3748results about How to "Detection speed" patented technology

The invention relates to a night preceding vehicle detection method based on a millimeter-wave radar and machine vision, which belongs to the field of vehicle control. The night preceding vehicle detection method comprises the following steps: (1) performing camera calibration, so as to obtain a projection matrix of world coordinates to image pixel coordinates, establishing a transition relation between a radar coordinate system and a world coordinate system, and converting radar coordinates into the image pixel coordinates; (2) resolving received millimeter-wave radar data, excluding false targets and determining effective targets through data processing, and synchronously collecting camera images; (3) projecting radar scanning points under the world coordinate system to an image pixel coordinate system, and establishing an region of interest (ROI) on the images according to projective points; (4) detecting whether a vehicle exists in the region of interest based on an image processing method. Compared with the prior art, the night preceding vehicle detection method has the characteristics of fusion of the millimeter-wave radar and the machine vision, high real-time performance and high accuracy.

The invention discloses a vehicle detection method based on a convolutional neural network. The method includes the step S1 of collecting vehicle samples and non-vehicle samples and classifying the vehicle samples, the step S2 of preprocessing the samples, the step S3 of training a CNN vehicle detector, the step S4 calculating an average similarity table of a characteristic pattern, the step S5 of constructing a similarity characteristic pattern set, the step S6 of obtaining a CNN-OP vehicle detector, the step S7 of obtaining detection images, the step S8 of preprocessing the obtained detection images, the step S9 of constructing an image pyramid for the detection images, the step S10 of extracting characteristics, the step S11 of scanning characteristic patterns, the step S12 of classifying the characteristics, and the step S13 of combining detection windows and conducting output. An offline optimization scheme is put forward, the convolutional neural network which is completely trained is optimized, the strategy of scanning the windows after extracting the characteristics is adopted at the detection stage, and therefore the characteristics are prevented from being repeatedly calculated, and the detection speed of the system is increased.

The invention relates to a mobile phone casing defect detecting method based on depth learning. The method comprises the steps that (1) the image of a mobile phone casing to be detected is acquired and pre-processed; and (2) the pre-processed image is input into a pre-trained defect detection model for defect detecting to acquire the position of a defect on the mobile phone casing, and the confidence of the position as the defect is provided. The defect detection model is a depth network based on depth learning, and comprises a feature extraction network and a classifier and regression device network, wherein the feature extraction network and the classifier and regression device network are in successive cascade. The feature extraction network carries out feature extraction on the pre-processed image to acquire a feature image. The classifier and regression device network classifies and regresses the feature image to acquire the defect position and the confidence of the mobile phone casing. Compared with the prior art, the method provided by the invention has the advantages of high detection precision and accurate and reliable detection result.

The invention relates to one digital mobile communication technique suitable for one transmission base station monitor method and system based on wireless mobile terminal, which uses GSM communication network short message channel to sort monitor data and to transmit on focus degree, wherein, the alarm information and inquire information send by real time and the operation information without alarm sends method and process technique to form alarm guide base station monitor system by network monitor center, base station and other human cell phone network.

A real-time visual detection and identification method for high speed rail surface defects comprises the following steps of: (1) image acquisition; (2) image preprocessing; (3) defect preliminary detection, that is, performing logic or operation combination of detection results based on gray scale compensation with detection results based on top-hat operation, and detecting whether an abnormal area exists in an image, if not, finishing the detection, or else continuing the processing; (4) defect accurate positioning, that is, accurately positioning the defect by an algorithm of bonding single defect, an algorithm of filling holes in the defect area, and an algorithm of selecting the main defect, and extracting the defect area through marks; (5) defect classification, that is, extracting and selecting characteristics of the defect area, designing and training a BP neural network, and classifying the defects by the BP neural network. The invention has the advantages of simple principle, high automation degree, high detection speed, and high detection precision.

The invention relates to a driver fatigue detection method based on face video analysis, belonging to the field of vehicle active safety and mode recognition. The method comprises the steps of: carrying out face detection on a face image to be detected for primarily positioning local organs, such as eyes, nose and mouth; further obtaining face characteristic points positioned accurately; and finally, on the basis of an accurate positioning result of multiple frames of face characteristic points to be detected, carrying out quantization description on a face motion characteristic, and obtaining the result of fatigue detection on a driver to be detected according to a face motion statistical indicator. The driver fatigue detection method has high reliability, has no special requirements on hardware, does not involve complex operation, and has good instantaneity so as to be applied in real time in practice. The driver fatigue detection method has better robustness on the aspects of eyeglasses wearing, face angles, nonuniform illumination and the like, and can be suitable for various types of vehicles for reminding a driver of being in a fatigue state so that traffic accidents are avoided.

The invention relates to a nondestructive detection method for tea quality based on a near infrared spectrum and a machine vision technology and a device thereof. The detection method comprises the following steps: spectrum and image acquisition to tea are synchronously performed, obtained initial data are subjected to preprocessing, feature extraction and fusion, and then an expert evaluation result is combined to establish a quality grade evaluation model of the tea to quickly and nondestructively detect the comprehensive internal and external quality of the tea. The detection device comprise a spectrum acquisition device, an image acquisition device and a computer, wherein the spectrum acquisition device and the image acquisition device finish the signal acquisition of a tea sample and then transfer a signal to the computer; and the computer finishes the extraction and fusion of feature information, and then substitutes in the pre-established model to judge a final result of the quality of the tea. The method applies a fused nondestructive detection means based on the two technologies to the detection process of the comprehensive quality of the tea, has the advantages of high detection accuracy, good result consistency, strong automation degree and so on, and creates conditions for standardized classification of the quality of the tea.

The invention discloses a method for quickly and accurately detecting and tracking a human face based on a video sequence, which relates to the technical field of mode identification. The method comprises the following steps of: 1, extracting a video frame image from a video stream; 2, preprocessing the video frame image, namely compensating light rays, extracting skin color areas, performing morphological processing and combining the areas; 3, detecting the human face, namely representing the human face by using Harr-like characteristics and detecting the human face by using a cascaded Adaboost algorithm with an assistant decision function; 4, establishing the characteristics of the human face, namely detecting the area characteristics of the detected human face and the shape characteristics of the edge profile of the human face; 5, tracking the human face, particularly tracking the human face by using a human face area characteristic model when an intersection does not occur in a human face area, and further matching when the intersection occurs according to the shape characteristics of the edge profile of the human face; and 6, extracting the sequence of a human face image. By the technical method, the human face can be detected and tracked quickly and accurately on the basis of the video sequence.

The invention discloses a method and a device for detecting a text area in an image and an electronic device. The method comprises steps: a candidate text line area image is extracted from a target image; a depth study text/non text classifier through training is adopted to judge whether a sub area in the candidate text line area image is a text area, and a sub area which is judged to be the text area is marked; and sub areas marked as the text areas are combined, and a text area for the target image is acquired. The method provided by the invention can be applied to text area detection on different types of images, different languages and different styles of fonts, and the technical scheme has universality; the text line area diversity adaptability ability and the anti-noise interference ability are improved, and the detection result accuracy is ensured; and the classifier judgment areas are greatly reduced, and the detection speed is improved.

The invention relates to an enzyme-linked immune analysis method and a fully-automatic enzyme-linked immune analyzer. The analyzer comprises a rack component, a washing component, a sample adding/reagent adding component, a heating and temperature control component, a fluid path system, an input and output device, an optical measurement component and a control system, wherein the rack component comprises a rack soleplate; a pillar is arranged on the rack soleplate; a lower fixed plate and an upper fixed plate are arranged on the pillar from bottom to top in sequence; a circular reaction plate is arranged between the lower fixed plate and the upper fixed plate; the circular reaction plate is connected with the upper fixed plate and the lower fixed plate through a central shaft; a first motor is fixedly arranged at the lower part of the lower fixed plate; and the first motor is used for driving the circular reaction plate to rotate through a first transmission mechanism. When in use, the enzyme-linked immune analysis method and the fully-automatic enzyme-linked immune analyzer can carry out the detection of corresponding projects without wasting reagent through only one sample; and detection reagents need not to be respectively contained in different reagent bottles, so that the operation is very convenient, and the operation error is not easily caused, thereby ensuring the accuracy of the detection results.

The invention discloses a method for quickly measuring a blade of a large-sized water turbine, which is characterized by comprising the following steps: firstly, sticking a mark point to the surface of the blade, then shooting a group of photos from different angles as measured primary data, and inputting the data to a computer to carry out analytic processing; by carrying out image detection for the group of photos in a measurement software, identifying the mark point in each photo and positioning the center of the mark point, and matching the mark points with the same name; finally, reconstructing a three-dimensional coordinate of corresponding object points according to a plurality of two-dimensional coordinates of the mark points, fitting a sparse framework model of a target by the reconstructed three-dimensional mark points, then scanning the surface of the blade block by block by using a binocular grating scanning method to acquire a local dense point cloud, and aligning the dense point cloud to an overall coordinate system according to the local mark points to acquire a dense point model of the blade; and by comparing the dense point model with a CAD designed model after aligning, calculating a three-dimensional processing error of the surface of a workpiece.

The invention relates to an online automatic detection method of fabric defects based on machine vision and a device thereof, wherein the clear and integral standard fabric images without the defects of the fabric are shot on a batching and burling machine as a standard image template by utilizing an industrial camera in order to solve the problems of great labor intensity and poor detection quality of the traditional manual detection method; the corresponding characteristic parameters are extracted and stored into a computer; the range of the fabric defect detection characteristic parameters is set according to the requirements of users; the fabric images which are shot in real time are transmitted to the computer to be compared with the standard image template by utilizing the industrial camera and compared with the standard characteristic parameters; if the fabric characteristic parameters are not in conformity with the set requirements, the alarm is started by detection software; the defects are analyzed; and the printing of defects labels is executed. The invention has the advantages of high detection accuracy and high speed; and the labor intensity is greatly reduced.

The invention provides a vehicle license plate recognition method, and relates to a method for image recognition. The method comprises the following steps of preprocessing an image; partitioning a vehicle region according to color and texture characteristics; extracting a remarkable factor graph of a vehicle region diagram; extracting candidate vehicle license plates by an Adaboost classifier based on expanded Harr-like characteristic; determining the position of a real vehicle license plate from the candidate vehicle license plates; partitioning the marked vehicle license plate from the corresponding vehicle region original diagram; carrying out character segmentation according to structural characteristic; and carrying out character recognition based on the improved template matching method. With the method provided by the invention, the defects that the application scene of the traditional vehicle license plate recognition method is relatively single, some traditional vehicle license plate recognition methods are only suitably used for single vehicle license plate recognition of the single scene and difficultly used for multiple-vehicle license plate recognition of multiple scenes, and the recognition rate is easily affected by strong light, haze and weak light environments are overcome.

The invention relates to a laser detection device and method for gear parameters. The laser detection device is characterized in that a worktable is provided with an internal point; a laser displacement sensor is arranged on a bracket; the bracket is arranged on a linear motor sliding block of a sliding table; the sliding table is arranged on an angular displacement rotating system and is fixedlyconnected to a rotating disk together with a rotating shaft; a casing of the angular displacement rotating system is arranged on a lifting arm through screws; the lifting arm is connected with the vertical surface of a machine body through a high-precision linear guide rail and a sliding block; a servo motor drives a ball screw which is fixedly connected to the vertical surface of the machine body to rotate; and a data acquisition and communication system is arranged on a rotating shaft upper plane of the angular displacement rotating system. Tested workpieces are subjected to data measurement, acquisition, transmission, reconstruction, separation, comparison and display to finish the full process of detection. According to the laser detection device and method, the non-contact and blind spot-free measurement is realized, the detection speed and measurement precision are improved; the difficult problem that a pinion is difficult to detect is solved; and in the measuring process, the gear is stationary and a measuring head does measuring movement, thus the measuring error caused by mounting the gear is reduced.

The invention provides an MS-KCF (MobileNet-SSD-kernelized correlation filters) based rapid and stable detection method of a human face in an image sequence. To solve the problem about detection of the human face with larger angle change and very severe shielding in the image sequence, a new automatic DTD (detection-tracking-detection) mode integrating rapid and accurate target detection model MSand rapid tracking model KCF is provided, that is, an MS-KCF human face detection model is provided. The method comprises steps as follows: S1, establishing an MS detection network; S2, detecting a target by use of the MS network; S3, updating the tracking model to predict the position of the next frame of human face target; S4, updating an MS detection network after tracking several frames, and performing redetection and positioning on the human face target; S5, comparing and analyzing experiment results. Experiments prove that the MS-KFC model guarantees the detection stability of the humanface with larger angle change and very severe shielding in the image sequence, and besides, the detection speed is greatly increased.

The invention discloses a full automatic biochip detection system belonging to the clinical detection field of multi-marker biochips. The system adopts modular structure and comprises an automatic sample processing module, a reaction washing module, a detection module, a Tip head storage module, a reagent storage module, a biochip storage module, a sample storage module, a system base, an electric control box and a computer, the electric control box and all the modules are operated under the control of software, so as to realize the automatic sampling, the sample adding, the reaction, the washing, the detection and other processes. All the modules can work independently and can also be combined together and matched for work. The full automatic biochip detection system can overcome the shortcomings of the existing biochip detector and reduce the errors caused by human operation, and has stable and reliable detection result and good flexibility, so that the full automatic biochip detection system can not only greatly improve the detection efficiency, but also can be conductive to the accuracy of the detection result; the system has simple operation, therefore, the system is not only applicable to the scientific research and the applications of laboratories and hospitals, but also can be used for large-scale sample screening of large-scale hospitals and blood stations.

The invention relates to the technical field of face recognition, in particular to a rapid detection method of a face in a high-resolution color image under a complex background. The invention comprises the following steps: building a face skin color mixed model which is composed of two color space restrictions of RGB and YCbCr according to a large amount of acquired skin color sample data to determine the skin color pixel; rapidly skipping non-face regions by adopting a whole skin color pixel ratio to improve the location efficiency of a face candidate region; then using the improved face rapid detection algorithm which is based on forward characteristic selection to realize face preliminary judging of the face candidate region; and finally utilizing a false alarm restraining method which is based on space restriction and geometric restriction to further lower false detection rate and complete face detection. The invention can realize rapid location of a plurality of frontal faces in images at a high detection rate under the condition of low false alarm rate; the good performances of the invention are proved by the results of the test set of Bao open database and a plurality of video frequencies and high resolution color images.

An exercise repetition sensor comprises an electricity generator, such as an electricity generator, which is coupled to an exercise system, where the electricity generator is capable of sensing exercise movements of any size or intensity on the exercise system. The electricity generator can be based on a number of electrical, magnetic, or optical sensing principles. For example, an electricity generator comprising an electricity generator includes a spindle that is coupled to one or more parts that move in proportion to an applied force. The voltage-generator generates an electrical current as the spindle moves, and sends the electrical current to an electronic display interface. In one embodiment, the voltage-generator sends a positive direct current through one of two circuit wires to the electronic console, such that the electronic console can immediately identify that the user has performed an exercise repetition.

A full-face vehicular detection method for a railway tunnel lining and a device aim to avoid collision of ground penetrating radar antennas with an overhead line system and a support of the overhead line system, the detection speed is a normal running speed of a train, the antennas in full-face detection are not interfered with each other, automatic positioning is realized during detection, only ground penetrating radar signals in a tunnel need to be acquired, and a penetrating radar signal processing and analyzing method in tunnel detection is modified. The vehicular device comprises a six-channel high-speed scanning penetrating radar, a positioning portion, a laser ranging portion and data acquisition and processing software. The pulse repetition frequency of the ground penetrating radar is 3MHz, the pulse repetition frequency of each channel is 500kHz, and the scanning rate is 976scan/s. The ground penetrating radar is provided with TEM (transverse electric and magnetic field) short-horn air coupled antennas, each group of antennas realizes a double-transmission and single-receiving function, and the center frequency of the antennas is 300MHz. The ground penetrating radar antennas are mounted outside passenger train connectors, radiation surfaces of the antennas respectively face to an arch crown, arch springing and side walls, and the full-face vehicular detection method and the device are used for automatically detecting to exam the railway tunnel lining.

The invention provides a multi-direction ship target detection and identification method in a high-resolution remote sensing image. The method is characterized by designing and realizing a multi-direction ship target detection and identification network structure under a complex scene and in a large-scale environment; automatically exploring shallow-layer and deep-layer multidimensional features and the like of a ship target based on a convolutional neural network; and realizing quick and accurate detection and recognition of multi-directional, and different scales and kinds of ship targets inthe high-resolution remote sensing image under a small sample environment. Compared with a conventional target detection method, the method is faster in detection speed and more accurate in detectionresult.

The invention discloses detection equipment and a detection method. The detection equipment comprises a sampling device used for collecting a sample to be detected, a preprocessing sample injection device used for preprocessing the sample from the sampling device, and a sample analysis device used for separating the preprocessed sample from the preprocessing sample injection device and analyzing the separated sample. The detection equipment is miniaturized, can quickly and accurately detect gas-phase matters or particulate matters without unpacking, and is high in accuracy and suitable for security check of airports, ports, metro stations and the like.

The invention discloses a product detection method based on machine vision. The product detection method can achieve automatic detection of product defects by use of machine vision and template matching, locate the coordinates of defective products, control a mechanical arm to grab the unqualified products and to place the unqualified products in a disqualification area by a data acquisition card, and convey products passing through detection to the next workstation by a production line. The product detection method can achieve subtle high-precision detection of missing, deflection and parameter errors of such electronic components as resistors on a PCB, as well as status disqualification of a dial switch; through edge grabbing arrangement of the six-degrees-of-freedom mechanical arm, the detected unqualified products are automatically grabbed away from the production line to realize automation of the whole process; and in combination with matching and high-precision location of edge detection, the approximate positions of the products are found by matching at first, then the pixel coordinates and the angle of a corner of each cuboid product are determined via detection of two edges, the unqualified products are automatically grabbed out, and the product detection method is suitable for detecting different products.

The invention provides a multi-type workpieces batch visual measuring system and a method, and belongs to the field of industrial detection automation. The measuring system comprises a data processingterminal, a workpieces detecting unit, an image acquiring unit, a control unit and the like. The measuring method comprises the following steps of: judging whether the to-be-detected workpieces are put into a detecting platform or not; obtaining a local depth image; obtaining a global image; identifying the type and number of the workpieces; and completing the size parameter measurement requiredby the measurement task. According to the multi-type workpieces batch visual measuring system and method, multiple kinds and multiple workpieces can be simultaneously detected at the same time; compared with traditional measurement means, the type and quantity of the workpieces, speed and accuracy and the like in measuring are significantly improved.

The invention relates to impulse response analytical test apparatus and method for detecting deformation of transformer winding, belonging to the technical field of transformer winding detection. The apparatus mainly comprises an impulse generator, a broadband digital oscilloscope, a computer, a high-voltage probe, a head end signal impedance matching device, a tail end signal impedance matching device and a screened coaxial cable. In the method, site test and analysis are carried out by using the apparatus. The invention has the advantages of high test sensitivity, rapid detection, strong capacity of resisting disturbance and flexible analytical method, and can detect slight deformation of the transformer winding and judge early potential faults effectively with high judging accuracy. The invention can be widely applied to the detection of the deformation of the transformer winding and the state overhauling.

The invention discloses a pedestrian flow monitoring method based on pedestrian detection and tracking. The method includes: acquiring and decoding a camera video stream to obtain single-frame RGB images, performing pedestrian detection on each image frame to obtain a group of pedestrian positions, calculating similarity, matching the pedestrians of every two adjacent image frames so as to track the pedestrians and obtain motion trajectory of each pedestrian, setting detection lines in the monitoring video, and judging pedestrian flow in different directions through the obtained pedestrian trajectories. The method is based the latest developments of pedestrian detection in computer vision, high in detection accuracy, fast in detection and promising in development prospect. By combining the method with a fast tracking method based on similarity and using a multi-scale detection method from sparsity to density, detection speed is further increased, fast pedestrian tracking is realized, detection and tracking speed can reach 10FPS on a current common computer, and practical level is reached.