CN105956592B - A kind of Aircraft Targets detection method based on saliency and SVM - Google Patents

A kind of Aircraft Targets detection method based on saliency and SVM Download PDF

Info

Publication number
CN105956592B
CN105956592B CN201610303628.8A CN201610303628A CN105956592B CN 105956592 B CN105956592 B CN 105956592B CN 201610303628 A CN201610303628 A CN 201610303628A CN 105956592 B CN105956592 B CN 105956592B
Authority
CN
China
Prior art keywords
window
value
aircraft
seed point
image
Prior art date
Application number
CN201610303628.8A
Other languages
Chinese (zh)
Other versions
CN105956592A (en
Inventor
李映
聂金苗
陈迪
Original Assignee
西北工业大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 西北工业大学 filed Critical 西北工业大学
Priority to CN201610303628.8A priority Critical patent/CN105956592B/en
Publication of CN105956592A publication Critical patent/CN105956592A/en
Application granted granted Critical
Publication of CN105956592B publication Critical patent/CN105956592B/en

Links

Abstract

The Aircraft Targets detection method based on saliency and SVM that the present invention relates to a kind of, there are two types of vision attention modes in salient region detection, are respectively: the attention mode of the attention mode of bottom-up (data-driven), top-down (task-driven).The present invention first extracts histograms of oriented gradients (HOG) feature of training sample, Training Support Vector Machines (SVM) classifier, then the bottom-up visual attention model using a kind of based on remaining spectral theory carries out salient region detection, there may be the candidate regions of target for rapidly extracting, then the HOG feature of candidate region is extracted, it reuses trained SVM classifier to classify to candidate region, completes target detection.

Description

A kind of Aircraft Targets detection method based on saliency and SVM

Technical field

The invention belongs to Computer Image Processing, are related to Aircraft Targets detection method, and in particular to a kind of aobvious based on image The Aircraft Targets detection method of work property and SVM.

Background technique

Visible images target detection is important one of the branch of object detection field, is had in military field particularly important Using.Currently, experts and scholars both domestic and external have done a large amount of research work in terms of Airplane detection.Than there is base earlier In the airplane detection method of image angle point and edge feature, aircraft is judged by face shaping that angle point and edge are surrounded Position.In addition, there is a kind of circle filtering for Airplane detection in the prior art in the unique shape due to aircraft in the picture Device detection method;But this method is easy to be limited by aircraft size, to the inappropriate aircraft region of scale using circle filtering The detection effect that device can not reach.And the airplane detection method based on saliency, then mainly utilize the vision of human eye System features tentatively obtain the aircraft suspicious region in image, and the inspection realized to aircraft position is then combined with target signature It surveys.

In the method based on statistical learning, it is seen that the target detection in light image is usually identified as one two classification and asks Topic, i.e., target to be detected or be target or be not target.With the methods of machine learning and feature extraction research it is continuous It deeply and is constantly applied in type target detection, existing machine learning method examines target with feature extracting method The accuracy of survey is greatly improved, but still cannot efficiently and accurately extract the candidate region in image comprising target.

Summary of the invention

Technical problems to be solved

In order to avoid the shortcomings of the prior art, the present invention proposes a kind of aircraft mesh based on saliency and SVM Detection method is marked, it is not high to solve detection accuracy by object detection field is applied to based on the image segmentation that salient region detects The problems such as.

Technical solution

A kind of Aircraft Targets detection method based on saliency and SVM, it is characterised in that steps are as follows:

Step 1, data preparation: visible light Airport Images are chosen from publicly available all kinds of images as training sample And target atlas to be detected, and grayscale image is converted to, the size of the external square of maximum of aircraft is from minimum value in figure: a1×a1, It is a to maximum value2×a2;Selected part image will be used as positive sample after the cutting of aircraft region in image as training sample, Negative sample is used as after his region cutting;Remaining parts of images is as test sample;The sample of the training is scaled a3×a3 The size of size;

Step 2: extracting the HOG feature of positive negative training sample respectively;

Step 3: by the HOG feature of each the positive negative sample extracted and its class label, positive sample 1, negative sample A vector, training SVM classifier are combined into for -1;

Step 4: the notable figure of image in test sample is obtained using the conspicuousness detection method based on remaining spectral theory;

Step 5: the connected domain in notable figure is extracted by area threshold method, generates the candidate region of Aircraft Targets, Process is as follows:

Step 5a: the mean value of notable figure is calculated firstAnd variance

Wherein, w indicates that the width of image, h indicate that the height of image, Sal (i, j) indicate the pixel of the i-th row jth column in notable figure Value;

Step 5b: the mean value of notable figure is utilizedAnd varianceThreshold value T is calculated, notable figure is divided with threshold value T;The threshold Value T:

Coefficient k is in order to which tension metrics are poorAnd mean valueWeight in threshold value T value

Step 5c, connected domain filtering is carried out to the notable figure after thresholding: is n with size1×n1Rectangular window, with the i-th row A neighborhood is intercepted centered on jth column pixel (i, j);The area that the region is defined with the number of pixels in certain region finds out place In the area of the marking area in the contiguous range;If the area is greater than certain threshold value, just retains the region, otherwise do not protect It stays;Using all regions remained as the candidate region of Aircraft Targets;

Step 6: Aircraft Targets are extracted from the candidate region of Aircraft Targets, process is as follows:

Step 6a, response matrix is constructed:

A two-dimensional response matrix M is constructed, the value of each element is a two-dimensional array M in matrixi,j(s, r) its Middle i ∈ [1, w], j ∈ [1, h], s are used for record window size, and r is used to record SVM caused by the window there are Aircraft Targets Response;When initialization, which is initialized as a full 0 matrix identical with image size;

Using the local pixel maximum of any candidate region as the center of the candidate region, referred to as: seed point;

Step 6b, secondary windows method rejects invalid seed point, retains most probable aircraft region, process is as follows:

(A) determine first time image block window: window is a rectangular window centered on seed point, the size of window For h1×h1, in which:

Wherein, int () function representation round.Original image is intercepted with the window, the figure that will be truncated to As block is scaled a3×a3Size extracts the HOG feature of image block, then HOG feature is updated in SVM classifier, calculates SVM classifier response r1

(B) determine second of image block window: window is a rectangular window centered on seed point, the size of window For h2×h2, in which:

h2=2 (h1-1)+1

Original image is intercepted with the window, the image block being truncated to is scaled a3×a3Size extracts image block Then HOG feature is updated in SVM classifier by HOG feature, calculate SVM classifier response r2

(C) judge whether to retain the region:

If the classifier response being calculated twice is respectively less than 0, then it is assumed that the corresponding aircraft candidate regions of the seed point Domain is invalid, therefore rejects the invalid seed point;

Otherwise it is assumed that the region that window includes there are aircraft or contains most of fuselage of aircraft, by two secondary response In the larger value assignment into response matrix on the corresponding coordinate position of seed point, the referred to as seed point of response matrix, and recording The lower corresponding window size of the response;Specifically, if changing coordinates are as follows: (u, v), the SVM classifier response that needs are recorded, It is assigned to the r value at the seed point of response matrix in the two-dimensional array of element M (u, v);Corresponding interception window when the response will be generated Square side length value in mouth size, is assigned to the s value at the seed point of response matrix in the two-dimensional array of element M (u, v);

Step 6c, optimize response matrix, determine aircraft region:

(1) optimize the window size recorded in each seed point:

To the seed point of each response matrix, transformed edge of window long value h is first calculated according to the following formula3:

Centered on the coordinate at the seed point of response matrix, with h3×h3Interception window is established to original image for window size As being intercepted, the image block being truncated to is scaled a3×a3Size extracts the HOG feature of image block, then by HOG feature It is updated in SVM classifier, calculates SVM classifier response r3

Transformed edge of window long value h is calculated further according to following formula4:

Centered on the coordinate at the seed point of response matrix, with h4×h4Interception window is established to original image for window size As being intercepted, the image block being truncated to is scaled a3×a3Size extracts the HOG feature of image block, then by HOG feature It is updated in SVM classifier, calculates SVM classifier response r4

Find out r, r3,r4In maximum value, replace at the seed point of response matrix original r value in the two-dimensional array of element, With original s value in the two-dimensional array of element at the seed point of the corresponding edge of window long value replacement response matrix of the new r value;

It determines aircraft region, obtains final target detection result;

(2) according to the response matrix after optimization, the coordinate recorded using at the seed point of response matrix is as winged in original image The center of square area where machine target, pros where the s value recorded using at the seed point as Aircraft Targets in original image The side length in shape region can determine each aircraft region, obtain final Aircraft Targets testing result.

Beneficial effect

A kind of Aircraft Targets detection method based on saliency and SVM proposed by the present invention, salient region detection In there are two types of vision attention mode, be respectively: the attention mode of bottom-up (data-driven), top-down (task-driven) Pay attention to mode.The present invention first extracts histograms of oriented gradients (HOG) feature of training sample, Training Support Vector Machines (SVM) point Class device, then the bottom-up visual attention model using a kind of based on remaining spectral theory carries out salient region detection, fastly There may be the candidate regions of target for speed extraction, then extract the HOG feature of candidate region, reuse trained svm classifier Device classifies to candidate region, completes target detection.

The present invention will dexterously be tied based on the detection of the saliency of remaining spectral theory and the learning method of support vector machines Altogether, the selection for improving target area improves the robustness of detection accuracy and detection, and model is simple, and execution efficiency is high.

Detailed description of the invention

Fig. 1: the training flow chart of the detection network based on SVM

Fig. 2: the visible images Airplane detection flow chart based on saliency and SVM

Specific embodiment

Now in conjunction with embodiment, attached drawing, the invention will be further described:

Steps are as follows for embodiment:

Step 1: data preparation.

Visible light Airport Images are intercepted from GOOGLE-EARTH as training sample and target to be detected, are uniformly converted to Grayscale image, the size of the external square of maximum of aircraft is from minimum value in figure: a1×a1, until maximum value is a2×a2Differ.At this In embodiment, a1=20, a2=80.From the image after these interceptions, positive negative sample (each 2000) of the acquisition for training, Manually mark its aircraft region.Positive sample is the aircraft of various postures, different model, and negative sample is to build present in airport The intersection etc. of road in mark, airplane tail group, airport in object, airport.In training, sample standard deviation used is uniformly contracted It puts as a3×a3The size of size does not need to cut for every width test image.In the present embodiment, a3=64.

Step 2: extracting the HOG feature of positive negative training sample.

First using Gamma correction method to after scaling having a size of a3×a3Image normalization.Then by image uniform It is divided into b1×b1A " cell " (cell), the size of each cell are c1×c1A pixel, in which: c1=a3/b1.For just In calculating, usually by a3,b1,c1Value be adjusted to integer value, in the present embodiment, b1=8, c1=8.It finds out each in cell The gradient direction of pixel projects in corresponding histogram according to the amplitude weighting of its gradient direction, a cell pair Answer the vector of a N-dimensional (N=9 here extracts 9 dimensional features from each cell).Then take b2×b2A cell combination At a block (block), the interval between block and the initial position of block takes d1A pixel, so that mutual is overlapped between block, block Selection sequence are as follows: first from left to right, then from top to bottom.In the present embodiment, b2=2, d1=8, it may be assumed that horizontal direction and Vertical Square To there is 7 blocks respectively, so that image includes 49 blocks altogether.Each cell still takes N-dimensional feature, and the feature of block is by the straight of cell Square figure feature vector is composed in series according to putting in order for cell;The HOG feature of whole image is then by each piece of HOG feature Vector is composed in series.In the present embodiment, have 9 × 2 × 2 totally 36 dimensional feature, entire normalized image share 36 × 49 for each piece Totally 1764 dimensional feature.

Step 3: by the HOG feature of each the positive negative sample extracted in previous step and its class label, (positive sample is 1, negative sample is -1) it is combined into a vector, training SVM classifier.The kernel function of SVM is using radial base core letter in the present embodiment Number.

Step 4: after training, obtaining the significant of test image using the conspicuousness detection method based on remaining spectral theory Figure.

(1) width of gray level image I to be detected is set as w pixel, is highly h pixel, to the pixel of image

Set I (x) (wherein [0,255] I (x) ∈, x ∈ [1, w*h]) carries out Fourier transformation F (I (x)), and extracts figure Picture frequency

The phase property and amplitude characteristic in domain;

A (f)=R (F (I (x))) (1)

P (f)=S (F (I (x))) (2)

Wherein, A (f) indicates that the amplitude of frequency f, P (f) indicate the phase of frequency f, and R (F (I (x))) expression takes F (I (x)) Amplitude, S (F (I (x))) expression take F (I (x)) phase.

(2) log of calculated amplitude composes L (f), and composes to log and carry out mean filter, the residual spectra R (f) for then asking log to compose:

L (f)=log (A (f)) (3)

R (f)=L (f)-hn(f)*L(f) (4)

H in above formulanIt (f) be size is n × n (in the present embodiment select 3 × 3 sizes) mean filter convolution kernel, definition For

(3) residual spectra is acquired to new image spectrum in conjunction with phase spectrum, Fourier inversion is carried out to the image spectrum New image is acquired, and image smoothing is carried out using Gaussian convolution core to obtained image, can be obtained based on remaining spectral theory Image saliency map S (x):

S (x)=g (x) * F-1[exp(R(f)+P(f))]2 (5)

In above formula, F-1It (f) is Fourier inversion, g (x) indicates Gaussian convolution core.

Step 5: the connected domain in notable figure being extracted by area threshold method, the candidate regions of Aircraft Targets are generated with this Domain.

(1) mean value of notable figure is calculated firstAnd variance

Wherein, w indicates that the width of image, h indicate that the height of image, Sal (i, j) indicate the pixel of the i-th row jth column in notable figure Value.

(2) mean value of notable figure is utilizedAnd varianceThreshold value T is calculated, notable figure is divided with threshold value T.Here threshold value T:

Coefficient k is in order to which tension metrics are poorAnd mean valueWeight in threshold value T value, in the present embodiment:The such value of k can make threshold value T and standard deviationMeet certain inverse proportionality characteristics, the difference that debases the standard is excessive When influence to threshold value, or can the influence appropriate that increase standard deviation when standard deviation is too small.

(3) connected domain filtering is carried out to the notable figure after thresholding.It is n with size1×n1Rectangular window, with the i-th row jth A neighborhood, in the present embodiment, n are intercepted centered on column pixel (i, j)1=11.The area is defined with the number of pixels in certain region The area in domain can find out the area of the marking area in the contiguous range.If the area is greater than certain threshold value (this reality It applies in example, 60) threshold value takes, just retain the region, otherwise do not retain.Using all regions remained as the time of Aircraft Targets Favored area.

Step 6: extracting Aircraft Targets from the candidate region of Aircraft Targets.

(1) response matrix is constructed

A two-dimensional response matrix M is constructed, the value of each element is a two-dimensional array M in matrixi,j(s, r) its Middle i ∈ [1, w], j ∈ [1, h], s are used for record window size, and r is used to record SVM caused by the window there are Aircraft Targets Response.When initialization, which is initialized as a full 0 matrix identical with image size.

Using the local pixel maximum of some candidate region as the center of the candidate region, referred to as: seed point (that is: may be used There can be the regional center position of Aircraft Targets).

(2) invalid seed point is rejected, most probable aircraft region is retained

For the accuracy rate for improving screening, the present invention proposes a kind of secondary windows method, specific as follows:

(A) first time image block window is determined

The window is a rectangular window centered on seed point, and the size of window is h1×h1, in which:

Wherein, int () function representation round.Original image is intercepted with the window, the figure that will be truncated to As block is scaled a3×a3Size extracts the HOG feature of image block, then HOG feature is updated in SVM classifier, calculates SVM classifier response r1

(B) second of image block window is determined

The window is a rectangular window centered on seed point, and the size of window is h2×h2, in which:

h2=2 (h1-1)+1 (10)

Original image is intercepted with the window, the image block being truncated to is scaled a3×a3Size extracts image block Then HOG feature is updated in SVM classifier by HOG feature, calculate SVM classifier response r2

(C) judge whether to retain the region

If the classifier response being calculated twice is respectively less than 0, then it is assumed that the corresponding aircraft candidate regions of the seed point Domain is invalid, therefore rejects the invalid seed point.

Otherwise it is assumed that the region that window includes there are aircraft or contains most of fuselage of aircraft, this can be rung twice For the larger value assignment answered into the response matrix on the corresponding coordinate position of seed point, which is known as the seed of response matrix Point, and record the corresponding window size of the response.Specifically, if changing coordinates are as follows: (u, v), the svm classifier that needs are recorded Device response is assigned to the r value at the seed point of response matrix in the two-dimensional array of element M (u, v);It will generate corresponding when the response Interception window size in square side length value, be assigned at the seed point of response matrix in the two-dimensional array of element M (u, v) S value.

(3) optimize response matrix, determine aircraft region

(A) optimize the window size recorded in each seed point

To the seed point of each response matrix, transformed edge of window long value h is first calculated according to the following formula3:

Centered on the coordinate at the seed point of response matrix, with h3×h3Interception window is established to original image for window size As being intercepted, the image block being truncated to is scaled a3×a3Size extracts the HOG feature of image block, then by HOG feature It is updated in SVM classifier, calculates SVM classifier response r3

Transformed edge of window long value h is calculated further according to following formula4:

Centered on the coordinate at the seed point of response matrix, with h4×h4Interception window is established to original image for window size As being intercepted, the image block being truncated to is scaled a3×a3Size extracts the HOG feature of image block, then by HOG feature It is updated in SVM classifier, calculates SVM classifier response r4

Find out r, r3,r4In maximum value, replace at the seed point of response matrix original r value in the two-dimensional array of element, With original s value in the two-dimensional array of element at the seed point of the corresponding edge of window long value replacement response matrix of the new r value.

(B) it determines aircraft region, obtains final target detection result

According to the response matrix after optimization, the coordinate recorded using at the seed point of response matrix is as aircraft mesh in original image The center of square area where mark, square region where the s value recorded using at the seed point as Aircraft Targets in original image The side length in domain can determine each aircraft region, obtain final Aircraft Targets testing result.

Claims (1)

1. a kind of Aircraft Targets detection method based on saliency and SVM, it is characterised in that steps are as follows:
Step 1, data preparation: from publicly available all kinds of images choose visible light Airport Images as training sample and to Target atlas is detected, and is converted to grayscale image, the size of the external square of maximum of aircraft is from minimum value in figure: a1×a1, until most Big value is a2×a2;Selected part image will be used as positive sample, other areas after the cutting of aircraft region in image as training sample Negative sample is used as after the cutting of domain;Remaining parts of images is as test sample;The sample of the training is scaled a3×a3Size Size;
Step 2: extracting the HOG feature of positive negative training sample respectively;
Step 3: by the HOG feature of each the positive negative sample extracted and its class label, positive sample 1, negative sample is -1 It is combined into a vector, training SVM classifier;
Step 4: the notable figure of image in test sample is obtained using the conspicuousness detection method based on remaining spectral theory;
Step 5: the connected domain in notable figure being extracted by area threshold method, generates the candidate region of Aircraft Targets, process It is as follows:
Step 5a: the mean value of notable figure is calculated firstAnd variance
Wherein, w indicates that the width of image, h indicate that the height of image, Sal (i, j) indicate the pixel value of the i-th row jth column in notable figure;
Step 5b: the mean value of notable figure is utilizedAnd varianceThreshold value T is calculated, notable figure is divided with threshold value T;The threshold value T:
Coefficient k is in order to which tension metrics are poorAnd mean valueWeight in threshold value T value
Step 5c, connected domain filtering is carried out to the notable figure after thresholding: is n with size1×n1Rectangular window, with the i-th row jth A neighborhood is intercepted centered on column pixel (i, j);The area that the region is defined with the number of pixels in certain region is found out in institute State the area of the marking area in contiguous range;If the area is greater than certain threshold value, just retains the region, otherwise do not retain; Using all regions remained as the candidate region of Aircraft Targets;
Step 6: Aircraft Targets are extracted from the candidate region of Aircraft Targets, process is as follows:
Step 6a, response matrix is constructed:
A two-dimensional response matrix M is constructed, the value of each element is a two-dimensional array M in matrixi,j(s, r) wherein i ∈ [1, w], j ∈ [1, h], s are used for record window size, and r is used to record the response of SVM caused by the window there are Aircraft Targets; When initialization, which is initialized as a full 0 matrix identical with image size;
Using the local pixel maximum of any candidate region as the center of the candidate region, referred to as: seed point;
Step 6b, secondary windows method rejects invalid seed point, retains most probable aircraft region, process is as follows:
(A) determine first time image block window: window is a rectangular window centered on seed point, and the size of window is h1 ×h1, in which:
Wherein, int () function representation round;Original image is intercepted with the window, the image block that will be truncated to It is scaled a3×a3Size extracts the HOG feature of image block, then HOG feature is updated in SVM classifier, calculates SVM points Class device response r1
(B) determine second of image block window: window is a rectangular window centered on seed point, and the size of window is h2 ×h2, in which:
h2=2 (h1-1)+1
Original image is intercepted with the window, the image block being truncated to is scaled a3×a3Size extracts the HOG of image block Then HOG feature is updated in SVM classifier by feature, calculate SVM classifier response r2
(C) judge whether to retain the region:
If the classifier response being calculated twice is respectively less than 0, then it is assumed that the corresponding aircraft candidate region of the seed point without Effect, therefore reject the invalid seed point;
Otherwise it is assumed that the region that window includes there are aircraft or contains most of fuselage of aircraft, it will be in two secondary response On the corresponding coordinate position of the larger value assignment seed point into response matrix, the referred to as seed point of response matrix, and record this Respond corresponding window size;Specifically, if changing coordinates are as follows: (u, v), the SVM classifier response that needs are recorded are assigned to R value at the seed point of response matrix in the two-dimensional array of element M (u, v);Corresponding interception window ruler when the response will be generated Square side length value in very little, is assigned to the s value at the seed point of response matrix in the two-dimensional array of element M (u, v);
Step 6c, optimize response matrix, determine aircraft region:
(1) optimize the window size recorded in each seed point:
To the seed point of each response matrix, transformed edge of window long value h is first calculated according to the following formula3:
Centered on the coordinate at the seed point of response matrix, with h3×h3For window size establish interception window to original image into Row interception, is scaled a for the image block being truncated to3×a3Size extracts the HOG feature of image block, then substitutes into HOG feature Into SVM classifier, SVM classifier response r is calculated3
Transformed edge of window long value h is calculated further according to following formula4:
Centered on the coordinate at the seed point of response matrix, with h4×h4For window size establish interception window to original image into Row interception, is scaled a for the image block being truncated to3×a3Size extracts the HOG feature of image block, then substitutes into HOG feature Into SVM classifier, SVM classifier response r is calculated4
Find out r, r3,r4In maximum value, original r value in the two-dimensional array of element is replaced at the seed point of response matrix, with new R value corresponding edge of window long value replacement response matrix seed point at element two-dimensional array in original s value;
It determines aircraft region, obtains final target detection result;
(2) according to the response matrix after optimization, the coordinate recorded using at the seed point of response matrix is as aircraft mesh in original image The center of square area where mark, square region where the s value recorded using at the seed point as Aircraft Targets in original image The side length in domain can determine each aircraft region, obtain final Aircraft Targets testing result.
CN201610303628.8A 2016-05-10 2016-05-10 A kind of Aircraft Targets detection method based on saliency and SVM CN105956592B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610303628.8A CN105956592B (en) 2016-05-10 2016-05-10 A kind of Aircraft Targets detection method based on saliency and SVM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610303628.8A CN105956592B (en) 2016-05-10 2016-05-10 A kind of Aircraft Targets detection method based on saliency and SVM

Publications (2)

Publication Number Publication Date
CN105956592A CN105956592A (en) 2016-09-21
CN105956592B true CN105956592B (en) 2019-03-29

Family

ID=56914362

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610303628.8A CN105956592B (en) 2016-05-10 2016-05-10 A kind of Aircraft Targets detection method based on saliency and SVM

Country Status (1)

Country Link
CN (1) CN105956592B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831402A (en) * 2012-08-09 2012-12-19 西北工业大学 Sparse coding and visual saliency-based method for detecting airport through infrared remote sensing image
CN104834933A (en) * 2014-02-10 2015-08-12 华为技术有限公司 Method and device for detecting salient region of image
CN104992183A (en) * 2015-06-25 2015-10-21 中国计量学院 Method for automatic detection of substantial object in natural scene

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8224078B2 (en) * 2000-11-06 2012-07-17 Nant Holdings Ip, Llc Image capture and identification system and process

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831402A (en) * 2012-08-09 2012-12-19 西北工业大学 Sparse coding and visual saliency-based method for detecting airport through infrared remote sensing image
CN104834933A (en) * 2014-02-10 2015-08-12 华为技术有限公司 Method and device for detecting salient region of image
CN104992183A (en) * 2015-06-25 2015-10-21 中国计量学院 Method for automatic detection of substantial object in natural scene

Also Published As

Publication number Publication date
CN105956592A (en) 2016-09-21

Similar Documents

Publication Publication Date Title
Kalogerakis et al. Learning 3D mesh segmentation and labeling
Ke et al. A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing
Sirmacek et al. Urban-area and building detection using SIFT keypoints and graph theory
Al Bashish et al. Detection and classification of leaf diseases using K-means-based segmentation and
Al Bashish et al. A framework for detection and classification of plant leaf and stem diseases
Secord et al. Tree detection in urban regions using aerial lidar and image data
EP1944731A2 (en) Method and apparatus for detecting objects in an image
US20110081081A1 (en) Method for recognizing objects in images
Quelhas et al. Cell nuclei and cytoplasm joint segmentation using the sliding band filter
Marchesi et al. A context-sensitive technique robust to registration noise for change detection in VHR multispectral images
Wang et al. A multiscale and hierarchical feature extraction method for terrestrial laser scanning point cloud classification
CN101859382A (en) License plate detection and identification method based on maximum stable extremal region
Huang et al. New postprocessing methods for remote sensing image classification: A systematic study
Ming et al. Semivariogram-based spatial bandwidth selection for remote sensing image segmentation with mean-shift algorithm
Chen et al. Vehicle detection in high-resolution aerial images via sparse representation and superpixels
CN103577475B (en) An image-automated classification method, image processing method and apparatus
Hussin et al. Digital image processing techniques for object detection from complex background image
CN102214298B (en) Method for detecting and identifying airport target by using remote sensing image based on selective visual attention mechanism
Zhang et al. A multilevel point-cluster-based discriminative feature for ALS point cloud classification
Lin et al. A multi-level morphological active contour algorithm for delineating tree crowns in mountainous forest
Li et al. A spatial clustering method with edge weighting for image segmentation
Huijuan et al. Fast image matching based-on improved SURF algorithm
US9092696B2 (en) Image sign classifier
US9824258B2 (en) Method and apparatus for fingerprint identification
US8379994B2 (en) Digital image analysis utilizing multiple human labels

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
GR01 Patent grant