categories, so that the object is colored by suitable colors and a quick colorization of infrared video sequence is realized. Experimental results show that the method of the invention improves the processing speed and can receive a satisfactory result.

The invention discloses an expansion target stable trace point extraction method which comprises the following steps of: firstly, recovering the expansion target successfully identified by early association into a binary image; then, performing contour tracing to obtain the contour point array arranged in order; smoothing the target contour by use of a method based on chord-arc ratio filtering, removing the sharp arc section on the target contour, and linearly connecting two endpoints of the removed arc section to form a new closed contour after filtering; calculating the head direction of the target by combining the target motion direction and the main shaft direction, and then obtaining the forefront point in the head direction of the target; and calculating the centroid in the local round area as a trace point by taking the forefront point as the center. Through the method, the finally calculated target trace point is stable and reliable, severe shake is avoided, the tracing stability is improved, and the risk of tracing loss is reduced.

A system and process of nearsighted (myopia) camera object detection involves detecting the objects through edge detection and outlining or thickening them with a heavy border. Thickening may include making the object bold in the case of text characters. The bold characters are then much more apparent and heaver weighted than the background. Thresholding operations are then applied (usually multiple times) to the grayscale image to remove all but the darkest foreground objects in the background resulting in a nearsighted (myopic) image. Additional processes may be applied to the nearsighted image, such as morphological closing, contour tracing and bounding of the objects or characters. The bound objects or characters can then be averaged to provide repositioning feedback for the camera user. Processed images can then be captured and subjected to OCR to extract relevant information from the image.

The invention discloses an eight-point method-based contour-line tracing algorithm. Topographical feature influence factors in reality are blended; when a contour line comes across an exit selection condition, eight-point method expansion and judgment can be carried out; after current regional topographical features are judged, tracking exit acceptation or rejection is carried out, so that the contour line is prevented from tracking a wrong exit, the contour line does not cut apart a large landform, and does not generate a wrong small circle in valley and ridge areas; finally the contour line can restore the real topographical features; a drawn contour line map is relatively beneficial to simple and intuitive comprehensive analysis. The eight-point method-based contour tracing algorithm is widely applied to the geoscience fields such as building of a hydrological model, terrain simulation, surveying and planning of roads and railways, and natural resource management; a plurality of advantages are shown; the algorithm is simple and clear, and is convenient to process by virtue of a computer; the contour line, the slope and the gradient can be easily calculated; the terrain is automatically extracted.

The invention relates to artificial intelligence, and provides a video data processing method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a target data set and a to-be-processed video set; extracting at least two video frame images from each original video; enabling the image recognition model to perform image binarization processing, edge detection processing and contour tracking processing on the video image; obtaining a license plate area, a human face area and a human body feature area, extracting text features of the license plate area through a character segmentation algorithm, obtaining a license plate number result, extracting human face features of the human face area through a YOLO algorithm, obtaining a human face result, extracting human body posture features of the human body feature area through a chain code curvature algorithm, and obtaining a human body feature result; determining an identification result; extracting a matching fragment; and performing splicing to obtain a video synthesis fragment, and performing sorting to obtain a target video. In addition, the invention also relates to a blockchain technology, and the target data set can be stored in the blockchain node.

A bicycle disc brake rotor basically has an outer portion, an inner portion and an intermediate portion. The outer portion is made of a first material. The inner portion is made of the first material. The intermediate portion is disposed between the outer portion and the inner portion. The intermediate portion is made of the first material. The intermediate portion is at least partially laminated by a layer made of a second material. The second material is different from the first material. The layer has a contour tracing a contour of the intermediate portion.

A cancer therapeutic window evaluation method is provided. In some embodiments, the method may comprise: detecting tumor oxygenated perfusion by having a patient breathe air to acquire MRI baseline data; inhalation of hyperoxia gas to generate higher than baseline HbO₂ blood circulating in body to acquire MRI enhanced data; the region-of-interest (ROI), which in this case is a tumor volume (V₀), and which may be performed by volume contour tracing/region-of-interest (ROI) analysis and 3D tumor volumetry methods; calculating voxel's enhanced signal intensity (ΔSI); calculating tumor oxygenated perfusion percentage (OPP %); selecting different threshold and calculating maps such as a reconstruction OPP % pseudo color map; calculating tumor volume change ratio (Vt %); overlaying reconstruction OPP % pseudo color map to original images for visualizing tumor response data; drawing or plotting the OPP % and Vt % may on a cancer treatment evaluation diagram, and calculating risk/benefit analysis based on pooled collected data.