CN101930549A - Second generation curvelet transform-based static human detection method - Google Patents
Second generation curvelet transform-based static human detection method Download PDFInfo
- Publication number
- CN101930549A CN101930549A CN 201010259562 CN201010259562A CN101930549A CN 101930549 A CN101930549 A CN 101930549A CN 201010259562 CN201010259562 CN 201010259562 CN 201010259562 A CN201010259562 A CN 201010259562A CN 101930549 A CN101930549 A CN 101930549A
- Authority
- CN
- China
- Prior art keywords
- human body
- sample
- training
- vector
- training sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a second generation curvelet transform-based static human detection method, which mainly solves the problem of high detection false-alarm rate in the conventional human detection technology. The detection process comprises the following steps of: acquiring a negative sample through bootstrap operation of the negative sample, and forming a training sample set by the negative sample and other positive samples in a database; calculating curvelet transform-based feature vectors of all training samples to form a training sample feature set; performing classification training on the sample feature set by adopting an AdaBoost algorithm to obtain a classifier; inputting a to-be-tested image with any size, calculating curvelet transform-based feature vectors of all scan window images in the to-be-tested image; inputting the curvelet transform-based feature vectors of all scan window images into the obtained classifier for classification; and according to classification results, combining all scan windows classified as human by utilizing a main window merging method to form the final human detection result. The method has the advantages of high detection accuracy and low false-alarm rate, and can be used for classifying and detecting human in the image.
Description
Technical field
The invention belongs to mode identification technology, relate to human body detecting method, can be used for classification and detection the human body in the image and other complex target.
Background technology
Human detection has many important use in computer vision, as video monitoring, intelligent automobile and intelligent transportation, robot and senior man-machine interaction etc.Yet because the influence of factors such as the diversity of the variation of human body self attitude, clothes and illumination, the appearance change of human body is very big, causes human detection to become a very problem of difficulty.
At present, in the still image method of human detection mainly contain method based on manikin, based on the method for template matches with based on the method for statistical classification.Method based on manikin has clear and definite model, can handle occlusion issue, and can infer the attitude of human body.Shortcoming is that the structure of model is difficult, finds the solution also more complicated.Calculate simply based on the method for template matches, shortcoming is because the complicacy of human body attitude is difficult to construct enough templates to handle different attitudes.Based on the method for statistical classification by machine learning from a series of training data middle school acquistion to a sorter, represent human body with this sorter, utilize this sorter input window is classified and to discern then.Advantage based on the method for statistical classification is the comparison robust, and shortcoming is to need a lot of training datas, and is difficult to the problem that solves attitude and block.
Method based on statistical classification mainly comprises two steps: feature extraction and classifier design.Wherein the sign ability of selected feature will directly influence the performance of sorter.Present selected feature comprises: original gray feature space, Haar wavelet character, shape description symbols feature, Gabor feature, oriented histogram of gradients HOG feature and SIFT feature etc.Wherein the extraction rate of HOG feature extracting method is fast, and it is also higher to detect accuracy, thus, has obtained in recent years using widely.How further to improve the accuracy that detects, become one of key problem of this research field.
According to the method for designing of sorter, existing method based on statistical classification can be divided into method based on neural network NN, based on the method for support vector machine SVM with based on the method for AdaBoost.AdaBoost is a kind of Boosting algorithm with adaptivity, it makes the performance of weak learning machine get a promotion by setting up many learning machine combinations, because what it was exclusive pays close attention to the self-adaptation of learning machine performance with to learning the immunity of phenomenon excessively, having caused in recent years widely.
The method that the characteristics of human body of classics extracts is the method for the direction gradient histogram HOG of Dalal and Trigg proposition, and their result shows that HOG method method before is greatly improved on the detection accuracy; Another method is the edgelet method, and it utilizes the edge direction characteristic of a kind of edgelet of being called as descriptor; Edgelet is exactly one section straight line or the curve on the detected edge; Granularity is adjustable, and gradient subregion GGP descriptor has merged heterogeneous feature, and the representation of concept by granularity comes out.Because exist in background when disturbing the edge, it is poor that the HOG feature shows, and has the situation that the feature in some backgrounds is judged as the characteristics of human body, therefore the false alarm rate that detects is higher.
Candes and Donoho have introduced a kind of new multiscale analysis system and have been called the curve wave conversion.The curve wave conversion is a multiple dimensioned pyramid, at each yardstick a lot of directions and position is arranged.The curve wave energy is the uncontinuity at edge in the presentation video effectively.
People such as MohamedElAroussi have been applied to the method for curve wave conversion in the detection of people's face, the method for detecting human face of block-based curve wave conversion has been proposed, the statistical nature that utilization is extracted from the piece that the coefficient of curve wave conversion is divided carries out people's face as proper vector and detects, at ORL, obtained good detection effect on YALE and the FERET data set, the curve wave conversion has been used for the detection of human body but also have no talent at present.
Summary of the invention
The objective of the invention is to overcome the high problem of above-mentioned HOG method false alarm rate when having noisy background, proposed a kind of based on the edge of curve wave conversion and the human body detecting method of texture associating feature extraction, with the false alarm rate of reduction human detection, thereby improved the accuracy that detects.
The know-why that realizes the object of the invention is that the method that the people's face with above-mentioned block-based curve wave conversion detects is applied in the human detection, and above-mentioned method improved, extracting method based on the human body edge feature of curve wave conversion has been proposed, and added the textural characteristics that extracts the coefficient behind the curve wave conversion, extract the feature of human body training sample set, train these features by the AdaBoost algorithm, obtain sorter, and use the detection of sliding window method for scanning realization human body in the still image.Detailed process is as follows:
(1) in the INRIA database, obtains negative sample by bootstrapping operation, these negative samples other positive sample composing training sample set in database;
(2) extract the edge feature vector that training sample is concentrated each training sample, and the edge feature vector that extracts has been carried out the selection of optimum statistic based on the curve wave conversion;
(3) extract the texture feature vector that training sample is concentrated each training sample, and, constitute characteristics of human body's vector jointly the vectorial cascade of edge feature that this texture feature vector and step (2) are extracted based on the curve wave conversion;
(4) characteristics of human body's vector of all training samples in the calculation training sample set is formed the sample characteristics collection, utilizes the AdaBoost sorting algorithm that it is carried out classification based training, obtains a sorter;
(5) input arbitrarily size by altimetric image, adopt sliding window method for scanning to being scanned detection by altimetric image, and calculate the characteristics of human body's vector based on the curve wave conversion of all scanning window images, be input in the step (4) and classify in the resulting sorter;
(6) according to the classification results of sorter output, utilize the main window act of union, all scanning windows that are divided into human body are made up, form final human detection result.
The present invention has the following advantages compared with prior art:
1, because the present invention has used two kinds of different feature extracting methods to carry out the bootstrapping operation of negative sample, make that the negative sample that is obtained is more representative, the sorter of the sample set training of its formation has better classification performance.
2, because the statistical nature of coefficient behind the curve wave conversion that the present invention uses when the edge feature that extracts based on the curve wave conversion, can extract compactness and the edge feature of the meaning represented is arranged, reduced the dimension of feature simultaneously, can be more conducive to the sorter training, the further feature close with intrinsic dimensionality compared, and corresponding sorter reaches the required training time of identical training error to be shortened greatly.
3, since the statistical information that the co-occurrence matrix of utilization of the present invention coefficient behind the curve wave conversion extracts as textural characteristics, expanded edge feature, thereby further improved the accuracy that detects, remedied the false alarm rate high shortcoming that detects when noisy for background of HOG.
4, experimental result shows, edge and the texture based on the curve wave conversion that use among the present invention are united better picture engraving of feature, make and compare with traditional HOG feature extracting method that be significantly improved on classification accuracy rate, it is also more accurate to detect.
Description of drawings
Fig. 1 is a schematic flow sheet of the present invention;
Fig. 2 is positive sample of part and the negative sample image that uses among the present invention;
Fig. 3 is the present invention and traditional HOG feature extracting method and based on the Edge Gradient Feature method of the curve wave conversion error attenuated comparison diagram when the sample training;
Fig. 4 be the present invention and traditional HOG feature extracting method and based on the Edge Gradient Feature method of curve wave conversion at the recipient's operating characteristic curve ROC that test sample book is carried out the branch time-like;
Fig. 5 be the sorter of method of the present invention training test sample book is carried out the branch time-like some by the test sample book of mis-classification;
Fig. 6 is the human detection result figure that the present invention is used for still image.
Embodiment
The present invention utilizes the curve wave conversion, extracts the feature of the edge feature associating textural characteristics of curve wave conversion coefficient as image, classify and detected image in human body.Behind the edge and texture associating feature that extract based on the curve wave conversion, utilize the AdaBoost sorting algorithm to carry out sample training, and classification results and HOG feature are compared.Describe in detail as Fig. 1, Fig. 3 and Fig. 4.
With reference to Fig. 1, specific implementation process of the present invention is as follows:
The database that the present invention uses is from INRIA somatic data storehouse, and download address is: http://pascal.inrialpes.fr/data/human/.Because this database do not provide enough negative samples, thus need be based on this database, operate by the bootstrapping of negative sample and to obtain negative sample.
The present invention has more representativeness in order to make training sample, has used the HOG feature respectively and unite these two kinds of features of feature based on the edge and the texture of curve wave conversion when feature extraction, carries out the bootstrapping operation of negative sample, can obtain two negative sample collection; Getting it then occurs simultaneously as final negative sample collection; Added by this negative sample collection at last positive sample set in the INRIA database to obtain final training sample set, have 6246 samples, as shown in Figure 2, wherein Fig. 2 (a) be a just sample of part, and Fig. 2 (b) is the part negative sample; As training set, 1132 positive samples and 821 negative samples are as test set with wherein 2416 positive samples and 1877 negative samples, and size is 64 * 128 pixels.
The bootstrapping operating process of described negative sample is as follows:
(1.1) first appointing from the INRIA database, got positive sample of sub-fraction and negative sample, carries out feature extraction, training preliminary classification device;
(1.2) use this preliminary classification device, detect all the other the non-human body images in the database, to these non-human body images, be divided in the scanning window image of positive sample a random choose part in mistake and form new negative sample collection, use random choose can avoid sneaking into the sample image of a large amount of feature similarities with current negative sample;
(1.3) repeat (the 1.1)-feature extraction of (1.2), training classifier, the non-human body image of detection and form new this process of negative sample collection until collecting final negative sample.
Step 2 is utilized the curve wave conversion, calculates the edge feature vector based on the curve wave conversion of all training samples, and the edge feature vector that extracts is carried out the selection of optimum statistic;
(2.1) each training sample is done fast discrete curve wave conversion, the parameter of curve wave conversion is set to real-valued curve wave conversion; And scale parameter is 3 layers; Inferior rough layer has 8 direction subbands; Detailed level is a curve wave system number, has 16 direction subbands;
(2.2) for the coefficient after the conversion, at first the sub-band coefficients matrix that has identical size in inferior rough layer and the detailed level is spliced, then the matrix of coefficients of each layer is carried out two according to 8 * 8 coefficient magnitude and advance to deduct marks, obtain curve ripple piece, do not have overlapping in the subdivision process between the piece;
(2.3) in each piece, extract these several statistics of energy, entropy, standard deviation, average, maximal value, minimum value and contrast, and the resulting statistic of different piecemeals is connect the initial edge proper vector that obtains image; And the initial edge proper vector has been carried out the selection of optimum statistic;
(2.4) calculate the initial edge proper vector of all training samples, obtain the initial edge proper vector of training sample set, put into and carry out training classifier in the AdaBoost algorithm, because the selected probability of feature is directly proportional with the sign ability of feature, so during statistics training AdaBoost sorter, with every kind of selected number of times of statistic the statistic in the step (2.3) is screened, just can obtain optimum statistic.The experimental result that optimum statistic is selected is as shown in table 1:
Table 1 optimum statistic is selected experimental result
Wherein, C is a sorter exercise wheel number,
The present invention selects experiment according to statistic, has preferentially chosen following several statistic as optimum statistic:
Energy:
Entropy:
Contrast:
Standard deviation:
Maximal value: max (c
I, j), wherein, c
I, jFor in each curve ripple piece so that (i j) is the coefficient of coordinate, and N is the number of contained element in each curve ripple piece;
(2.5) optimum statistic with the different curve ripple pieces of training sample connects, and forms a proper vector, i.e. edge feature vector.
Step 3 is extracted the texture feature vector based on the curve wave conversion that training sample is concentrated each training sample, and with the vectorial cascade of edge feature that this texture feature vector and step 2 are extracted, constitutes characteristics of human body's vector jointly.
(3.1) take 1/2 overlapping mode to carry out subdivision for the sub-band coefficients of the rough layer after the conversion with the piece of 8*8;
(3.2) the coefficient fritter to each 8 * 8 size calculates its co-occurrence matrix, and the quantification progression of this co-occurrence matrix is 16;
(3.3) for the co-occurrence matrix of the coefficient fritter of each 8 * 8 size, calculate its angle second moment, entropy, contrast, correlativity, average and and variance and this six statistics, that is:
The angle second moment:
Entropy:
Contrast:
N=|i-j|. wherein
Correlativity:
μ wherein
x, μ
y, σ
x, σ
yBe defined as respectively:
Average and:
Wherein:
Variance and:
Wherein, i represents the line number of element in the coefficient co-occurrence matrix of piece, and j represents the columns of element in the coefficient co-occurrence matrix of piece,
The coefficient co-occurrence matrix of expression piece the (i, j) individual element, G represent the quantification progression of co-occurrence matrix of the sub-piece of rough layer sub-band coefficients subdivision of curve wave conversion;
(3.4) statistic of the co-occurrence matrix of the coefficient of different masses is connect obtain the image texture features vector;
(3.5) the edge feature vector with image texture features vector sum step 2 gained carries out the proper vector of cascade as human body.
Step 4, characteristics of human body's vector of all training samples in the calculation training sample set is formed the training sample feature set, utilizes the AdaBoost sorting algorithm that it is carried out classification based training, obtains a sorter;
(4.1) extract the edge feature vector sum texture feature vector that training sample is concentrated each sample according to the method for step 2 and step 3 respectively, and the edge feature vector sum texture feature vector of each training sample that will extract carries out cascade, obtains characteristics of human body's vector of each training sample;
(4.2) suppose that characteristics of human body's vector is the vector of a M dimension, it is N that training sample is concentrated the number of training sample, and then the proper vector that training sample set is extracted will form the matrix of a N * M dimension, as the input of AdaBoost algorithm, train a sorter.
Described AdaBoost is a kind of Boosting algorithm with adaptivity, and it makes the performance of weak learning machine get a promotion by setting up the combination of many learning machines, has adaptive learning machine performance and to crossing the immunity of study phenomenon.
In the Adaboost algorithm, use the weighted value of each sample to represent the size that this sample is divided by mistake.In the weight renewal process that each is taken turns, can be become greatly by the wrong weight of sample of dividing, if a sample has been divided many times by mistake, the weight of this sample is just increasing so.
Step 5, input arbitrarily size by altimetric image, adopt sliding window method for scanning to being scanned detection, and calculate the characteristics of human body's vector based on the curve wave conversion of all scanning window images by altimetric image, the specific implementation step is as follows:
(5.1) input arbitrarily size by altimetric image, be that the ratio of [0.4,0.5,0.6,0.7,0.8,0.9] is carried out convergent-divergent with it by pantograph ratio;
(5.2) will in behind the described ratio scaling by the zone of a sample size in the altimetric image upper left corner as first scanning window, every to 8 pixels of right translation or downwards 8 pixels of translation obtain one group of scanning window thus as a new scanning window;
(5.3) image section in the scanning window is carried out the curve wave conversion, matrix of coefficients for the curve wave conversion, after the splicing of matrix of coefficients piece, to the matrix of coefficients on each yardstick carry out respectively 8 * 8 two advance to deduct marks, calculate these a few class statistics of energy, entropy, contrast, standard deviation and maximal value on each curve ripple fritter, and the statistic of different masses is connect to the end scanning window edge of image proper vector;
(5.4) the overlapping mode of the coefficients by using 1/2 of the rough layer of matrix of coefficients of curve wave conversion is carried out subdivision with the fritter of 8*8; Calculate each fritter angle second moment, entropy, contrast, correlativity, average and and variance and this several statistics, and the statistic of different fritters connect obtain scanning window image texture features vector;
(5.5) scanning window edge of image proper vector and texture feature vector are carried out the proper vector that cascade obtains final scanning window image;
(5.6) proper vector of all scanning windows is input in the resulting sorter of step 4 classifies, obtain one group of result of determination.
Sorter will judge whether the image in all scanning windows is human body.Each scanning window can obtain one and judge mark, if this judgement mark is the human body window greater than 0 this scanning window of expression, otherwise be non-human body window, will be by the classification results of the sorter mark of the position of the pantograph ratio of altimetric image, all scanning window images and gained thereof as sorter output.
Step 6, the classification results according to sorter output utilizes the main window act of union, and all scanning windows that are divided into human body are made up, and forms final human detection result, and concrete steps are as follows:
(6.1) according to the fractional value of the scanning window image of sorter output, whether judgement is comprised human body in the altimetric image, if the scanning window of sorter output does not have the human body window, then do not comprised human body in the altimetric image, otherwise, from all human body windows, find out its sorter mark the highest as main window;
(6.2) main window and other human body windows are made up judgement, when other human body windows are in around the main window and overlapping being judged to less than 1/2 time do not made up, otherwise make up;
(6.3) with the border average of main window and the human body window that all need make up as a testing result, the present invention, when asking the border average, with the sorter mark of the human body window weighted value as the border: the sorter mark is big more, its border weighting is big more, and is big more to final testing result influence; The sorter mark is more little, and its border weighting is more little, and is also more little to final testing result influence, can make the detection position of human body more accurate like this;
(6.4) the human body window of deletion main window and all participation combinations;
(6.5) if also have remaining human body window, then find out again sorter mark wherein the highest as main window, and repeat the operation of (2)-(4);
(6.6) mark all testing results on tested person's volume image, by the altimetric image final human detection result, generally adopt rectangle frame to represent testing result as this, the human body that is detected is in the rectangle frame.
Effect of the present invention can further specify by following emulation:
1. emulation content:
Adopt feature extracting method and present widely used HOG feature extracting method based on the curve wave conversion proposed by the invention to carry out simulation comparison experiment.Positive sample set is wherein taken from the INRIA database, the negative sample collection is based on this database, obtain by negative sample bootstrapping operation, the sample set that obtains at last has 6246 samples, wherein 2416 positive samples and 1877 negative samples are as training set, 1132 positive samples and 821 negative samples are as test set, and sample size is 64 * 128 pixels.Fig. 2 has provided part sample image wherein, and wherein Fig. 2 (a) is the positive sample of part, and Fig. 2 (b) is the part negative sample.
At every kind of feature extracting method, extract the feature of training set earlier, re-use the AdaBoost algorithm and carry out classification based training, obtain a sorter, use this sorter that test set is carried out class test then, input at last detects whether to comprise human body arbitrarily by altimetric image, if comprise human body then will detect the position of human body.Be 480 * 640 pixels or 640*480 pixel size by the altimetric image size wherein, scanning window is 64 * 128 pixels, and zoom factor is got [0.4,0.5,0.6,0.7,0.8,0.9].During scan image, use dense scanning, 8 pixels of directions X translation, 8 pixels of Y direction translation.At first at the convergent-divergent yardstick, the scanning entire image, therefrom extract the proper vector on all scanning window images then, carry out Classification and Identification, the synthetic testing result of group of windows that will be divided into human body at last, and show on by altimetric image former, what wherein window combination adopted is the method that main window merges, hardware platform is: Intel Core2 Duo CPU E6550 @ 2.33GHZ, 2GB RAM, software platform is MATLAB 7.2.
2. simulation result and analysis:
Fig. 3 has provided the present invention and the error attenuated comparison diagram of traditional HOG feature extracting method when sample training.Wherein C is the exercise wheel number, and Error is a training error.As can be seen from Figure 3, adopt based on the edge of curve wave conversion and the texture associating feature error when the training will be all the time error when using the HOG feature and only adopting edge feature training based on the curve wave conversion.As seen, use edge and texture associating feature based on the curve wave conversion to be more conducive to carry out the sorter training, corresponding sorter reaches the required training time of identical training error to be shortened greatly.
Table 2 has provided the present invention and traditional HOG and has only adopted Edge Gradient Feature method based on the curve wave conversion in the performance comparison result who test sample book is carried out the branch time-like.
Fig. 4 has provided the recipient's operating characteristic curve ROC that with the sorter of three kinds of method training test sample book is classified respectively.As can be seen from Figure 4 the edge feature method HOG method recall rate under the situation of identical false alarm rate before based on the curve wave conversion improves, and method of the present invention, promptly add after the texture information, recall rate improves again, has embodied its advantage on human detection.
Fig. 5 has provided some by the image of false retrieval, wherein Fig. 5 (a) is become the positive sample of negative sample by false retrieval, be owing to block, the variation of illumination and the reasons such as variation of attitude cause, Fig. 5 (b) is become the negative sample of positive sample by false retrieval, be the situation of false-alarm, because the profile or the textural characteristics of some images are similar a bit to human body.
The contrast of table 2. classification results
100 training errors of taking turns just can be found out from table 2, use feature extracting method of the present invention, are more conducive to carry out the sorter training.Simultaneously, contrast different sorters under the identical training error as can be seen to the classification results of test set, feature extracting method of the present invention is compared the HOG feature extracting method, is enhanced on classification accuracy rate, and false alarm rate also has certain reduction with respect to the HOG method.In the table 2, last classifies the averaging time that each sample characteristics extracts as, and is more longer slightly than HOG method on the used time in the feature of extracting every width of cloth image, owing to carry out the curve wave conversion to image, and extract some statistics.
Fig. 6 has provided the testing result of method of the present invention for some human body image.Wherein Fig. 6 (a) is the result to the identification of scanning window image classification, the final human detection result of Fig. 6 (b) for the scanning window that is judged as human body in the image 6 (a) is made up, and Fig. 6 (c) is the testing result of another width of cloth image.As can be seen from Figure 6, use edge and the texture associating feature extracting method based on the curve wave conversion of the present invention, can from tested person's volume image, detect human body accurately, especially on the reduction false alarm rate, be greatly improved.
Experiment shows, uses HOG feature extracting method and edge and texture associating feature extracting method based on the curve wave conversion of the present invention, all can detect human body more accurately from tested person's volume image.But feature extracting method of the present invention has higher classification accuracy rate, has overcome the high shortcoming of false alarm rate of the existing detection of HOG feature extracting method, has improved the accuracy that detects, and is very suitable for the human detection of still image.
Claims (6)
1. static human detection method based on second generation curve wave conversion comprises following process:
(1) in the INRIA database, obtains negative sample by bootstrapping operation, these negative samples other positive sample composing training sample set in database;
(2) extract the edge feature vector that training sample is concentrated each training sample, and the edge feature vector that extracts has been carried out the selection of optimum statistic based on the curve wave conversion;
(3) extract the texture feature vector that training sample is concentrated each training sample, and, constitute characteristics of human body's vector jointly the vectorial cascade of edge feature that this texture feature vector and step (2) are extracted based on the curve wave conversion;
(4) characteristics of human body's vector of all training samples in the calculation training sample set is formed the sample characteristics collection, utilizes the AdaBoost sorting algorithm that it is carried out classification based training, obtains a sorter;
(5) input arbitrarily size by altimetric image, adopt sliding window method for scanning to being scanned detection by altimetric image, and calculate the characteristics of human body's vector based on the curve wave conversion of all scanning window images, be input in the step (4) and classify in the resulting sorter;
(6) according to the classification results of sorter output, utilize the main window act of union, all scanning windows that are divided into human body are made up, form final human detection result.
2. human body detecting method according to claim 1, wherein step (1) is described in the INRIA database, obtains negative sample by the bootstrapping operation, carries out as follows:
(2a) first appointing from the INRIA database, got positive sample of a part and negative sample;
(2b) use HOG feature and align negative sample based on characteristics of human body's extracting method of curve wave conversion and carry out feature extraction respectively, and use the AdaBoost algorithm to carry out classification based training, obtain two preliminary classification devices;
(2c) use this two preliminary classification devices respectively, the non-human body image of in the test I NRIA database all the other, for these non-human body images, random choose part image and current negative sample are formed new negative sample collection in the scanning window image that is divided into human body image by mistake;
(2d) repeat (2b-2c), from the negative sample of gained, remove the negative sample that repeats, obtain final negative sample collection.
3. human body detecting method according to claim 1, wherein the described extraction training sample of step (2) is concentrated the edge feature vector based on the curve wave conversion of each training sample, and the edge feature vector that extracts carried out the selection of optimum statistic, carry out as follows:
(3a) each training sample is done fast discrete curve wave conversion, the parameter of curve wave conversion is set to real-valued curve wave conversion, and scale parameter is 3 layers, and inferior rough layer has 8 direction subbands, and detailed level is a curve wave system number;
(3b) the identical sub-band coefficients matrix of size on inferior rough layer and the detailed level is spliced to form a big matrix of coefficients, and the matrix of coefficients of each yardstick is carried out the subdivision of 8 * 8 pixels, with the fritter of each 8 * 8 pixel as a curve ripple piece;
(3c) calculate these the several statistics of energy, entropy, standard deviation, average, maximal value, minimum value and contrast of coefficient in each curve ripple piece, and the statistic of each curve ripple piece is carried out cascade, obtain initial edge feature vector; Extract the initial edge feature of all training samples, obtain a sample characteristics collection, and carry out classification based training with the AdaBoost algorithm;
Every kind of number of times that statistic is selected when (3d) statistics is trained the AdaBoost sorter, to screening in the statistic in (3c), the statistic that selected number of times is more as the statistical characteristic value of optimum is: energy, entropy, contrast, standard deviation and maximal value;
(3e) optimum statistic with coefficient in all curve ripple pieces connects, and forms a proper vector, i.e. edge feature vector.
4. human body detecting method according to claim 1, wherein the described extraction training sample of step (3) is concentrated the texture feature vector based on the curve wave conversion of each training sample, carries out as follows:
(4a) matrix of coefficients to the rough layer behind each training sample curve wave conversion adopts 1/2 overlapping method to carry out the subdivision of 8 * 8 coefficient magnitude, and the coefficient fritter of each 8 * 8 size is calculated its co-occurrence matrix, and the quantification progression of this co-occurrence matrix is 16;
(4b) for the co-occurrence matrix of the coefficient fritter of each 8 * 8 size, calculate its angle second moment, entropy, contrast, correlativity, average and and variance and this six statistics, the statistic of the co-occurrence matrix of the coefficient fritter of all 8 * 8 sizes is connect, form proper vector, i.e. a texture feature vector.
5. human body detecting method according to claim 1, characteristics of human body's vector of all training samples in the described calculation training sample set of step (4) wherein, forming the sample characteristics collection, is to utilize the AdaBoost sorting algorithm that it is carried out classification based training, and concrete steps are as follows;
(5a) the edge feature vector sum texture feature vector of each training sample that will extract carries out cascade, obtains characteristics of human body's vector of each training sample;
(5b) characteristics of human body's vector of each training sample in the calculation training sample set, suppose that characteristics of human body's vector is the vector of a M dimension, it is N that training sample is concentrated the number of training sample, the proper vector that then all training samples extract will form the matrix of a N * M dimension, as the input of AdaBoost algorithm, train a sorter.
6. human body detecting method according to claim 1, wherein the sliding window method for scanning of the described employing of step (5) is carried out as follows to being scanned detection by altimetric image:
(6a) input arbitrarily size by altimetric image, be the proportional zoom of [0.4,0.5,0.6,0.7,0.8,0.9] with it by pantograph ratio;
(6b) with behind the convergent-divergent by the altimetric image upper left corner and zone size such as a sample as first scanning window image, every to 8 pixels of right translation or downwards 8 pixels of translation obtain one group of scanning window as a new scanning window;
(6c) image to each scanning window part utilizes the method for step (2) and step (3) to calculate its edge feature vector sum texture feature vector respectively;
(6d) the edge feature vector sum texture feature vector that the scanning window parts of images is extracted carries out the proper vector that cascade obtains final scanning window image, and carries out the judgement of human body and non-human body with the resulting sorter of step (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010259562 CN101930549B (en) | 2010-08-20 | 2010-08-20 | Second generation curvelet transform-based static human detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010259562 CN101930549B (en) | 2010-08-20 | 2010-08-20 | Second generation curvelet transform-based static human detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101930549A true CN101930549A (en) | 2010-12-29 |
| CN101930549B CN101930549B (en) | 2013-02-27 |
Family
ID=43369714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010259562 Expired - Fee Related CN101930549B (en) | 2010-08-20 | 2010-08-20 | Second generation curvelet transform-based static human detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101930549B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101984440A (en) * | 2010-10-26 | 2011-03-09 | 大连工业大学 | Holographic clothes design method |
| CN102426653A (en) * | 2011-10-28 | 2012-04-25 | 西安电子科技大学 | Static human body detection method based on second generation Bandelet transformation and star type model |
| CN102810159A (en) * | 2012-06-14 | 2012-12-05 | 西安电子科技大学 | Human body detecting method based on SURF (Speed Up Robust Feature) efficient matching kernel |
| CN102902950A (en) * | 2012-06-26 | 2013-01-30 | 西安电子科技大学 | Human movement identification method based on second-generation Curvelet transformation |
| CN103870795A (en) * | 2012-12-13 | 2014-06-18 | 北京捷成世纪科技股份有限公司 | Automatic detection method and device of video rolling subtitle |
| CN103942540A (en) * | 2014-04-10 | 2014-07-23 | 杭州景联文科技有限公司 | False fingerprint detection algorithm based on curvelet texture analysis and SVM-KNN classification |
| CN104090658A (en) * | 2014-07-04 | 2014-10-08 | 四川长虹电器股份有限公司 | Human body image detection method based on HOG features |
| CN104091178A (en) * | 2014-07-01 | 2014-10-08 | 四川长虹电器股份有限公司 | Method for training human body sensing classifier based on HOG features |
| CN106127233A (en) * | 2016-06-15 | 2016-11-16 | 天津中科智能识别产业技术研究院有限公司 | A kind of eyes open detection method and the system of closed state |
| CN107589449A (en) * | 2017-08-29 | 2018-01-16 | 电子科技大学 | Three-dimensional data tomography Enhancement Method based on curve Gabor filtering |
| CN111214255A (en) * | 2020-01-12 | 2020-06-02 | 刘涛 | Medical ultrasonic image computer-aided diagnosis method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070038691A1 (en) * | 2005-04-07 | 2007-02-15 | Emmanuel Candes | Methods for performing fast discrete curvelet transforms of data |
| CN101430788A (en) * | 2008-11-19 | 2009-05-13 | 西安电子科技大学 | Lunette local Wiener filtering method based on second generation Curvelet transformation |
-
2010
- 2010-08-20 CN CN 201010259562 patent/CN101930549B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070038691A1 (en) * | 2005-04-07 | 2007-02-15 | Emmanuel Candes | Methods for performing fast discrete curvelet transforms of data |
| CN101430788A (en) * | 2008-11-19 | 2009-05-13 | 西安电子科技大学 | Lunette local Wiener filtering method based on second generation Curvelet transformation |
Non-Patent Citations (1)
| Title |
|---|
| 《系统工程与电子技术》 20100430 殷海青等 联合纹理提取和边缘检测的新方法 第32卷, 第4期 2 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101984440A (en) * | 2010-10-26 | 2011-03-09 | 大连工业大学 | Holographic clothes design method |
| CN102426653A (en) * | 2011-10-28 | 2012-04-25 | 西安电子科技大学 | Static human body detection method based on second generation Bandelet transformation and star type model |
| CN102426653B (en) * | 2011-10-28 | 2013-04-17 | 西安电子科技大学 | Static human body detection method based on second generation Bandelet transformation and star type model |
| CN102810159B (en) * | 2012-06-14 | 2014-10-29 | 西安电子科技大学 | Human body detecting method based on SURF (Speed Up Robust Feature) efficient matching kernel |
| CN102810159A (en) * | 2012-06-14 | 2012-12-05 | 西安电子科技大学 | Human body detecting method based on SURF (Speed Up Robust Feature) efficient matching kernel |
| CN102902950A (en) * | 2012-06-26 | 2013-01-30 | 西安电子科技大学 | Human movement identification method based on second-generation Curvelet transformation |
| CN103870795A (en) * | 2012-12-13 | 2014-06-18 | 北京捷成世纪科技股份有限公司 | Automatic detection method and device of video rolling subtitle |
| CN103942540A (en) * | 2014-04-10 | 2014-07-23 | 杭州景联文科技有限公司 | False fingerprint detection algorithm based on curvelet texture analysis and SVM-KNN classification |
| CN104091178A (en) * | 2014-07-01 | 2014-10-08 | 四川长虹电器股份有限公司 | Method for training human body sensing classifier based on HOG features |
| CN104090658A (en) * | 2014-07-04 | 2014-10-08 | 四川长虹电器股份有限公司 | Human body image detection method based on HOG features |
| CN106127233A (en) * | 2016-06-15 | 2016-11-16 | 天津中科智能识别产业技术研究院有限公司 | A kind of eyes open detection method and the system of closed state |
| CN107589449A (en) * | 2017-08-29 | 2018-01-16 | 电子科技大学 | Three-dimensional data tomography Enhancement Method based on curve Gabor filtering |
| CN107589449B (en) * | 2017-08-29 | 2020-04-28 | 电子科技大学 | Three-dimensional data fault enhancement method based on curve Gabor filtering |
| CN111214255A (en) * | 2020-01-12 | 2020-06-02 | 刘涛 | Medical ultrasonic image computer-aided diagnosis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101930549B (en) | 2013-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101930549B (en) | Second generation curvelet transform-based static human detection method | |
| CN103761531B (en) | The sparse coding license plate character recognition method of Shape-based interpolation contour feature | |
| CN102682287B (en) | Pedestrian detection method based on saliency information | |
| CN101859382B (en) | License plate detection and identification method based on maximum stable extremal region | |
| CN103514456B (en) | Image classification method and device based on compressed sensing multi-core learning | |
| CN105825183B (en) | Facial expression recognizing method based on partial occlusion image | |
| CN107945153A (en) | A kind of road surface crack detection method based on deep learning | |
| CN110503054B (en) | Text image processing method and device | |
| CN105160317A (en) | Pedestrian gender identification method based on regional blocks | |
| CN103902968A (en) | Pedestrian detection model training method based on AdaBoost classifier | |
| CN106778687A (en) | Method for viewing points detecting based on local evaluation and global optimization | |
| CN103366160A (en) | Objectionable image distinguishing method integrating skin color, face and sensitive position detection | |
| CN103020614B (en) | Based on the human motion identification method that space-time interest points detects | |
| CN106909946A (en) | A kind of picking system of multi-modal fusion | |
| CN101520839B (en) | Human body detection method based on second-generation strip wave conversion | |
| CN105205449A (en) | Sign language recognition method based on deep learning | |
| CN103971106A (en) | Multi-view human facial image gender identification method and device | |
| CN103186776A (en) | Human detection method based on multiple features and depth information | |
| CN103824062B (en) | Motion identification method for human body by parts based on non-negative matrix factorization | |
| CN102609715B (en) | Object type identification method combining plurality of interest point testers | |
| CN103455826A (en) | Efficient matching kernel body detection method based on rapid robustness characteristics | |
| CN103077383B (en) | Based on the human motion identification method of the Divisional of spatio-temporal gradient feature | |
| CN102129557A (en) | Method for identifying human face based on LDA subspace learning | |
| CN104268557A (en) | Polarization SAR classification method based on cooperative training and depth SVM | |
| CN104239895B (en) | SAR target identification method based on feature dimension reduction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130227 Termination date: 20180820 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |