CN108629754A - ISAR image self-adaptive detail enhancement method - Google Patents
ISAR image self-adaptive detail enhancement method Download PDFInfo
- Publication number
- CN108629754A CN108629754A CN201810414603.4A CN201810414603A CN108629754A CN 108629754 A CN108629754 A CN 108629754A CN 201810414603 A CN201810414603 A CN 201810414603A CN 108629754 A CN108629754 A CN 108629754A
- Authority
- CN
- China
- Prior art keywords
- level
- amplitude
- isar image
- isar
- histogram
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000006835 compression Effects 0.000 claims abstract description 21
- 238000007906 compression Methods 0.000 claims abstract description 21
- 230000003044 adaptive effect Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
本发明提供一种ISAR图像自适应细节增强方法。技术方案包括下述步骤：S1：求取ISAR图像的L级灰度直方图；S2：空幅度级压缩；S3：条件判断；S4：低概率幅度级压缩；S5：高概率幅度级扩展；S6：灰度映射。本发明针对空间目标ISAR图像动态范围大且在高幅度区稀疏、直方图冗余的特点，自适应地进行冗余幅度级压缩和高概率幅度级扩展，在保留目标细节信息不丢失的情况下有效提高目标灰度图像的局部对比度，提高目标ISAR图像的视觉效果，提升目标识别能力，具有重要工程应用价值。
The invention provides an ISAR image adaptive detail enhancement method. The technical solution includes the following steps: S1: obtain the L-level gray histogram of the ISAR image; S2: empty amplitude-level compression; S3: condition judgment; S4: low-probability amplitude-level compression; S5: high-probability amplitude-level expansion; S6 : grayscale map. Aiming at the characteristics of large dynamic range, sparseness in high-amplitude areas and redundant histograms of spatial target ISAR images, the present invention adaptively performs redundant amplitude-level compression and high-probability amplitude-level expansion, while retaining target detail information without loss Effectively improve the local contrast of the target grayscale image, improve the visual effect of the target ISAR image, and improve the target recognition ability, which has important engineering application value.
Description
技术领域technical field
本发明涉及ISAR(Inverse Synthetic Aperture Radar，逆合成孔径雷达)图像处理技术，尤其涉及一种基于冗余幅度级压缩和高概率幅度级扩展的ISAR图像自适应细节增强方法。The present invention relates to ISAR (Inverse Synthetic Aperture Radar, Inverse Synthetic Aperture Radar) image processing technology, in particular to an ISAR image adaptive detail enhancement method based on redundant amplitude level compression and high probability amplitude level expansion.
背景技术Background technique
与光学图像不同，ISAR图像在成像过程中受目标特性、雷达系统、环境噪声以及成像算法等多种因素的影响，通常表现为孤立的散射中心分布，具有稀疏性、动态范围大、对比度较低等特点。这使得后续的图像分析、解译面临很大的难度，因此在进行后续处理前，对ISAR图像进行细节增强处理显得十分必要。Different from optical images, ISAR images are affected by many factors such as target characteristics, radar system, environmental noise, and imaging algorithms during the imaging process, and usually appear as isolated scattering center distribution, with sparseness, large dynamic range, and low contrast. Features. This makes subsequent image analysis and interpretation very difficult, so it is very necessary to enhance the details of ISAR images before subsequent processing.
现有的图像细节增强方法主要应用于光学图像。如Gamma校正方法，参见文献(彭国福,林正浩.图像处理中Gamma校正的研究和实现[J].电子工程师,2006,(2):30-32,36.)。这种方法通过一个特定的Gamma变换算子来改善图像对比度。但是这种方法应用于具有稀疏性、动态范围大的ISAR图像细节增强时，难以取得令人满意的效果。如直方图均衡化法，参见文献(张锐,贾娜.海域图像增强方法综述[J].液晶与显示,2017,(10):828-834.)，则通过使图像灰度级的概率密度函数满足近似均匀分布的形式来增大图像动态范围和提高图像对比度，对于动态范围已经很大的ISAR图像而言，难以实现细节增强，而对目标主体的增强甚至会削弱图像的可视性。目前，尚未查到有关ISAR图像细节增强方法的相关资料。Existing image detail enhancement methods are mainly applied to optical images. For example, the Gamma correction method, see the literature (Peng Guofu, Lin Zhenghao. Research and implementation of Gamma correction in image processing [J]. Electronic Engineer, 2006, (2): 30-32, 36.). This method improves image contrast through a specific Gamma transformation operator. However, it is difficult to achieve satisfactory results when this method is applied to ISAR image detail enhancement with sparsity and large dynamic range. For example, the histogram equalization method, see the literature (Zhang Rui, Jia Na. A review of sea area image enhancement methods [J]. Liquid Crystal and Display, 2017, (10): 828-834.), then by making the probability of the gray level of the image The density function satisfies the form of approximately uniform distribution to increase the dynamic range of the image and improve the image contrast. For ISAR images with a large dynamic range, it is difficult to achieve detail enhancement, and the enhancement of the target subject may even weaken the visibility of the image. . At present, there is no relevant information about the method of ISAR image detail enhancement.
发明内容Contents of the invention
针对上述技术中存在的问题，本发明提出一种基于冗余幅度级压缩和高概率幅度级扩展的ISAR图像自适应细节增强方法。该方法利用ISAR图像的稀疏性，对ISAR灰度图像冗余幅度级进行压缩，对高概率幅度级进行扩展，实现图像自适应细节增强，可以有效提高目标ISAR图像的视觉效果，丰富目标细节信息。Aiming at the problems existing in the above technologies, the present invention proposes an ISAR image adaptive detail enhancement method based on redundant amplitude level compression and high probability amplitude level expansion. This method utilizes the sparsity of the ISAR image to compress the redundant amplitude levels of the ISAR gray image and expand the high-probability amplitude levels to achieve image adaptive detail enhancement, which can effectively improve the visual effect of the target ISAR image and enrich the target detail information .
本发明采用的技术方案为：一种基于冗余幅度级压缩和高概率幅度级扩展的ISAR图像自适应细节增强方法，该方法包括以下步骤：The technical solution adopted by the present invention is: a method for adaptive detail enhancement of ISAR images based on redundant amplitude level compression and high probability amplitude level expansion, the method comprising the following steps:
设获得的ISAR图像G在坐标(m,n)处的灰度值g(m,n)，其中m∈[1,M]、n∈[1,N]，M和N分别表示ISAR图像G在方位向和距离向的分辨单元数。Suppose the gray value g(m,n) of the obtained ISAR image G at coordinates (m,n), where m∈[1,M], n∈[1,N], M and N respectively represent the ISAR image G The number of resolution units in the azimuth and range directions.
S1：求取ISAR图像的L级灰度直方图S1: Find the L-level gray histogram of the ISAR image
将ISAR图像G的灰度范围均匀划分为L级，得到ISAR图像G对应的L级灰度直方图。幅度级数L的取值根据ISAR图像的灰度范围大小确定。The gray scale range of ISAR image G is evenly divided into L levels, and the L level gray level histogram corresponding to ISAR image G is obtained. The value of the amplitude series L is determined according to the gray scale range of the ISAR image.
S2：空幅度级压缩S2: Null Amplitude Level Compression
删除L级灰度直方图中包含像素数目为0的幅度级，得到幅度级数为L′的L′级灰度直方图。Delete the amplitude level whose number of pixels is 0 in the L level gray level histogram, and obtain the L' level gray level histogram whose amplitude level is L'.
S3：条件判断S3: Condition judgment
如果L′小于设定的最终级数L0，则执行S5；如果L′大于设定的最终级数L0，则执行S4；否则，执行S6。最终级数L0的取值根据需要量化的灰度级数确定，一般取L0＝256。If L' is smaller than the set final number of stages L 0 , execute S5; if L' is greater than the set final number of stages L 0 , execute S4; otherwise, execute S6. The value of the final number of levels L 0 is determined according to the number of gray levels to be quantized, and generally L 0 =256.
S4：低概率幅度级压缩S4: low-probability magnitude-level compression
S4.1对出现频率最低的幅度级进行压缩处理，即将该幅度级与其相邻的出现频率较低的幅度级合并。S4.1 Perform compression processing on the amplitude level with the lowest frequency of occurrence, that is, merge the amplitude level with its adjacent amplitude level with a lower frequency of occurrence.
S4.2统计压缩处理后新的幅度级数和对应的幅度级灰度直方图，若新的幅度级数等于设定的最终级数L0，则执行S6；否则，执行S4.1。S4.2 Statistically compress the new amplitude series and the corresponding amplitude level gray histogram. If the new amplitude series is equal to the set final series L 0 , execute S6; otherwise, execute S4.1.
S5：高概率幅度级扩展S5: High Probability Magnitude-Level Expansion
S5.1对出现频率最高的幅度级进行扩展处理，即将该幅度级对应的灰度区间均匀划分得到两个新的幅度级。S5.1 Extend the amplitude level with the highest frequency of occurrence, that is, evenly divide the gray scale interval corresponding to the amplitude level to obtain two new amplitude levels.
S5.2统计扩展处理后新的幅度级灰度直方图，若新的幅度级数等于设定的最终级数L0，则执行S6；否则，执行S5.1。S5.2 Statistically expand the new amplitude level gray histogram, if the new amplitude level is equal to the set final level L 0 , execute S6; otherwise, execute S5.1.
S6：灰度映射S6: Grayscale Mapping
L0级灰度直方图对应的ISAR图像G′，即为增强后的结果。The ISAR image G' corresponding to L0 -level grayscale histogram is the enhanced result.
本发明的有益效果：通过本发明的方法处理，针对空间目标ISAR图像动态范围大且在高幅度区稀疏、直方图冗余的特点，自适应地进行冗余幅度级压缩和高概率幅度级扩展，在保留目标细节信息不丢失的情况下有效提高目标灰度图像的局部对比度，提高目标ISAR图像的视觉效果，提升目标识别能力，具有重要工程应用价值。Beneficial effects of the present invention: through processing by the method of the present invention, aiming at the characteristics of large dynamic range, sparseness in high-amplitude areas, and redundant histograms of spatial target ISAR images, redundant amplitude-level compression and high-probability amplitude-level expansion are adaptively performed , effectively improve the local contrast of the target grayscale image without losing the target detail information, improve the visual effect of the target ISAR image, and improve the target recognition ability, which has important engineering application value.
附图说明Description of drawings
图1为本发明处理流程；Fig. 1 is the processing flow of the present invention;
图2是进行仿真实验获得的灰度直方图；Figure 2 is a grayscale histogram obtained from a simulation experiment;
图3是进行对比实验的结果。Figure 3 is the result of a comparative experiment.
具体实施方式Detailed ways
下面结合附图对本发明的具体实施方式进行进一步描述。Specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
图1为本发明处理流程。图2为本发明基于冗余幅度级压缩和高概率幅度级扩展的图像增强示意图。Fig. 1 is the processing flow of the present invention. Fig. 2 is a schematic diagram of image enhancement based on redundant amplitude-level compression and high-probability amplitude-level expansion in the present invention.
本发明所述一种基于冗余幅度级压缩和高概率幅度级扩展的ISAR图像自适应细节增强方法，该方法包括以下步骤：According to the present invention, an ISAR image adaptive detail enhancement method based on redundant amplitude level compression and high probability amplitude level expansion, the method comprises the following steps:
S1：求取ISAR图像的L级灰度直方图。S1: Obtain the L-level gray histogram of the ISAR image.
将ISAR图像G的灰度范围均匀划分为L级，得到ISAR图像G对应的L级灰度直方图。幅度级数L的取值根据ISAR图像的幅度范围大小确定。其中，均匀划分的含义是使得灰度直方图的每个幅度级对应的灰度范围区间的长度一致。The gray scale range of ISAR image G is evenly divided into L levels, and the L level gray level histogram corresponding to ISAR image G is obtained. The value of the amplitude series L is determined according to the amplitude range of the ISAR image. Wherein, the meaning of uniform division is to make the lengths of the gray range intervals corresponding to each amplitude level of the gray histogram consistent.
S2：空幅度级压缩S2: Null Amplitude Level Compression
删除L级灰度直方图中包含像素数目为0的幅度级，得到幅度级数为L′的灰度直方图。Delete the amplitude level whose number of pixels is 0 in the L level gray level histogram, and obtain the gray level histogram whose amplitude level is L'.
S3：条件判断S3: Condition judgment
通过条件判断，决定是进行低概率幅度级压缩和高概率幅度级扩展，还是终止技术方案。Through condition judgment, it is decided whether to carry out low-probability amplitude-level compression and high-probability amplitude-level expansion, or to terminate the technical solution.
S4：低概率幅度级压缩S4: low-probability magnitude-level compression
如果进行幅度级压缩，则对出现频率最低的幅度级进行压缩处理，出现频率最低的幅度级是指该幅度级(即灰度区间)包含像素数目最少的幅度级。将该幅度级与其相邻的出现频率较低的幅度级合并，是指从与该幅度级在灰度区间上相邻的两个(或1个)幅度级中，选择包含像素较少的幅度级进行合并。新的幅度级包括的灰度区间是两个被合并的幅度级的灰度区间的和。If amplitude level compression is performed, the amplitude level with the lowest frequency of occurrence is compressed, and the amplitude level with the lowest frequency of occurrence means that the amplitude level (ie, the gray scale interval) contains the least number of pixels. Combining the amplitude level with its adjacent amplitude level with a lower frequency of occurrence refers to selecting the amplitude level with fewer pixels from the two (or one) amplitude levels adjacent to the amplitude level in the gray scale interval levels are merged. The gray scale interval included in the new amplitude level is the sum of the gray scale intervals of the two combined amplitude levels.
S5：高概率幅度级扩展S5: High Probability Magnitude-Level Expansion
对出现频率最高的幅度级进行扩展处理，即将该幅度级对应的灰度区间进行均匀划分得到两个新的灰度区间，每个灰度区间对应一个新的幅度级。统计落入新的幅度级的像素数，从而得到新的幅度级灰度直方图。The amplitude level with the highest frequency of occurrence is extended, that is, the gray-scale interval corresponding to the amplitude level is evenly divided to obtain two new gray-scale intervals, and each gray-scale interval corresponds to a new amplitude level. Count the number of pixels falling into the new amplitude level, so as to obtain the new amplitude level gray histogram.
S6：灰度映射S6: Grayscale Mapping
图2是进行仿真实验获得的灰度直方图。图2-(a)是实验中使用的ISAR图像对应的原始的灰度直方图，幅度级数L＝1024。在形成灰度直方图时，通过Imhist函数划分为1024个级别。图2-(b)是利用本发明基于冗余幅度级压缩和高概率幅度级扩展后得到的灰度直方图；此时幅度级数包括L0＝256个级别。从图中可以看出，通过利用本发明，直方图在去掉冗余后得到扩展，在保留目标细节信息不丢失的情况下有效提高目标灰度图像的局部对比度。Figure 2 is the gray histogram obtained from the simulation experiment. Figure 2-(a) is the original grayscale histogram corresponding to the ISAR image used in the experiment, and the amplitude series L=1024. When forming a grayscale histogram, it is divided into 1024 levels by Imhist function. Fig. 2-(b) is a gray histogram obtained by using the present invention based on redundant amplitude level compression and high probability amplitude level expansion; at this time, the amplitude level includes L 0 =256 levels. It can be seen from the figure that by using the present invention, the histogram is expanded after removing redundancy, and the local contrast of the target grayscale image is effectively improved while retaining target detail information.
图3是进行对比实验的结果。(a)为仿真飞机目标的原始ISAR成像结果，(b)是利用Gamma变换(系数是0.4)增强的结果，(c)是现有直方图均衡化增强结果，(d)是利用本发明方法得到的图像增强结果。从图中可以看出，Gamma变换法对具有稀疏性、动态范围大的ISAR图像增强时，目标和背景噪声同时进行增强。直方图均衡化法对于动态范围已经很大的ISAR图像而言，难以实现细节增强，而对目标主体的增强甚至会变得模糊。而本发明的方法可以更有效地增强细节信息。Figure 3 is the result of a comparative experiment. (a) is the original ISAR imaging result of the simulated aircraft target, (b) is the enhanced result using Gamma transform (coefficient is 0.4), (c) is the existing histogram equalization enhanced result, (d) is the method of the present invention The obtained image enhancement result. It can be seen from the figure that when the Gamma transform method enhances the ISAR image with sparsity and large dynamic range, the target and background noise are simultaneously enhanced. For the ISAR image with a large dynamic range, the histogram equalization method is difficult to achieve detail enhancement, and the enhancement of the target subject may even become blurred. However, the method of the present invention can enhance detail information more effectively.
为进一步验证本发明的有效性，采用三个度量标准构建综合评价指标体系，进行定量分析，包括模糊性指数、局部对比度、细节区域方差。模糊性指数越小、局部对比度越大、细节区域方差越大，图像增强性能就越优越。利用上述三个指标对图3的实验结果定量对比，如表1所示。In order to further verify the effectiveness of the present invention, three metrics are used to construct a comprehensive evaluation index system for quantitative analysis, including fuzziness index, local contrast, and variance of detail regions. The smaller the fuzziness index, the larger the local contrast, and the larger the variance of the detail area, the better the image enhancement performance. Using the above three indicators to quantitatively compare the experimental results in Figure 3, as shown in Table 1.
表1定量比较Table 1 Quantitative comparison
根据表1得到对比结果如下：According to Table 1, the comparison results are as follows:
①根据模糊性指数及局部对比度的对比结果可知，本发明方法在提高图像细节信息的丰富程度和局部对比度方面比其它算法更优。① According to the comparison results of fuzziness index and local contrast, the method of the present invention is better than other algorithms in improving the richness of image detail information and local contrast.
②细节区域方差值方面，本发明方法的结果同样最大，且增加幅度较大。这一结果表明本发明方法在实现大动态范围压缩时，保留局部细节或保持局部对比度的能力比其他方法更优越。② In terms of the variance value of the detail area, the result of the method of the present invention is also the largest, and the increase is relatively large. This result shows that the method of the present invention is superior to other methods in preserving local details or maintaining local contrast when realizing large dynamic range compression.
仿真和对比实验均通过Matlab2010a实现。操作系统是Microsoft Windows XPProfessionalSP3，处理器是Pentium Dual-Core 2.7GHz。图3仿真实验利用的实测数据大小为401×256，所用的时间开销对比结果，如下表所示。The simulation and comparative experiments are all realized by Matlab2010a. The operating system is Microsoft Windows XP Professional SP3, and the processor is Pentium Dual-Core 2.7GHz. The size of the measured data used in the simulation experiment in Figure 3 is 401×256, and the comparison results of the time overhead used are shown in the table below.
表2.不同算法的时间开销(s)Table 2. Time overhead (s) of different algorithms
从表中给出的对比结果可以看到，本发明方法仿真时运算量比其他算法有一定增长，但这种时间开销的增加相对于算法性能的提升可以忽略不计。From the comparison results given in the table, it can be seen that the calculation amount of the method of the present invention increases to a certain extent compared with other algorithms, but the increase in time overhead is negligible relative to the improvement of algorithm performance.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810414603.4A CN108629754B (en) | 2018-05-03 | 2018-05-03 | ISAR image self-adaptive detail enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810414603.4A CN108629754B (en) | 2018-05-03 | 2018-05-03 | ISAR image self-adaptive detail enhancement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108629754A true CN108629754A (en) | 2018-10-09 |
| CN108629754B CN108629754B (en) | 2019-05-24 |
Family
ID=63695237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810414603.4A Active CN108629754B (en) | 2018-05-03 | 2018-05-03 | ISAR image self-adaptive detail enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108629754B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129675A (en) * | 2011-02-24 | 2011-07-20 | 中国兵器工业系统总体部 | Nonlinear adaptive infrared image enhancing method |
| CN102169580A (en) * | 2011-04-08 | 2011-08-31 | 中国船舶重工集团公司第七○二研究所 | Self-adaptive image processing method utilizing image statistic characteristics |
| CN106342330B (en) * | 2009-08-12 | 2013-04-17 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of image enchancing method of the gamma correction based on infrared image |
| CN105069460A (en) * | 2015-08-21 | 2015-11-18 | 航天长征火箭技术有限公司 | ISAR image ship target feature extraction method |
| CN105184759A (en) * | 2015-09-22 | 2015-12-23 | 中国科学院西安光学精密机械研究所 | Image self-adaptive enhancement method based on histogram compactness transformation |
| CN106296599A (en) * | 2016-07-29 | 2017-01-04 | 南京信息工程大学 | A kind of method for adaptive image enhancement |
| CN106339994A (en) * | 2016-08-29 | 2017-01-18 | 合肥康胜达智能科技有限公司 | Image enhancement method |
| CN107292834A (en) * | 2017-05-24 | 2017-10-24 | 杭州天铂红外光电技术有限公司 | Infrared image detail enhancing method |
| CN107527333A (en) * | 2017-07-31 | 2017-12-29 | 湖北工业大学 | A kind of rapid image Enhancement Method based on gamma transformation |
| CN107945122A (en) * | 2017-11-07 | 2018-04-20 | 武汉大学 | Infrared image enhancing method and system based on self-adapting histogram segmentation |
-
2018
- 2018-05-03 CN CN201810414603.4A patent/CN108629754B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106342330B (en) * | 2009-08-12 | 2013-04-17 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of image enchancing method of the gamma correction based on infrared image |
| CN102129675A (en) * | 2011-02-24 | 2011-07-20 | 中国兵器工业系统总体部 | Nonlinear adaptive infrared image enhancing method |
| CN102169580A (en) * | 2011-04-08 | 2011-08-31 | 中国船舶重工集团公司第七○二研究所 | Self-adaptive image processing method utilizing image statistic characteristics |
| CN105069460A (en) * | 2015-08-21 | 2015-11-18 | 航天长征火箭技术有限公司 | ISAR image ship target feature extraction method |
| CN105184759A (en) * | 2015-09-22 | 2015-12-23 | 中国科学院西安光学精密机械研究所 | Image self-adaptive enhancement method based on histogram compactness transformation |
| CN106296599A (en) * | 2016-07-29 | 2017-01-04 | 南京信息工程大学 | A kind of method for adaptive image enhancement |
| CN106339994A (en) * | 2016-08-29 | 2017-01-18 | 合肥康胜达智能科技有限公司 | Image enhancement method |
| CN107292834A (en) * | 2017-05-24 | 2017-10-24 | 杭州天铂红外光电技术有限公司 | Infrared image detail enhancing method |
| CN107527333A (en) * | 2017-07-31 | 2017-12-29 | 湖北工业大学 | A kind of rapid image Enhancement Method based on gamma transformation |
| CN107945122A (en) * | 2017-11-07 | 2018-04-20 | 武汉大学 | Infrared image enhancing method and system based on self-adapting histogram segmentation |
Non-Patent Citations (6)
| Title |
|---|
| NING LIU等: "Detail enhancement for high-dynamic-range infrared images based on guided image filter", 《INFRARED PHYSICS & TECHNOLOGY》 * |
| 刘慧敏等: "逆合成孔径雷达像轮廓提取方法", 《系统工程与电子技术》 * |
| 张颖宁: "多基站ISAR成像融合算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 杨效余等: "舰船ISAR图像特征提取方法研究", 《遥测遥控》 * |
| 田淑芳，詹骞主编: "《遥感地质学（第2版）》", 31 January 2014, 地质出版社 * |
| 蔡骏: "红外图像自适应细节增强算法的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108629754B (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Application of RNAMlet to surface defect identification of steels | |
| CN114897779B (en) | Cervical cytology image abnormal region positioning method and device based on fusion attention | |
| CN109785250B (en) | Image restoration method based on Criminisi algorithm | |
| CN114235758A (en) | Defect detection method, device, equipment and storage medium | |
| CN111986126B (en) | Multi-target detection method based on improved VGG16 network | |
| CN104751147A (en) | Image recognition method | |
| CN110675340A (en) | Single image defogging method and medium based on improved non-local prior | |
| CN105069796A (en) | Wavelet scatternet-based SAR image segmentation method | |
| CN104766095A (en) | Mobile terminal image identification method | |
| CN111415323A (en) | Image detection method and device and neural network training method and device | |
| CN106407959A (en) | Low-illumination complicated background license plate positioning method based on wavelet transform and SVM | |
| CN103077499B (en) | SAR (Synthetic Aperture Radar) image pre-processing method based on similar block | |
| CN103077507B (en) | Beta algorithm-based multiscale SAR (Synthetic Aperture Radar) image denoising method | |
| CN100345152C (en) | Face recognition method based on template matching | |
| CN109801208B (en) | SAR image change detection method based on multi-GPU task optimization | |
| CN104952071A (en) | Maximum between-cluster variance image segmentation algorithm based on GLSC (gray-level spatial correlation) | |
| CN118297837B (en) | Infrared simulator virtual image enhancement system based on image processing | |
| CN106846366B (en) | TLD video moving object tracking method using GPU hardware | |
| CN114240990A (en) | SAR image point target segmentation method | |
| CN108629754A (en) | ISAR image self-adaptive detail enhancement method | |
| CN106934805A (en) | SAR image superpixel segmentation method based on Gamma filtering | |
| CN107607927B (en) | Stripe laser echo information extraction method | |
| CN113160214B (en) | Novel method for measuring similarity of local neighborhood pixels of image | |
| CN107330869B (en) | An abnormal pixel reconstruction method after overlapping cell segmentation | |
| CN115937302A (en) | Hyperspectral image sub-pixel positioning method combined with edge preservation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |