Pub Date : 2019-08-04DOI: 10.1080/19479832.2019.1649309
Lin Teng, Hang Li, Shoulin Yin, Shahid Karim, Yang Sun
Image segmentation (Lin et al. 2018, Shoulin et al. 2018) is the basic link of image processing and machine vision, so it is very important to study this content. Because the image can be interfered by many factors in the process of imaging, the image is usually with some problems such as heterogeneous, edge blur, noisy, which makes low accuracy of traditional segmentation methods. In recent years, the active contour model (Ben Rabeh et al. 2017) has achieved great success in image segmentation, which is widely concerned by researchers. The active contour model can be divided into two categories: parameter active contour model (Hanbay and Talu 2018) and geometric active contour model (Khamechian and Saadatmand-Tarzjan 2018). The geometric active contour model can be subdivided into two categories: dynamic contour model based on edge (Amini et al. 2004) and active contour model based on region (Soudani and Zagrouba 2017, Elisee et al. 2017). For the edge-based active contour model, the results are not ideal when it segments weak edge and the images with noise, the robustness of the initial contour lines is also poor. To this end, the scholars propose an active contour model based on region. There are some representative region-based active contour models, such as chan-vese model (CV) and Piecewise Smooth model (PS). The model is used to guide the curve evolution by using the information of pixel grey variance in the curve. And it does not depend on the gradient information of the image, so it can deal with the weak edge of image better. Shyu et al. (2012) introduced the Retinex theory into the active contour model, which was commonly used for image segmentation. The segmentation procedure was then guided by the image intensity and light reflection. In order to solve the proposed model efficiently, this work developed a new fast Split Bregman algorithm. The results were better. Xiaomin and Tingting (2017) presented an alternative criterion derived from the least squares projection twin support vector machine (LSPTSVM) for image segmentation. The proposed model treated image segmentation as pattern classification problem, and hence tried to seek the projected axis and centre for the foreground and background intensities, respectively. With level set representation, the discriminative function of LSTSVM was incorporated into the energy function of the active contour model, and derived the contour evolution accordingly. Experiment results demonstrated that this model held higher segmentation accuracy and more noise robustness. Le and Savvides (2016) proposed a novel joint formulation
图像分割(Lin et al. 2018, Shoulin et al. 2018)是图像处理和机器视觉的基础环节，因此对这一内容的研究非常重要。由于图像在成像过程中会受到多种因素的干扰，图像通常存在异质性、边缘模糊、噪声等问题，使得传统的分割方法精度较低。近年来，活动轮廓模型(Ben Rabeh et al. 2017)在图像分割方面取得了巨大成功，受到研究者的广泛关注。活动轮廓模型可分为两类:参数活动轮廓模型(Hanbay and Talu 2018)和几何活动轮廓模型(Khamechian and Saadatmand-Tarzjan 2018)。几何活动轮廓模型可细分为两类:基于边缘的动态轮廓模型(Amini et al. 2004)和基于区域的活动轮廓模型(Soudani and Zagrouba 2017, Elisee et al. 2017)。基于边缘的活动轮廓模型在分割弱边缘和含噪声图像时效果不理想，初始轮廓线的鲁棒性也较差。为此，学者们提出了一种基于区域的活动轮廓模型。有代表性的基于区域的活动轮廓模型有chan-vese模型(CV)和分段平滑模型(PS)。该模型利用曲线中像素灰度方差信息来指导曲线演化。该方法不依赖于图像的梯度信息，能较好地处理图像的弱边缘。Shyu et al.(2012)将Retinex理论引入到常用的图像分割活动轮廓模型中。然后以图像强度和光反射为指导进行分割。为了有效地求解所提出的模型，本文开发了一种新的快速分割Bregman算法。结果更好。Xiaomin和Tingting(2017)提出了一种基于最小二乘投影双支持向量机(LSPTSVM)的图像分割替代准则。该模型将图像分割视为模式分类问题，分别寻求前景和背景强度的投影轴和投影中心。通过水平集表示，将LSTSVM的判别函数融入到活动轮廓模型的能量函数中，推导出轮廓的演化过程。实验结果表明，该模型具有较高的分割精度和较强的噪声鲁棒性。Le和Savvides(2016)提出了一种新的联合配方
{"title":"An active contour model based on hybrid energy and fisher criterion for image segmentation","authors":"Lin Teng, Hang Li, Shoulin Yin, Shahid Karim, Yang Sun","doi":"10.1080/19479832.2019.1649309","DOIUrl":"https://doi.org/10.1080/19479832.2019.1649309","url":null,"abstract":"Image segmentation (Lin et al. 2018, Shoulin et al. 2018) is the basic link of image processing and machine vision, so it is very important to study this content. Because the image can be interfered by many factors in the process of imaging, the image is usually with some problems such as heterogeneous, edge blur, noisy, which makes low accuracy of traditional segmentation methods. In recent years, the active contour model (Ben Rabeh et al. 2017) has achieved great success in image segmentation, which is widely concerned by researchers. The active contour model can be divided into two categories: parameter active contour model (Hanbay and Talu 2018) and geometric active contour model (Khamechian and Saadatmand-Tarzjan 2018). The geometric active contour model can be subdivided into two categories: dynamic contour model based on edge (Amini et al. 2004) and active contour model based on region (Soudani and Zagrouba 2017, Elisee et al. 2017). For the edge-based active contour model, the results are not ideal when it segments weak edge and the images with noise, the robustness of the initial contour lines is also poor. To this end, the scholars propose an active contour model based on region. There are some representative region-based active contour models, such as chan-vese model (CV) and Piecewise Smooth model (PS). The model is used to guide the curve evolution by using the information of pixel grey variance in the curve. And it does not depend on the gradient information of the image, so it can deal with the weak edge of image better. Shyu et al. (2012) introduced the Retinex theory into the active contour model, which was commonly used for image segmentation. The segmentation procedure was then guided by the image intensity and light reflection. In order to solve the proposed model efficiently, this work developed a new fast Split Bregman algorithm. The results were better. Xiaomin and Tingting (2017) presented an alternative criterion derived from the least squares projection twin support vector machine (LSPTSVM) for image segmentation. The proposed model treated image segmentation as pattern classification problem, and hence tried to seek the projected axis and centre for the foreground and background intensities, respectively. With level set representation, the discriminative function of LSTSVM was incorporated into the energy function of the active contour model, and derived the contour evolution accordingly. Experiment results demonstrated that this model held higher segmentation accuracy and more noise robustness. Le and Savvides (2016) proposed a novel joint formulation","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"11 1","pages":"97 - 112"},"PeriodicalIF":2.3,"publicationDate":"2019-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1649309","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47790020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-15DOI: 10.1080/19479832.2019.1641164
J. Zelasco, J. Donayo
ABSTRACT Research studies have shown that when the error of a digital elevation model (DEM) is accepted as random, one of the two solutions is generally used. One is the employment of a benchmark, and the other is measuring the vertical distance to evaluate the vertical error. For the first solution, a benchmark or adequate random sample may be unavailable. The second solution consists of measuring only the vertical distance from a point of the DEM to the surface of the reference DEM. This solution provides only a biased vertical error. In this paper, a perpendicular distance evaluation method (PDEM) is proposed. This approach allows estimating the vertical error, and under certain irregular terrain conditions, the horizontal error. Simulations are presented in detail, starting from a real reference DEM, with 100 000 points. The results confirm that, the more irregular the terrain is, the better the horizontal error results, and that the evaluation of the vertical error is not biased.
{"title":"Effectiveness of geometric quality control using a distance evaluation method","authors":"J. Zelasco, J. Donayo","doi":"10.1080/19479832.2019.1641164","DOIUrl":"https://doi.org/10.1080/19479832.2019.1641164","url":null,"abstract":"ABSTRACT Research studies have shown that when the error of a digital elevation model (DEM) is accepted as random, one of the two solutions is generally used. One is the employment of a benchmark, and the other is measuring the vertical distance to evaluate the vertical error. For the first solution, a benchmark or adequate random sample may be unavailable. The second solution consists of measuring only the vertical distance from a point of the DEM to the surface of the reference DEM. This solution provides only a biased vertical error. In this paper, a perpendicular distance evaluation method (PDEM) is proposed. This approach allows estimating the vertical error, and under certain irregular terrain conditions, the horizontal error. Simulations are presented in detail, starting from a real reference DEM, with 100 000 points. The results confirm that, the more irregular the terrain is, the better the horizontal error results, and that the evaluation of the vertical error is not biased.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"263 - 279"},"PeriodicalIF":2.3,"publicationDate":"2019-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1641164","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48303301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-23DOI: 10.1080/19479832.2019.1625977
Á. Barsi, Z. Kugler, A. Juhász, G. Szabó, C. Batini, H. Abdulmuttalib, Guoman Huang, Huanfeng Shen
ABSTRACT The importance of data quality assessment has significantly increased with the boom of information technology and the growing demand for remote sensing (RS) data. The Remote Sensing Data Quality Working Group of the International Society for Photogrammetry and Remote Sensing aimed to conduct an investigation on the principles of data quality. Literature review revealed that most publications introduce data quality models for application specific processing chains and quality schemes are built case by case with particular domain indicators only. Yet no general concept independent from applications has been developed so far. This paper focuses on the formulation of a RS quality concept adopted from information technology domain describing a triangular RS data quality scheme that relates data sources, quality dimensions and lifecycle phases. Following the introduction it provides examples of international standards and fundamentals of theoretic quality modelling. After a short overview on platforms/sensors, definitions of different quality dimensions are presented with their metrics organised in clusters (like resolution or accuracy). The main achievement of the paper relates lifecycle phases to different quality dimensions of high relevance. The objective is not only to address experts of RS but to raise awareness of uncertainty for the general RS user community.
{"title":"Remote sensing data quality model: from data sources to lifecycle phases","authors":"Á. Barsi, Z. Kugler, A. Juhász, G. Szabó, C. Batini, H. Abdulmuttalib, Guoman Huang, Huanfeng Shen","doi":"10.1080/19479832.2019.1625977","DOIUrl":"https://doi.org/10.1080/19479832.2019.1625977","url":null,"abstract":"ABSTRACT The importance of data quality assessment has significantly increased with the boom of information technology and the growing demand for remote sensing (RS) data. The Remote Sensing Data Quality Working Group of the International Society for Photogrammetry and Remote Sensing aimed to conduct an investigation on the principles of data quality. Literature review revealed that most publications introduce data quality models for application specific processing chains and quality schemes are built case by case with particular domain indicators only. Yet no general concept independent from applications has been developed so far. This paper focuses on the formulation of a RS quality concept adopted from information technology domain describing a triangular RS data quality scheme that relates data sources, quality dimensions and lifecycle phases. Following the introduction it provides examples of international standards and fundamentals of theoretic quality modelling. After a short overview on platforms/sensors, definitions of different quality dimensions are presented with their metrics organised in clusters (like resolution or accuracy). The main achievement of the paper relates lifecycle phases to different quality dimensions of high relevance. The objective is not only to address experts of RS but to raise awareness of uncertainty for the general RS user community.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"280 - 299"},"PeriodicalIF":2.3,"publicationDate":"2019-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1625977","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47877070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-04DOI: 10.1080/19479832.2019.1625449
Ravinder Singh, K. S. Nagla
ABSTRACT Occupancy grid mapping in the field of mobile robotics is an integrative and promising solution for the various prerequisite such as path planning, autonomous navigation, localization, SLAM (Simultaneously Localization And Mapping) etc. The reliability of the occupancy grid mapping depends upon diverse parameters such as sensor accuracy, size of a grid cell, intrinsic and extrinsic parameters, sensor registration, sensor modelling, scanning angle, ambient conditions, etc. This research reveals the uncertainty in the generation of the laser occupancy grid map with the implementation of conventional laser geometry technique when the detected obstacle/target is on the perimeter of the grid cell. During autonomous navigation, the obstacle and the mobile robot are in a dynamic state that consequence in the wrong perception of the environment by identifying the wrong grid cell as occupied in the occupancy grid map when the obstacle is on the perimeter of the grid cell. The examined error is reduced by a newly designed Perimeter-based SLAM (P-SLAM) technique based on the vector algebra, laser geometry, Inverse Sensor Model and coordinate system. The obtained results with the implementation of P-SLAM are validated w.r.t conventional approaches with qualitative and quantitative analysis by performing real-world experiments.
在移动机器人领域，占用网格映射是解决路径规划、自主导航、定位、SLAM (simultaneous localization and mapping)等前提条件的一种综合解决方案。占用网格映射的可靠性取决于不同的参数，如传感器精度、网格单元的大小、内在和外在参数、传感器配准、传感器建模、扫描角度、环境条件等。本研究揭示了当检测到的障碍物/目标位于网格单元的周长时，采用传统激光几何技术生成激光占用网格图的不确定性。在自主导航过程中，障碍物和移动机器人都处于动态状态，当障碍物处于占用网格图的外围时，会在占用网格图中识别出错误的网格单元，从而导致对环境的错误感知。采用基于矢量代数、激光几何、逆传感器模型和坐标系的新设计的基于周长的SLAM (P-SLAM)技术，减小了检测误差。通过实际实验，对P-SLAM实现的结果进行了定性和定量分析，验证了常规方法的有效性。
{"title":"Development of an efficient laser grid mapping technique: P-SLAM","authors":"Ravinder Singh, K. S. Nagla","doi":"10.1080/19479832.2019.1625449","DOIUrl":"https://doi.org/10.1080/19479832.2019.1625449","url":null,"abstract":"ABSTRACT Occupancy grid mapping in the field of mobile robotics is an integrative and promising solution for the various prerequisite such as path planning, autonomous navigation, localization, SLAM (Simultaneously Localization And Mapping) etc. The reliability of the occupancy grid mapping depends upon diverse parameters such as sensor accuracy, size of a grid cell, intrinsic and extrinsic parameters, sensor registration, sensor modelling, scanning angle, ambient conditions, etc. This research reveals the uncertainty in the generation of the laser occupancy grid map with the implementation of conventional laser geometry technique when the detected obstacle/target is on the perimeter of the grid cell. During autonomous navigation, the obstacle and the mobile robot are in a dynamic state that consequence in the wrong perception of the environment by identifying the wrong grid cell as occupied in the occupancy grid map when the obstacle is on the perimeter of the grid cell. The examined error is reduced by a newly designed Perimeter-based SLAM (P-SLAM) technique based on the vector algebra, laser geometry, Inverse Sensor Model and coordinate system. The obtained results with the implementation of P-SLAM are validated w.r.t conventional approaches with qualitative and quantitative analysis by performing real-world experiments.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"177 - 198"},"PeriodicalIF":2.3,"publicationDate":"2019-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1625449","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42669472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-04DOI: 10.1080/19479832.2019.1625448
Y. Stepanov, A. Stepanov
ABSTRACT A myriad of spatial and attribute data are in use when designing and operating mine-engineering systems. These data are hosted on various servers of a company and are diverse in structure of data and units of measurement and have different subject areas related to each other in a complex way. There is no conformity between conventional systems for managing and storing data and tools for analysing incoming data. Big Data paradigm that implies methods for processing distributed data is utilised in ‘big data’ processing. A MapReduce method involves two procedures: map procedure that applies a proper function to each element of the list and reduce procedure, integrating the map procedure results. Such conventional database management system methods as integration and indexation, graph search and other methods are used to cluster big data. These methods should be used within MapReduce. Employing standard equipment and means to control a distributed Hadoop and Apache Hadoop Distributed File System (HDFS) file system, data storages in petabytes can be implemented. To make a more in-depth analysis, Data Mining methods are utilised along with network analysis, predictive analytics, etc. The articlecovers various methods applied to collect and analyse ‘big data’ to do a feasibility study and design mine and engineering systems.
{"title":"Big Data technologies to process spatial and attribute data when designing and operating mine-engineering systems","authors":"Y. Stepanov, A. Stepanov","doi":"10.1080/19479832.2019.1625448","DOIUrl":"https://doi.org/10.1080/19479832.2019.1625448","url":null,"abstract":"ABSTRACT A myriad of spatial and attribute data are in use when designing and operating mine-engineering systems. These data are hosted on various servers of a company and are diverse in structure of data and units of measurement and have different subject areas related to each other in a complex way. There is no conformity between conventional systems for managing and storing data and tools for analysing incoming data. Big Data paradigm that implies methods for processing distributed data is utilised in ‘big data’ processing. A MapReduce method involves two procedures: map procedure that applies a proper function to each element of the list and reduce procedure, integrating the map procedure results. Such conventional database management system methods as integration and indexation, graph search and other methods are used to cluster big data. These methods should be used within MapReduce. Employing standard equipment and means to control a distributed Hadoop and Apache Hadoop Distributed File System (HDFS) file system, data storages in petabytes can be implemented. To make a more in-depth analysis, Data Mining methods are utilised along with network analysis, predictive analytics, etc. The articlecovers various methods applied to collect and analyse ‘big data’ to do a feasibility study and design mine and engineering systems.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"217 - 231"},"PeriodicalIF":2.3,"publicationDate":"2019-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1625448","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48707183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-05-05DOI: 10.1080/19479832.2019.1611668
Amirata Taghavi, M. Maanijou, D. Lentz, A. Sepahi
ABSTRACT This study uses remote sensing image-processing to enhance recognition of areas with mineral abundance halo, which can be associated with porphyry mineralisation of the Urumieh-Dokhtar Magmatic Belt (UDMB) in western Yazd. Granitoid intrusions of Oligocene-Miocene age in UDMB hosts the most important Porphyry Copper Deposits (PCDs) of Iran such as Darezereshk and Aliabad PCDs. Diagnostic spectral absorption features of six shortwave infrared (SWIR) and three visible and near-infrared (VNIR) bands of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data were applied to determine the alteration minerals and their abundance. In this research reflectance data from various representative alteration types throughout the study area were measured by the FieldSpec-3 spectroradiometer and applied for mapping minerals. Different remote sensing analytical techniques, including the Principal Component Analysis (PCA), band ratio, relative absorption band depth, and MTMF, were applied to enhance mapping the alteration minerals. Field works including rock sampling, petrography and field spectroradiometer followed up the alteration mapping. Field observation implies that, the vein-type mineralisation above the cupola of this porphyry system is preserved in the western part, although it was eroded in the eastern area. Consequently, PCDs potential is expected to be higher in the western area.
{"title":"Partial sub-pixel and pixel-based alteration mapping of porphyry system using ASTER data: regional case study in western Yazd, Iran","authors":"Amirata Taghavi, M. Maanijou, D. Lentz, A. Sepahi","doi":"10.1080/19479832.2019.1611668","DOIUrl":"https://doi.org/10.1080/19479832.2019.1611668","url":null,"abstract":"ABSTRACT This study uses remote sensing image-processing to enhance recognition of areas with mineral abundance halo, which can be associated with porphyry mineralisation of the Urumieh-Dokhtar Magmatic Belt (UDMB) in western Yazd. Granitoid intrusions of Oligocene-Miocene age in UDMB hosts the most important Porphyry Copper Deposits (PCDs) of Iran such as Darezereshk and Aliabad PCDs. Diagnostic spectral absorption features of six shortwave infrared (SWIR) and three visible and near-infrared (VNIR) bands of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data were applied to determine the alteration minerals and their abundance. In this research reflectance data from various representative alteration types throughout the study area were measured by the FieldSpec-3 spectroradiometer and applied for mapping minerals. Different remote sensing analytical techniques, including the Principal Component Analysis (PCA), band ratio, relative absorption band depth, and MTMF, were applied to enhance mapping the alteration minerals. Field works including rock sampling, petrography and field spectroradiometer followed up the alteration mapping. Field observation implies that, the vein-type mineralisation above the cupola of this porphyry system is preserved in the western part, although it was eroded in the eastern area. Consequently, PCDs potential is expected to be higher in the western area.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"300 - 326"},"PeriodicalIF":2.3,"publicationDate":"2019-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1611668","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42882689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-05-05DOI: 10.1080/19479832.2019.1611667
Jiang Wu, Ping Jiang
ABSTRACT Image quality assessment (IQA) is widely used in digital image processing, and no-reference (NR) IQA has become research focus recently. This paper proposes a NR IQA method based on local features without access to prior knowledge of the images or their distortions. Four gradient masks are used to detect the maximum local gradient (MLG), and the analysis shows that the MLG of strong structure (such as region boundary) includes very tiny noise component, thus this paper assesses image visual quality by using MLGs of strong structures. The proposed method can assess noisy image and blurred image at the same time, and the quality score drops either when the test image becomes blurred or corrupted by random noise. The experiment results show that the proposed approach works well on LIVE, TID2013 and CSIQ databases, and it outperforms some state-of-the-art algorithms.
{"title":"A complete no-reference image quality assessment method based on local feature","authors":"Jiang Wu, Ping Jiang","doi":"10.1080/19479832.2019.1611667","DOIUrl":"https://doi.org/10.1080/19479832.2019.1611667","url":null,"abstract":"ABSTRACT Image quality assessment (IQA) is widely used in digital image processing, and no-reference (NR) IQA has become research focus recently. This paper proposes a NR IQA method based on local features without access to prior knowledge of the images or their distortions. Four gradient masks are used to detect the maximum local gradient (MLG), and the analysis shows that the MLG of strong structure (such as region boundary) includes very tiny noise component, thus this paper assesses image visual quality by using MLGs of strong structures. The proposed method can assess noisy image and blurred image at the same time, and the quality score drops either when the test image becomes blurred or corrupted by random noise. The experiment results show that the proposed approach works well on LIVE, TID2013 and CSIQ databases, and it outperforms some state-of-the-art algorithms.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"165 - 176"},"PeriodicalIF":2.3,"publicationDate":"2019-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1611667","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44962950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-27DOI: 10.1080/19479832.2019.1601642
S. Gholinejad, S. B. Fatemi
ABSTRACT In this study, vegetation changes in the Zayandeh-rud river basin in the period 2001 to 2016 have been investigated based on the combining of the 15 different vegetation indices. Two main plans were applied and tested to produce the final vegetation change map. In the first plan, change maps were produced by differencing the original vegetation indices individually. The second plan, which was a fusion perspective, included two algorithms. In the first one, change maps, obtained from vegetation indices, were fused at the decision level using the Majority Voting Method. The second algorithm included a particle swarm optimisation (PSO) based weighted combination of the different vegetation maps. The results show that the high correlation between vegetation indices does not necessarily provide the same results and combination of all them can be done automatically by applying PSO. Although PSO-based combination could not significantly improve the change detection, it solved the problem of finding optimal threshold value for the change detection process. However, from the vegetation change point of view, they all indicate that during the years of study, the vegetation cover has increased in the study area due to irregular water usage of the Zayandeh-rud river in its western part.
{"title":"Optimum indices for vegetation cover change detection in the Zayandeh-rud river basin: a fusion approach","authors":"S. Gholinejad, S. B. Fatemi","doi":"10.1080/19479832.2019.1601642","DOIUrl":"https://doi.org/10.1080/19479832.2019.1601642","url":null,"abstract":"ABSTRACT In this study, vegetation changes in the Zayandeh-rud river basin in the period 2001 to 2016 have been investigated based on the combining of the 15 different vegetation indices. Two main plans were applied and tested to produce the final vegetation change map. In the first plan, change maps were produced by differencing the original vegetation indices individually. The second plan, which was a fusion perspective, included two algorithms. In the first one, change maps, obtained from vegetation indices, were fused at the decision level using the Majority Voting Method. The second algorithm included a particle swarm optimisation (PSO) based weighted combination of the different vegetation maps. The results show that the high correlation between vegetation indices does not necessarily provide the same results and combination of all them can be done automatically by applying PSO. Although PSO-based combination could not significantly improve the change detection, it solved the problem of finding optimal threshold value for the change detection process. However, from the vegetation change point of view, they all indicate that during the years of study, the vegetation cover has increased in the study area due to irregular water usage of the Zayandeh-rud river in its western part.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"199 - 216"},"PeriodicalIF":2.3,"publicationDate":"2019-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1601642","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43680297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-13DOI: 10.1080/19479832.2019.1604574
Lin Teng, Hang Li, Shoulin Yin, Yang Sun
ABSTRACT Traditional image segment algorithms have some demerits: edge blur, discontinuous edge is susceptible to peripheral irrelevant information, Poor noise resistance. Therefore, we propose an improved krill group-based region growing algorithm for image segmentation in this paper. First, texture feature of the image is extracted by using Gabor filter. Then, we modify the krill group by the way that the population particle dynamics is divided into two categories: worse fitness value of particle and better fitness value of particle. The inertial weight of worse fitness value of particle is reset to zero, so as to eliminate the adverse effect of inertial weight on the current iteration of the algorithm. The inertial weight of better fitness value particle remains unchanged. The step size scaling factor in the algorithm is treated with non-linear declination to further improve the global exploring ability of the algorithm. Finally, the improved kill group optimisation is used to search for the optimal solution, and the segmentation results are finally obtained. The experimental results show that the proposed image segmentation model can not only improve the segmentation accuracy and reduce the number of iterations but also suppress the background. The contour positioning of the object area is effective.
{"title":"Improved krill group-based region growing algorithm for image segmentation","authors":"Lin Teng, Hang Li, Shoulin Yin, Yang Sun","doi":"10.1080/19479832.2019.1604574","DOIUrl":"https://doi.org/10.1080/19479832.2019.1604574","url":null,"abstract":"ABSTRACT Traditional image segment algorithms have some demerits: edge blur, discontinuous edge is susceptible to peripheral irrelevant information, Poor noise resistance. Therefore, we propose an improved krill group-based region growing algorithm for image segmentation in this paper. First, texture feature of the image is extracted by using Gabor filter. Then, we modify the krill group by the way that the population particle dynamics is divided into two categories: worse fitness value of particle and better fitness value of particle. The inertial weight of worse fitness value of particle is reset to zero, so as to eliminate the adverse effect of inertial weight on the current iteration of the algorithm. The inertial weight of better fitness value particle remains unchanged. The step size scaling factor in the algorithm is treated with non-linear declination to further improve the global exploring ability of the algorithm. Finally, the improved kill group optimisation is used to search for the optimal solution, and the segmentation results are finally obtained. The experimental results show that the proposed image segmentation model can not only improve the segmentation accuracy and reduce the number of iterations but also suppress the background. The contour positioning of the object area is effective.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"327 - 341"},"PeriodicalIF":2.3,"publicationDate":"2019-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1604574","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42564265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-03DOI: 10.1080/19479832.2019.1589585
Rejith Rajan Girija, Sundararajan Mayappan
ABSTRACT The remote sensing (RS) techniques have become a guiding and promising tool for mineral exploration and mapping of lithological units. The RS for mineral exploration begins with Landsat multispectral data in which the iron oxide and clay minerals associated with hydrothermal alteration zones were delineated using techniques like BR and PCA. Later, the advanced image processing techniques like spectral angle mapping, spectral feature fitting, Crosta technique and MNF transformation were successfully implemented to delineate clay, sulphate and iron oxide minerals using the shortwave infrared bands of Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) data. The thermal bands of ASTER allowed mapping of carbonate and quartz mineralogy based on their silica content. The quantitative mapping of minerals started with the advent of hyperspectral RS data like Hyperion. The recent advances in satellite sensor technology get paralleled by the development of new and innovative approaches in RS data processing and integration. The studies have opened up new methods for mineral evaluation using sustainable and eco-friendly exploitation of natural resources. This paper provides a review of RS data products and techniques widely used for geological applications.
{"title":"Mapping of mineral resources and lithological units: a review of remote sensing techniques","authors":"Rejith Rajan Girija, Sundararajan Mayappan","doi":"10.1080/19479832.2019.1589585","DOIUrl":"https://doi.org/10.1080/19479832.2019.1589585","url":null,"abstract":"ABSTRACT The remote sensing (RS) techniques have become a guiding and promising tool for mineral exploration and mapping of lithological units. The RS for mineral exploration begins with Landsat multispectral data in which the iron oxide and clay minerals associated with hydrothermal alteration zones were delineated using techniques like BR and PCA. Later, the advanced image processing techniques like spectral angle mapping, spectral feature fitting, Crosta technique and MNF transformation were successfully implemented to delineate clay, sulphate and iron oxide minerals using the shortwave infrared bands of Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) data. The thermal bands of ASTER allowed mapping of carbonate and quartz mineralogy based on their silica content. The quantitative mapping of minerals started with the advent of hyperspectral RS data like Hyperion. The recent advances in satellite sensor technology get paralleled by the development of new and innovative approaches in RS data processing and integration. The studies have opened up new methods for mineral evaluation using sustainable and eco-friendly exploitation of natural resources. This paper provides a review of RS data products and techniques widely used for geological applications.","PeriodicalId":46012,"journal":{"name":"International Journal of Image and Data Fusion","volume":"10 1","pages":"106 - 79"},"PeriodicalIF":2.3,"publicationDate":"2019-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19479832.2019.1589585","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44695806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：