239 results about "Gray level histogram" patented technology

The invention belongs to the technical field of vehicle active safety and relates to a lane line detection method based on monocular vision. The lane line detection method comprises the following steps: acquiring an original image of a road condition in front of a vehicle; intercepting subimages of boundary regions at the two sides, wherein the subimages include the original image; removing the high-frequency noise of the subimages and carrying out grey level histogram equalization and binaryzation; intercepting left and right lane line detection region images; filtering based on the fixed width range of a lane line according to the features of low grey value pavements at the two sides of the lane line; preliminarily determining feature points of the lane line in a sampling line scanning manner and screening; and carrying out lane detection. The lane line detection method has the characteristics of good real time and high reliability.

The invention discloses a method for automatically identifying a breast tumor area based on an ultrasound image. The method comprises the following steps of acquiring the ultrasound image of the breast, and preprocessing the ultrasound image; segmenting the ultrasound image subjected to preprocessing through an image segmentation method to obtain a plurality of segmented subareas; extracting a grey level histogram, texture features, gradient features and morphological features of the ultrasound image, and combining the grey level histogram, the texture features, the gradient features and the morphological features of the ultrasound image with two-dimensional position information to obtain high-dimensionality feature vectors; selecting the most effective feature subset of the high-dimensionality feature vectors through feature ordering based on biclustering and a selection method; performing learning classification on the selected most effective feature subset through a classifier, and then automatically identifying the breast tumor area. By means of the method, the breast tumor area can be identified automatically from segment results of the breast tumor ultrasound image, therefore, automation performance of computer-aided diagnosis is improved, manual operation of clinical doctors is reduced, and subjective influence of clinical doctors is reduced.

In a contrast correcting apparatus 1 which divides an image into unit regions and carries out a contrast correction for each of unit regions, a gray level histogram calculation section 201 generates gray level histograms of the image, and a scene judgment section 202 makes a judgment on the state of the image. When the result of the judgment shows that the image is in a state such as overexposure, underexposure, low contrast or high contrast, a region size determining section 204 sets a greater size as the size of the unit regions. Based upon the size of the unit regions thus determined and the amount of contrast correction determined by the contrast correction amount determining section 203, gray level transformation curves are formed for the respective unit regions, and by using these, the contrast corrections are carried out on the respective unit regions. With this method, it is possible to properly reduce the occurrence of unevenness in gray levels in an image that tends to arise in the case when the size of the unit regions is small although the amount of contrast correction (the amount of emphasis) is great.

In a contrast correcting apparatus 1 which divides an image into unit regions and carries out a contrast correction for each of unit regions, a gray level histogram calculation section 201 generates gray level histograms of the image, and a scene judgment section 202 makes a judgment on the state of the image. When the result of the judgment shows that the image is in a state such as overexposure, underexposure, low contrast or high contrast, a region size determining section 204 sets a greater size as the size of the unit regions. Based upon the size of the unit regions thus determined and the amount of contrast correction determined by the contrast correction amount determining section 203, gray level transformation curves are formed for the respective unit regions, and by using these, the contrast corrections are carried out on the respective unit regions. With this method, it is possible to properly reduce the occurrence of unevenness in gray levels in an image that tends to arise in the case when the size of the unit regions is small although the amount of contrast correction (the amount of emphasis) is great.

The invention discloses an automatic coal and gangue sorting system and method, and belongs to a coal and gangue sorting system and method. The sorting system comprises a vibrator feeder, a queuing device, a coal collecting hopper, a gangue collecting hopper, a belt conveyor, a detecting device, a camera, an industrial personal computer, a lens hood, an LED light source, an executing device, a controller, a high-speed electromagnetic valve and a spray gun. A belt is monitored in real time through the camera, and two square sub-regions are selected, wherein side lengths of belt imaging regions corresponding to the sub-regions are smaller than the lower limit of granularity of coal and gangue; the grey level histogram average value of the two sub-regions is calculated in real time and compared with a threshold, determined through a test, of gangue, coal and the belt, when the grey level histogram average value of the sub-regions is larger than the threshold, the material is judged as gangue, the controller controls the high-speed electromagnetic valve to be switched on, the spray gun blows the gangue into the gangue collecting hopper, and coal continues to move and fall to the coal collecting hopper or the conveying belt. Real-time monitoring is conducted through the camera, control is timely, the sorting result is accurate, the layout is close to that of site artificial gangue discharge, and actual transformation is easy.

The embodiment of the invention discloses a method and system for detecting whether a camera is covered or not and belongs to the technical field of image processing. By The adoption of the method and system for detecting whether the camera is covered or not, the covered state of the camera can be accurately judged, and the misjudgment rate is reduced. The method mainly comprises the steps that an image frame obtained when the camera is not covered is used as a reference frame; the distribution similarity between the grey level histogram of a current frame and the grey level histogram of the reference frame is compared with a first threshold value, if the distribution similarity is smaller than the first threshold value, the distribution similarities between the grey level histograms of multiple continuous frames behind the current frame and the reference frame are sequentially compared with the first threshold value, and if all the distribution similarities are smaller than the first threshold value, the next frame of the multiple continuous frames is used as a first current frame; the similarity between the grey level histograms of every two adjacent image frames of the first current frame and multiple continuous frames behind the first current frame is compared with a second threshold value, and if the similarity between the grey level histograms of every two adjacent image frames of the first current frame and multiple continuous frames behind the first current frame is larger than the second threshold value, it is determined that the camera is covered.

The invention discloses a non-reference image quality objective evaluation method based on deep learning. Multi-resolution pyramid and Gaussian difference decomposition is performed on distortion images to be evaluated and then natural statistical characteristics can be extracted by performing simple local normalization on sub-band images without extracting characteristics from a transform domain so that complexity is greatly reduced. Degree of distortion of the images is measured by degree of loss of the natural statistical characteristics with no requirement for reference images or distortion types. The change condition of visual quality of the images under the influence of various image processing and compression methods can be objectively reflected by the method, and evaluation performance of the method is not influenced by the image content or the distortion types and is consistent with subjective perception of human eyes. An existing L moment estimation method is adopted to estimate the distribution parameters of the envelope curve of a gray level histogram, and the distribution parameters obtained through estimation are more accurate and have higher generalization capability.

The invention discloses a machine vision-based method for detecting and sorting polycrystalline silicon solar energy. The method comprises the following steps of: 1) allowing a polycrystalline silicon solar cell to pass through an image acquisition area, and acquiring a corresponding image through a charge coupled device (CCD) camera; 2) performing image preprocessing on the acquired image, wherein the image preprocessing comprises image extraction, gray processing, image noise filtering, image enhancement, edge detection and solar cell positioning; and 3) performing image recognition, comparing the parameters of the polycrystalline silicon solar cell acquired in the step 2) with a template, performing image similarity measurement, performing color classification to sort the colors. The grey level histogram of the polycrystalline silicon solar cell is analyzed and is compared with a standard sample image for calculation to obtain the standard deviation of the histogram distribution, and a classification decision is made through the obtained standard deviation. Through the proving of the experiment proves, the method has the advantages that the detection speed is high and the accuracy is high and the detection requirements can be met.

The invention discloses a license plate character segmentation method based on grey level histogram binaryzation. The plate character segmentation method comprises the following steps of converting an original color license plate image into a gray level image, calculating the gray average of the interest region in the gray level image and a gray level histogram, namely, the number of the pixel points corresponding to all gray values, sequentially verifying whether the gray values can meet set binaryzation threshold conditions, using the corresponding gray values as the binaryzation thresholds to carry out binaryzation treatment on the license plate image if the binaryzation threshold conditions are met, and utilizing a projection method to segment a binaryzation image to obtain license plate characters. The license plate character segmentation method based on the grey level histogram binaryzation can little affected by factors of uneven illumination, license plate contamination and the like, can set the binaryzation threshold of the license plate gray level image in a self-adaption mode, separates the license plate characters from a background area, obtains a clear binary image and can conveniently utilize the projection method to regionally segment the binaryzation image.

The invention discloses a corrugated board production quality regulation and control method based on machine vision, relates to the field of artificial intelligence, and is mainly used for mechanical parameter control of corrugated board production. The method comprises the steps of obtaining a target surface grayscale image; obtaining the gray gradient direction of each pixel point; calculating the defect probability of each pixel point; establishing a gray level histogram, calculating a background probability value of each gray level, and obtaining a background region of the gray level image; calculating the abnormal degree of each pixel point in the grayscale image, and constructing a sequence of all abnormal degrees in the grayscale image; calculating an influence degree value of each abnormal degree sequence to obtain an overall influence degree value of the target surface image; and adjusting production machinery parameters according to the overall influence degree value of the target image. According to the technical means provided by the invention, the influence degree of the defect is calculated through the target surface grayscale image, so that the mechanical parameters are adjusted, and the product quality and the production efficiency are improved.

The invention belongs to the technical field of intelligent shipping management, relates to an image distinguishing and detecting technology, and in particular relates to a ship distinguishing and tracking method based on a tail. The ship distinguishing and tracking method based on the tail comprises the following steps: 1: extracting the ship characteristic information of a valid distinguishing area relative to fairway information from an acquired video image, so as to distinguish a ship; 2, carrying out grey level histogram subtracting method to obtain a background-removal pure ship pixel accumulative grey level histogram gaussian model according to the foreground and background which are distinguished by a ship sorter based on gridding; and 3, analyzing connected regions, and separating and marking the targeted ship; and 4: carrying out follow-up tracking and analysis based on ship detection. According to the ship distinguishing and tracking method based on the rail, the ship can be quickly distinguished from the fairway based on the ship characteristics, the ship is tracked based on the tail, and thus the circumstance that the ships are illegally parked in no-parking areas on two sides of the fairway can be determined.

The invention relates to a method for detecting the color cast of a video image based on Lab chrominance space. The method comprises the following steps: a) converting RGB (Red Green Blue) color space into the Lab chrominance space; b) calculating color cast factors. The invention provides a new color cast detecting factor, which is successively used for detecting the color cast of the image. First, the image is converted from the original RGB color space into the Lab chrominance space; then according to the distinction of the spatial gray level histogram distribution of a chrominance and b chrominance between a normal image without color cast and an abnormal image with color cast, the mean value of the spatial gray level histogram distribution of the a chrominance and the b chrominance are respectively calculated; then according to the statistical distribution between the mean value and the mid value of histograms, the color factors are calculated. A lot of experiments of real street view image databases prove that the new color cast detecting factor disclosed by the invention can really reflect the degree of color cast of images so as to complete color cast detection. The method has the advantages of high detection speed and accurate precision.

The invention relates to a rapid threshold segmentation method based on gray level-gradient two-dimensional symmetrical Tsallis cross entropy, aims at the problems that approximate assumption exists in a conventional gray level-average gray level histogram and a whole solution space is required to be searched by calculation, so that segmentation is inaccurate and the efficiency is not high, and provides improved two-dimensional symmetrically Tsallis cross entropy threshold segmentation and a rapid recursive method thereof. The threshold segmentation method is higher in universality and accurate in segmentation; in order to realize accurate segmentation of a gray image, a new gray level-gradient two-dimensional histogram is adopted, and a two-dimensional symmetrical Tsallis cross entropy theory with a superior segmentation effect is combined with the histogram, so that the gray level image segmentation accuracy is effectively improved; the requirement for on-line timeliness of an industrial assembly line is met at the same time, a novel rapid recursive algorithm is adopted, and redundant calculation is reduced; and after a gray level image of the industrial assembly line is processed, the inside of an image zone is uniform, the contour boundary is accurate, the texture detail is clear, and at same time, good universality is provided.

A license plate character partitioning method based on a quick region labeling algorithm and a license plate master space location method belongs to the image processing technical field and relates to a license plate automatic recognition technique. Firstly the license plate region is converted through grey level histogram and grey level stretching conversion to realize reinforcement of the character region on the license plate; secondly a two-valued threshold value is calculated and the license plate grey level image is converted into a two-valued image; thirdly a connectivity analysis of the license plate two-valued image is carried out according to the quick region labeling algorithm and an alternate region of characters is obtain through a region growing method; fourthly a master space location is fixed from the license plate two-valued image; fifthly the final character region is obtained through mending and making up for the character region based on the feature of the license plate master space location; finally the characters are partitioned from the license plate grey level image. The license plate character partitioning method based on the quick region labeling algorithm and the license plate master space location method provided by the invention can effectively improve performances such as systematic versatility and location accuracy.

The invention discloses an image grey level histogram-based foggy day detection method, which mainly comprises: a first step of performing initialization to obtain a grey level histogram of an image; a second step of primarily detecting whether the image is marked to indicate a foggy day or a fogless day; a third step of performing processing again if the image is marked to indicate the fogless day, and marking the image to indicate the foggy day when a certain condition is met; a fourth step of further performing detection if the image is marked to indicate the foggy day, and marking the image to indicate the fogless day when the certain condition is met; and a fifth step of performing the detection for the third time if the image is marked to indicate the foggy day, marking the image to indicate a densely-foggy day when the certain condition is met, otherwise, marking the image to indicate a thinly-foggy day. In the method, the grey level histogram of the image is utilized to detect weather for the first time, and three levels which are the fogless day, the thinly-foggy day and the densely-foggy day respectively are detected by utilizing corresponding relationships between the number of pixels and grey level values in the grey level histogram and a series of threshold values. Compared with other foggy day detection methods, the method has the advantages of low cost, easy popularization, high processing speed, wide application range, high accuracy and ideal effect.

The invention discloses a method for dynamically adjusting backlight brightness based on the image content. The method can dynamically adjust a backlight and adjust the image contrast effectively. The method includes the following steps: (1) calculating the gray level histogram of an image to be used for calculating the highest degree of distortion and the largest gain coefficient of the image; (2) limiting the maximum value of the gain coefficient to reduce the influences that the display effect is weakened and a user feels uncomfortable in vision, wherein the influences are caused by sudden change of the backlight; (3) according to the ambient brightness, determining the minimum value of the current brightness of a mobile phone to determine the current maximum distortion so that the situation that the user is unable to recognize the content on a screen because the environment is too bright will not happen; (4) introducing an image similarity algorithm of a historical frame and a current frame to reduce the number of times of calculation of the gain coefficient. The method dynamically adjusts the backlight according to the display content on the screen, reduces calculation amount to the greatest extent under the condition that the effect of the calculation amount on the performance of the mobile phone is taken into consideration, compensates for the caused image distortion, and ensures that the visual experience of the user will not be affected by the design of low power consumption.

The invention proposes a rough set based image segmentation method for quickly inhibiting fuzzy clustering. The method is used for solving the technical problems of low running speed, low segmentation accuracy and poor noise robustness of an existing image segmentation method. The method is implemented by the steps of 1, inputting a to-be-segmented image I1; 2, calculating a weighted mean of local information and a mean of non local information of pixel points xi in the image I1; 3, obtaining a reconstructed image; 4, clustering a grey level histogram of the reconstructed image; 5, judging whether a current iterative frequency is greater than a maximum iterative frequency T or not, and if yes, performing the step 6, otherwise, adding 1 to the iterative frequency and performing the step 6; 6, outputting a membership matrix and a clustering center of the obtained reconstructed image; and 7, obtaining segmented images. According to the method, the running speed of image segmentation is increased, the accuracy of segmentation is improved, and the noise robustness is enhanced; and the method can be used for feature extraction and target identification of artificially synthesized images, medical images and natural images.

The invention relates to a nonlinear adaptive infrared image enhancing method, which comprises the following steps: A) inputting original image data and counting a histogram; B) analyzing the histogram and counting the sizes, positions and widths of each crest and trough, and confirming a main peak; C) substituting the main peak in an application formula and acquiring a nonlinear mapping curve through calculation; D) calculating to acquire a gray level histogram mapping table corresponding to the whole image; and E) using the histogram mapping table established in the step D to perform table look-up mapping on the histogram counted in the step A), thereby forming a new image data, sending the image data to a terminal and displaying. By using the nonlinear adaptive infrared image enhancing method provided by the invention, the image contrast can be obviously promoted while the image details are maintained, and the problems of the traditional image enhancing method that the noise suppression capability and the scene adaptability are inferior under a simple background and the infrared video flickers when the scene changes largely are solved, thereby increasing the environmental adaptability of an infrared imaging system.

The invention discloses a gray level image segmentation method based on multi-objective fuzzy clustering, relating to the technical field of image processing and mainly solving the problem of lower accuracy rate of gray level image segmentation. The gray level image segmentation method comprises the steps of: after graying an image, randomly generating a plurality of clustering centers according to a generated grey level histogram, and constituting the clustering centers into a parent antibody population. The gray level image segmentation method is characterized in that a dense separation effectiveness function as an evaluation criteria is combined with a fuzzy optimization function in a fuzzy C-mean value method to form a multi-objective optimization problem, the whole parent population is iterated for multiple times by adopting an immune clone multi-objective evolutionary algorithm, simultaneously searched from multiple directions, and calculated in parallel so as to finally acquire an optimum clustering center, and a classifying result is output. Therefore, the detail information in the gray level image is effectively reserved, the wrong fraction is reduced, the gray level image segmentation precision is improved, and a good platform is provided for subsequent operation of gray level image segmentation. The gray level image segmentation method can be used for extracting and obtaining the detail information of the gray level image.

The invention discloses a method and system for tracking targets in a video based on the PTZ. The method comprises the following steps: 100, utilizing a Gaussian mixture modeling method for setting up a background model for a video image obtained by a camera in a preset position scene, and detecting the motion targets in a monitored video image immediately obtained by the camera in the preset position scene; 200, calculating a grey level histogram of the motion targets of the monitored video image, recording template information of the motion targets, and updating parameter information of the motion targets according to the video image immediately obtained by the camera; 300, conducting judgment according to the parameter information and controlling the camera to conduct the corresponding adjustment according to the judged result. The method and system for tracking the targets in the video based on the PTZ can initially and accurately track the motion targets and accurately distinguish the motion targets of the video image.

The invention discloses a pasted paper money detection method and device. The pasted paper money detection method comprises the steps of coarse positioning an acquired paper money image; acquiring a coarse positioning area image with the existence of a paste situation probably; carrying out grey level histogram statistic on the coarse positioning area image; grading based on a statistic result according to a gray value range; carrying out binarization processing and envelopment fitting on each grade of image, and acquiring an image envelope of each grade of image; carrying out straight line detection on each image envelope; when detecting that the image envelope contains two straight lines which do not belong to paper money, marking the paper money corresponding to the paper money image as pasted paper money. According to the pasted paper money detection method and the device, provided by the invention, the detection rate of the pasted paper money can be effectively improved by aiming at patterns with different grey level situations probably formed by a pasted tape according to image characteristics of the pasted paper money displayed in the paper money image, the scheme can be realized easily, and the equipment cost is saved.

The invention discloses a pixel number clustering-based fuzzy C-average value gray level image splitting method, and mainly solves the problem of low accuracy of splitting of the gray level image. The method is realized by the steps of (1) reading a gray level image and counting a gray level histogram; (2) randomly initializing a clustering center; (3) calculating the Euclidean distance between each gray level and each clustering center; (4) calculating the total number of the pixels contained between each gray level and each clustering center by the Euclidean distance; (5) judging the type of each gray level by the total number of the pixels to obtain a classified result; (6) calculating each type of gray level average value by the classifying result to be used as a new clustering center; (7) calculating a membership matrix according to the clustering center; (8) updating the clustering center by the membership matrix; (9) repeating the steps (3)-(8) until the terminal condition is met, and outputting an updated clustering center; and (10) classifying the gray images by the updated clustering center to obtain a splitting result image. The pixel number clustering-based fuzzy C-average value gray level image splitting method has the advantage of high image splitting precision and can be used for extracting the detail information of the gray level image.

The invention discloses an SAS image segmentation method and system based on an SVM classifier. The method comprises the steps of (101) pre-processing an SAS image to be segmented to acquire grey level histograms and grey level co-occurrence matrices of different areas of the SAS image; (102) extracting a plurality of statistical property parameters from the grey level histograms and a plurality of textural feature parameters from the grey level co-occurrence matrices; (103) inputting the statistical property parameters and the textural feature parameters into the SVM classifier to carry out segmentation on the SAS image to be segmented, wherein the SVM classifier is obtained through training by taking a plurality of statistical property parameters extracted from a grey level histogram of a certain area of the training image and a plurality of textural feature parameters extracted from a grey level co-occurrence matrix of the certain area of the training image as training features; (104) optimizing segmented images output from step (103) by means of mathematical morphology operators so that cavities and isolated points in the segmented images can be removed.

The embodiment of the invention discloses an image processing method. The image processing method comprises the steps that a grey level histogram of non-sky-area pixels in a dark channel image of an initial image is determined; whether the initial image needs to be defogged or not is judged according to the grey level histogram; when the initial image needs to be defogged, the initial image is defogged; or, when the initial image does not need to be defogged, the initial image is not defogged. By means of the image processing method, whether the image needs to be defogged or not can be accurately judged, the number of occupied resources of a processor is small, the image processing time can be shortened, and the electricity quantity of an electronic device is saved.

The invention relates to a real-time robustness tracking device of a moving target or a dim small target under a complex background, a target image preprocessing unit of the device is used for performing preprocessing on an input image; a histogram statistical unit is used for performing calculation and processing to get a gray level histogram of the image; a calculation gray level image feature unit is used for calculating the difference delta x between the maximum gray level value xmax and the non-zero minimum gray level value xmin in the gray level histogram and calculating the different delta y between the number of pixels ymax of the maximum gray level value and the number of the pixels ymin of the non-zero minimum gray level value; a judging unit is used for autonomously judging whether the image belongs to the low-contrast dim small target situation or the complex background condition situation according to the delta x and the delta y; and then the device is used for autonomously deciding the adoption of the corresponding tracking method to perform target tracking and output the tracking result. The two features, namely the contrast and the gray level complexity, which can effectively represent the image in the gray level histogram of the image are adopted for comprehensive judgment, and then the great judgment result can be obtained.

The invention provides a color image enhancement method based on histogram segmentation, and relates to the field of image processing. The method is used for solving the problem that an existing color image enhancement method is large in calculated amount or poor in enhancement effect. The method comprises the steps that grey level histograms of component subgraphs R, G and B of a color image to be enhanced are segmented two times in sequence according to a gray level mid-value and the principle that the segmented histograms are equal in area; histogram equalization is carried out on four gray level areas, obtained after segmentation of the last step, of the component subgraphs R, G and B; the proportion of gray levels of all pixel points of the component subgraphs R, G and B of the color image to be enhanced to the total gray level number of the pixel points corresponding to the color image to be enhanced is calculated, and the component subgraphs R, G and B obtained in the last step after histogram equalization are synthesized according to the calculated proportion. According to the scheme, the calculation complexity is low, and the image enhancement effect is good.

The invention relates to a reversible secret information hiding and extracting method which is mainly used for realizing dynamic compromise control over hiding capacity and image quality. First, a carrier image is preprocessed to obtain a grey level histogram of partitioned images; then, a histogram steep index is introduced, a threshold value is set for the histogram steep index, and secret information is inlaid in the carrier image after judgment; finally, the secret information is extracted from the carrier image in which the secret information is inlaid so as to restore the original image. The reversible secret information hiding and extracting method achieves the effect that under the condition that the image quality is acceptable, the information hiding capacity is improved and dynamically controlled; the reversible secret information hiding and extracting method has application space in biomedicine image information hiding, important military image secrecy transmission and other aspects.

The invention provides a multi-factor two-dimension grey level histogram based threshold segmentation method belonging to the technical field of computer optical measurement. According to the invention, a multi-factor weight integrating image is created, a two-dimension grey level histogram is drawn and cross entropy is used for calculating the threshold value for segmenting the image. First, the weight integrating image based on three factors including neighborhood average gray level, gradient strength and gradient direction level. Further, a gray level image is combined and a gray level-integrated factor level two-dimension gray level histogram is drawn. Then an iteration method is adopted for solving gray level average values of foreground and background pixels. Finally, based on the minimum cross entropy, the optimal threshold value is calculated and the optimal threshold value is used for segmenting the image. The method provided by the invention solves a problem of image key information loss of a prior two-dimension gray level histogram; data accuracy and method reliability are ensured. The credibility of the threshold value and the image segmenting effect are improved. The whole threshold value segmenting algorithm is good in adaptability and high in validity.

An exposure correction method for digital images first computes a gray-level histogram of an image. Then determine whether the exposure of the image is normal from the gray-level histogram, thereby determining an exposure threshold. The central region of the image is extracted to find an average brightness Iave. The average brightness Iave and a destination brightness Idest are used to determine an adjusting curve y=f(x). The brightness channel is adjusted according to a constructed correspondence table. Therefore, the image processing effects are enhanced even though the processing time is reduced.

The invention belongs to the field of video image data processing and discloses a surveillance video pedestrian detection matching method which comprises a video pedestrian target detection step, an inter-frame common target relevance step, target sequence and to-be-matched target characteristic extraction step, a characteristic similarity calculation step and a target matching distinguishing step. Due to the fact that no big displacement exists between adjacent inter-frame pedestrian targets, a target sequence is obtained by utilizing detected location information of a pedestrian to conduct associating on the common target. One method for extracting target sequence features is to extract multi-frame grey level histogram features of the target sequence, and the other method is to extract a physical configuration audit (PCA) template. Due to the adoption of the multi-frame information, the surveillance video pedestrian detection matching method possesses better stability and matching accuracy compared with single frame target matching. A matching determination method utilizes iteration features to integrate the similarity of the two features to make judgment and obtain a matching result.