1818results about How to "Avoid missing detection" patented technology

The embodiment of the invention relates to a quick barrier detection method. The method comprises the steps that a two-dimensional grid map is established on the basis of point cloud data of a three-dimensional radar, the attributes of grids are calculated to determine impassable areas, points of which the scanning line gradient values exceed predetermined threshold values in the impassable areas are determined as barrier points, and correlation clustering is conducted on the barrier points by traversing the grid map.

The invention discloses an equipment and facility safety inspection intelligent patrolling operation system and an application method thereof. The system consists of a handheld wireless interconnection security patrolling device, a radio frequency identification (RFID) label card reader module and a central server, wherein a passive RFID label is distributed on a security facility in a closed space; the label number and three-dimensional (3D) virtual digital modeling data of the closed space are input into a computer system and / or a server by utilizing a global information system (GIS); when an inspector enters the closed space to inspect by carrying the handheld wireless interconnection security patrolling device; and identification codes stored in the passive RFID label, use informationof related security facility and equipment and location information thereof, and to-be-collected data which are collected by the security equipment through manual and automatic wireless sensing and collected by manual artificial detection are uploaded to the central server or transmitted to the computer system by the handheld wireless interconnection security patrolling device automatically, and are determined by the central server or the computer system. The system prompts and monitors the inspectors to maintain the security facility and equipment in time, so that the safety, effectiveness and reliability of the security facility and equipment can be improved.

The invention provides an electronic inspection system for troubleshooting safety production hidden danger. The system comprises a handheld terminal, a management server and an inspection plate, wherein the inspection plate adopts a two-dimensional code technology; the handheld terminal can scan two-dimensional codes to acquire information, perform image acquisition and inspector self-shooting evidence remaining on each inspection point site and report the data to the management server; the management server performs identity matching of the inspector and match inspection route and inspection time. According to the system, the problems that the inspector replaces a missing operator, has missing detection, takes time off and does not check according to the regulation and time and the like are properly solved.

The invention discloses a flexible general production line and a production method of an electronic product. The production line is characterized by comprising a main flow line and an intelligent control system of a flexible production line, wherein the main flow line comprises n independent functional module tables, at least one high-temperature aging table and a mobile conveying line; each functional module table has a same structure and comprises a scanner, a test part, a frock clamp operation part, a maintenance isolation part, a computer information system and a display; the high-temperature aging table comprises a high-temperature aging box body and a computer control system; and the computer information system of each functional module table and the computer control system of the high-temperature aging table are in two-way electric connection with the intelligent control system of the flexible production line respectively for information interaction, so intelligent control of the product in the whole production process is accomplished by verifying an identification code of each process of a produced target product and identifying whether the process is qualified. The functional module tables can be increased or decreased according to the type of the produced product, so that the formed production line is simple and convenient.

The invention belongs to the technical field of intelligent transportation, and relates to a front vehicle detection method based on monocular vision, which comprises the steps of: acquiring a vehicle front road condition original image, capturing a subimage, carrying out histogram equalization on the subimage, extracting a vehicle front road surface average gray threshold; obtaining a gray threshold by adopting an improved OTSU method; calculating a binarization threshold; estimating a binarization result, segmenting and reinforcing a target according to an estimation result; filtering; obtaining a key position line expressing a bottommost line in a vehicle bottom shadow, carrying out line fusion on the key position line, then extracting target information of an image to be used as a target result of a current frame; and matching the target result of the current frame with a target result of the last frame and information of a tracking target result, and carrying out classifying decision on the target result of the current frame according to a matching result, and determining a final detection result of a front vehicle of the current frame. The front vehicle detection method has the characteristics of good instantaneity, high detection accuracy rate and good robustness.

The invention relates to a squeal determining method and a squeal determining device. The method comprises the following steps: acquiring the current frame of a received audio signal; determining N sampling frequency points in the current frame according to preset sampling frequencies, wherein each of the N sampling frequency points corresponds to one frequency, and N is a positive integer greater than or equal to 2; determining the energy corresponding to each sampling frequency point; and determining squeal sampling frequency points in the current frame according to the energy corresponding to each sampling frequency point. According to the technical scheme, all potential squeal frequency points in an audio signal can be found comprehensively in the frequency dimension, no squeal sampling frequency point is missed, then, the continuity is analyzed on a possible squeal frequency point from the time domain, the duration of a high-energy signal of an audio frame where the squeal frequency point is located is judged to avoid misjudgment of the audio frame, and thus, comprehensive, accurate and fast detection of squeal in the audio signal is ensured.

The invention relates to the technical field of electronics and discloses a starting method and device of an application program. The starting method of the application program is applied to a mobile terminal, and comprises the following steps: binding fingerprint information which is obtained in advance with a pre-set shaking direction to form a fingerprint shaking combination; correspondingly binding the fingerprint shaking combination with the pre-set application program, and storing; when the mobile terminal is at a screen turned-off state or a screen turned-on and locked state, starting and identifying fingerprint information if a fingerprint identification module is pressed; if finding out fingerprint identification matched with the fingerprint identification identified by the fingerprint identification module from the pre-stored fingerprint shaking combination, detecting a shaking direction of the mobile terminal; and if detecting the fingerprint shaking combination comprises the identified fingerprint identification and the detected shaking direction, starting the application program bound with the fingerprint shaking combination. Therefore, the application program can be conveniently and rapidly started, the privacy of users is protected, the power consumption is saved and the user experience is improved.

The invention belongs to the field of internet of things and machine vision and discloses an urban expressway traffic real-time monitoring method based on an information physical network. The system realized the method comprises a video sensing unit, a video image processor and a network communication and traffic monitoring client. The system achieves accident detection based on a video transmission feedback control method through a road traffic parameter detection, traffic accident initial automatic early warning and traffic state quantization identification and by using of network communication, completes real-time monitoring on urban expressway traffic, improves real-time performance and an accuracy rate of an existing traffic accident detection method and adaptability on an emergent traffic accident, has stronger adaptive capacity on traffic states and environment, fully utilizes time and space information through a traffic abnormal predicting result fusing time and space on a decision-making level, and avoids traffic abnormal missing detection.

The invention discloses a pedestrian detection method. Multiple times of convolution and pooling are performed on an input image through the pedestrian detection method based on a convolutional neuralnetwork; the features of the original image are extracted so as to obtain the corresponding feature graph of the original image; the corresponding feature graph after zooming of the original image isapproximately calculated through the image feature pyramid rules; a candidate window is generated through a region proposal network RPN; a candidate proposal window is further selected and summarizedaccording to the pedestrian size distribution in the candidate window; the corresponding weight of different scales of pedestrian targets on different scales of images is trained by using the training data having the tag; and the classifier network is trained. The summarized candidate window is solved, and the confidence obtained through the classifier and the set threshold are compared and finalpedestrian detection judgment is performed. Heavy calculation amount of obtaining the feature graph through image zooming calculation can be avoided by application of the image feature pyramid, and detection is performed on different feature graphs by using the weighing mode of different weights so that misjudgment and leak detection caused by single feature graph detection can be effectively avoided.

The invention relates to a pressure pipeline ultrasonic internal detection automation device; a purpose comprises that the provided device can meet detection requirements of a larger-diameter pipeline and has the characteristics of high detection accuracy and high detection efficiency. The technical scheme comprises that the pressure pipeline ultrasonic automatic detection device comprises a pipeline crawling robot, a probe assembly device, encoders, centralizers, supporting frames, a phased array module device and an ultrasonic detecting instrument; the probe assembly device comprises a first annular phased array probe assembly, a second annular phased array probe assembly, a conical phased array probe assembly for detecting defects of inner and outer surfaces and an interior circumference, and corresponding probe holding devices; the first annular phased array probe assembly, the second annular phased array probe assembly and the conical phased array probe assembly are each composed of more than 3 of 128 array element phased array probes; ultrasonic waves emitted by piezoelectric crystal plates of the probe assemblies firstly pass through an annular concave lens and then scan circumferential pipeline walls.

The invention discloses a deep learning-based TFDS non-fault image detection method. The method comprises the steps of building a network model capable of synchronously detecting multiple regions and multiple types in combination with deep learning image classification and target detection technologies based on a deep learning theory; performing locating detection on regions of non-fault key parts in railway TFDS images by the model; judging the images, in which the regions of the non-fault key parts are not detected, as suspected fault images; and observing and detecting a small amount of the suspected fault images by human eyes of indoor train inspection personnel. According to the TFDS non-fault image detection method provided by the invention, a large amount of the non-fault images are filtered out and only a small amount of the suspected fault images are observed and judged by the human eyes by virtue of the deep learning technology; and the method can greatly reduce the workload and working intensity of the indoor train inspection personnel.

The invention discloses a detection method of electrocardiosignal R characteristic waves. A wavelet decomposition method for improving threshold value is carried out on collected electrocardiosignals to conduct filtering, then wavelet reconstruction protruding out of a QRS wave group is carried out, energy window conversion from time domain analysis to energy domain analysis is carried out, then a maximum value point is selected and optimized, and finally an wave selection is carried out according to R selection logics. The detection method uses multiresolution characteristics of wavelet analysis to decompose signals on different scales according to frequency to accordingly process the signals on the different scales in a targeted mode and increase algorithmic flexibility. The energy window conversion method is adopted to convert the signals from a time domain to an energy domain, effectively restrains interference of high-frequency noise and improves algorithmic stability. By means of wavelet reconstruction, the QRS wave groups are extracted, P waves and T waves serve as noise to be rejected, false detection caused by huge P waves and T waves in detection can be effectively avoided, and detection accuracy is improved.

The invention discloses a vehicle-mounted four-wire laser radar system and a circuit and a method thereof. The vehicle-mounted four-wire laser radar system mainly comprises a transmitting system, a receiving system, an optical system and a scanning system, wherein the transmitting system is combined with the scanning system; radar scanning is realized by a mode that a direct-current stepping motor controls a laser to rotate; and the laser is electrically connected with an external circuit through a mercury sliding ring, so the scanning system has a small volume. The vehicle-mounted four-wire laser radar system performs scanning by adopting four laser beams according to a laser pulse ranging theory; the detection distance is at most 200 meters; and the resolution is at most 10 centimeters. Therefore, the system has relatively high performance and precision, and is low in cost; and by combining system software, the vehicle-mounted four-wire laser radar system has functions of measuring a vehicle distance and a vehicle speed, retaining the vehicle distance, prewarning collision, automatically cruising, prewarning lane deflection and the like, so that the system assists in a driver to drive a vehicle safely.

The invention provides a small-diameter pipe inside weld surface defect identification device. The device comprises a computer, an industrial camera, an adapter, an industrial endoscope, a mobile portable light source, an endoscope fixing clamp and a pipe fitting to be detected. The industrial camera is connected with the computer. One end of the adapter is connected with the industrial camera, the other end is connected with the industrial endoscope, and the adapter can be used for acquiring weld images. The mobile portable light source is connected with the industrial endoscope and used for providing lighting inside the pipe. The endoscope fixing clamp is connected with the endoscope and used for center positioning, upward and downward adjustment and positioning and 360 degrees of rotation of the endoscope. Identification detection of the weld surface defects inside the pipe fitting to be detected is completed.

The invention discloses a remote sensing image change detection method based on multi-feature proof integration and structure similarity, comprising the following steps: A. data preparation: selecting remote sensing images to be carried out with change detection in different time phase and in the same spatial scope; B. feature extraction: respectively extracting features of textures, grads and edges of images in two time phases; C. structure similarity calculation: calculating the texture structure similarity, grads structure similarity and edge structure similarity of the remote sensing images in two time phases in a working window; D. basic probability assignment function determination: building basic probability assignment function (BPAF) of evidence theory based on texture structure similarity, the grads structure similarity and edge structure similarity; and E. forming evidence and obtaining change areas to realize change detection. The method carries out change detection based on the area statistic features of edges, texture sand grads of images and can effectively avoid detection miss and false detection caused by the change detection using single feature; and the algorithm has robustness.

The invention provides a vehicle control method and system. The vehicle control method comprises the steps that after a whole vehicle is powered off, a main controller and all auxiliary controllers monitor whether self hard-wire ports meet the dormant condition or not; if the auxiliary controllers meet the dormant condition, a dormant request message is sent to a CAN bus, and the auxiliary controllers enter a dormant state till receiving the dormant request message sent by the main controller; after the main controller receives a dormant request message sent by the auxiliary controllers, whether the auxiliary controllers are allowed to be dormant is judged; if yes, the dormant request message is sent to the auxiliary controllers through the CAN bus; if the main controller meets the dormant condition and all the auxiliary controllers enter the dormant state, the main controller enters the dormant state; and after all the controllers enter the dormant state, the CAN bus enters the dormant state. By means of the vehicle control method and system, the problem that a vehicle storage battery losses electricity due to the fact that a dormancy awakening method requires all controllers to be simultaneously dormant or awakened in the prior art can be solved.

The embodiment of the invention discloses an obstacle detection method and device, a vehicle and a storage medium. The method comprises the following steps: obtaining a depth map around a vehicle; performing ground fitting based on the depth map to determine a ground equation; determining an obstacle candidate point set according to the ground equation and based on the depth map; clustering each candidate point in the obstacle candidate point set to obtain at least one independent obstacle; and identifying and filterng false detection obstacles in at least one independent obstacle to obtain anobstacle detection result based on the depth map. It can avoid the obstacle missing detection problem caused by the sparse sampling points when using the laser radar for detection; and the missing detection problem caused due to the fact that since not all types of obstacles can be used as samples for model training when a monocular camera is adopted for detection, the types of untrained samplescannot be detected, can also be avoided.

The present invention provides a method for constructing a variable region sequencing library, and a method for determining a variable region nucleic acid sequence. The method for constructing the variable region sequencing library comprises: adopting a sample containing nucleic acid encoding the variable region as a template, amplifying the nucleic acid encoding the variable region so as to obtain a first amplification product, and adding a sequencing linker to at least one of both terminals of the first amplification product so as to obtain the variable region sequencing library, wherein the primers used by the amplifying comprise: a first primer comprising at least a nucleic acid molecule specifically recognizing the framework encoding sequence of the V region, and a second primer comprising at least a nucleic acid molecule specifically recognizing the encoding sequence of the J region or C region. With the method of the present invention, the variable region sequencing library can be effectively constructed.

The invention relates to a head detection method and apparatus. The method comprises the steps of segmenting a to-be-detected image into more than one sub-image; inputting each sub-image to a convolutional neural network trained according to a training image subjected to head position calibration, and outputting a first feature corresponding to each sub-image through front layers including a convolutional layer and sub-sampling layers in the convolutional neural network; mapping the first feature corresponding to each sub-image into a second feature corresponding to each sub-image through a convolutional layer behind the front layers in the convolutional neural network; mapping the second feature corresponding to each sub-image into a head position corresponding to each sub-image and a confidence degree corresponding to the head position through a regressive layer of the convolutional neural network; and filtering the head position corresponding to each sub-image according to a corresponding confidence degree, thereby obtaining the head position detected in the to-be-detected image. According to the method and the apparatus, the head detection accuracy can be improved.

The invention discloses a Bayesian saliency based SAR image target detection method and mainly solves the problems of low detection accuracy and incomplete structure of a detected target on a binary image in an existing SAR image target detection technology. The method is implemented by the steps of performing superpixel segmentation on an original SAR image; constructing a prior saliency map, a foreground likelihood graph and a background likelihood graph by utilizing a superpixel segmentation result; fusing results of the prior saliency map, the foreground likelihood graph and the background likelihood graph in a Bayesian framework to obtain a Bayesian posterior saliency map; segmenting the Bayesian posterior saliency map to obtain a binary image with a suspected target region; and performing clustering and false alarm region removal on the binary image and extracting a suspected target slice on an original SAR image, thereby finishing the SAR image target detection. Compared with dual-parameter CFAR detection, the method has the advantages of high detection accuracy and relatively complete structure of the detected target on the binary image, thereby being suitable for SAR image target detection in complicated scenes.

The invention discloses a rapid pedestrian detection method based on computer vision. The method comprises the following steps: firstly, acquiring a pedestrian video image, then establishing a background model for a video image frame by a ViBe algorithm, and segmenting out a foreground area by the ViBe algorithm combined with a frame difference method; secondly, calculating the coordinates of the highest point of each target block outline, thereby finishing location of a head candidate area; and finally, traversing the head candidate area by a target detection window to obtain a sample to be detected, inputting the sample to be detected in a composite head detection trained by an AdaBoost algorithm, and judging whether the sample is a human head sample to obtain a pedestrian detection result. According to the method with the technical scheme, the technical problem of poor robustness and real-time performance in the prior art is effectively solved.

The invention provides a prompt control method and system for an indoor unit, the indoor unit and a multi-split central air conditioner. The multi-split central air conditioner comprises at least two indoor units. The prompt control method for the indoor unit is used for the indoor unit and comprises the steps that whether the coil pipe temperature and the outlet air temperature of the current indoor unit are within a working temperature range or not is detected in the operating process; and when the coil pipe temperature and the current outlet air temperature are not within the working temperature range, a dedusting prompt signal for the current indoor unit is sent out. According to the prompt control method for the indoor unit, the dust accumulation condition of a filter screen is detected by detecting the operating parameter change, caused by excessive accumulated dust on the filter screen of the indoor unit, of the indoor unit, a user is effectively reminded to remove dust in time, the heat exchange effect of the multi-split central air conditioner is ensured, and user experience is improved; and the indoor unit applying the method is simple in structure, low in cost and effective in judgment.

The invention relates to a system and a method for recognizing different defect types in paper defect visual detection. The system and the method have high recognition rate and high speed, and can recognize different defect types in paper defect visual detection with the average recognition rate of 97.5% and false recognition rate of 2.5%, thereby substantially achieving exhaustive detection and recognition of defective images. The time for entire defect recognition process is less than 10 ms, and can substantially meet the time requirement for paper real-time detection under the actual production conditions. The system comprises an image pickup device matching with the paper sheet to be detected, and a light source matching with the paper sheet to be detected, wherein the image pickup device is connected with an image capture card; the image capture card transmits the obtained image to a computer and a DSP (digital signal processor) image processing unit; and the DSP image processing unit is connected with the computer.

The invention relates to a video monitoring system and a method for detecting a moving target of an image of the video monitoring system. The video monitoring system comprises a video terminal, a motion detection module and a server terminal. The video terminal acquires and digitalizes a current frame image of a video via a video acquisition module to generate a compressed video stream; the motion detection module is connected with the video acquisition module and used for receiving the compressed video stream and performing a moving target detection pre-treatment, obtaining a motion vector directly from the compressed video stream, and identifying the current frame image which may comprise the moving target by a judgment on the motion vector; and the server terminal is connected with the motion detection module via a network, and used for receiving the compressed video stream subject to the moving target detection pre-treatment, and performing moving target detection on the current frame image which may comprise the moving target to confirm the moving target appears in the current frame image. The system and the method disclosed by the invention have high robustness and high speed, and can precisely detect the moving target.

The disclosed detection method for defect and magnetic leakage of a large-area steel plate comprises: local magnetizing the steel plate, detecting flux density on pole to calculate the inner magnetization saturation state by a formula; then, using multiple magnetic sensitive elements to form a detection probe to detect leakage flux density by equal interval, processing the output signal, comparing the detected value with dynamic-set threshold for decision. This invention improves cover range and space resolution, and ensures detection precision.

The invention provides an automatic tracking and positioning fire water monitor and an automatic tracking and positioning jet flow fire-extinguishing method. The automatic tracking and positioning fire water monitor comprises a base, a support, a shell, a fire water monitor body, an infrared thermal imaging sensor, a processor, a water pump electric control valve, a horizontal stepping motor and a longitudinal stepping motor. The processor draws the coordinates of a thermal image in real time and judges the coordinates of the kindling point according to a preset temperature threshold value, and the thermal image is sent by the infrared thermal imaging sensor in real time. The fire water monitor body is positioned to the coordinates of the kindling point rapidly and tracks the coordinates of the kindling point in real time until the processor controls the water pump electric control valve to be opened and the fire water monitor body sprays water. The automatic tracking and positioning fire water monitor has the advantages of being scientific in design, rapid and accurate in positioning and capable of realizing movable fire tracking. The use method includes the steps of (1) clearing, (2) scanning, (3) judgment, (4) fire extinguishing, (5) water stop detection, (6) fire-extinguishing finishing and the like, and has the advantages of being simple, efficiency, capable of realizing movable fire tracking, complete in scanning coverage and capable of preventing detection omission.

The invention discloses an oil and gas pipeline intelligent internal detection device based on multi-module combined location. The device comprises an internal detector arranged inside an oil and gas pipeline and a floor marker arranged outside the oil and gas pipeline. The internal detector comprises a driving system, a magnetic leakage detecting system, a speed control system, a distance measuring system and a low frequency emitting system, wherein the driving system, the magnetic leakage detection system, the speed control system, the distance measuring system and the low frequency emitting system are relatively fixedly connected together; the floor marker at least comprises a low frequency receiving system; the low frequency emitting system is used for sending detection results obtained by the magnetic leakage detection system out of the oil and gas pipeline; the low frequency receiving system is used for receiving low frequency electromagnetic pulse signals transmitted by the low frequency emitting system. The oil and gas pipeline intelligent internal detection device based on the multi-module combined location can timely obtain the detection data of the pipeline detector and analyze the detection data and accordingly rapidly determine the defect conditions of the pipeline.

The embodiment of the invention discloses a method and device for counting vehicles, relating to the field of intelligent traffic monitoring and overcoming the problem of inaccurate vehicle counting. The method comprises the following steps of: determining a counting mode of the vehicles according to correlation coefficients corresponding to a gray scale histogram of a video image; in the daytime mode, carrying out motion detection and / or edge detection by utilizing a preset first virtual coil and vehicle head detection by utilizing a preset second virtual coil, and further identifying the vehicles in the video image and counting the vehicles; and in the night mode, carrying out head light detection and head light matching by utilizing a preset third virtual coil, and further identifying the vehicles in the video image and counting the vehicles. According to the embodiment of the invention, the counting modes of vehicle counting are determined according to the correlation coefficients corresponding to the gray scale histogram of the video image, the counting modes comprise the daytime mode and the night mode, and the corresponding method for counting the vehicles is called according to the determined counting mode, therefore, the accuracy rate of the vehicle counting is improved.

The invention discloses an adhesion object segmentation method based on VIBE in object detection. The method includes the steps of background subtraction based on the VIBE, HOG feature vector extraction, SVM training and detection and segmentation algorithm optimization of multiple moving objects. For solving the problem of object adhesion occurring when the moving objects are shielded, the algorithm that spatial-temporal features are used for conducting rough segmentation on the moving objects in a video and then HOG features of the objects are extracted, trained and classified to perform precise segmentation is provided, the algorithm includes the steps that firstly, object detection is conducted through a VIBE algorithm, and a moving object area in a foreground is obtained by the adoption of background subtraction; secondly, scaling is conducted on images of the roughly-segmented moving objects in an original drawing, gradient histogram features of the images are extracted, a support vector machine is used for training to obtain an object segmentation classifier; finally, screening is conducted on positions of obtained moving objects, wrong objects which have large-area overlapping positions and are inconsistent in size are removed, and therefore segmentation of adhesion objects is completed.

The invention discloses a novel coronavirus detection kit. The kit comprises a qRT-PCR reaction liquid, a qRT-PCR enzyme liquid, an internal standard, a negative quality control substance and a positive quality control substance, wherein the internal standard is an RNA pseudovirus containing an internal reference detection gene fragment; the positive quality control substance is an RNA pseudoviruscontaining a target detection gene fragment; and the qRT-PCR reaction liquid comprises four groups of upstream and downstream primers with sequences of SEQ ID NO:1-8 and four probes with sequences ofSEQ ID NO:9-12. The kit can be used to simultaneously detect three sections of target gene fragments, so that missed detection can be effectively avoided. In addition, pseudoviruses are used in boththe internal standard and the positive quality control substance of the kit, so that safety of the kit is effectively improved, and detection accuracy of the kit is further ensured. The kit is high sensitivity and good in stability.