KEYWORDS: Clouds, 3D modeling, Data modeling, 3D image processing, Feature extraction, RGB color model, 3D metrology, Data fusion, Image fusion, Inspection
Surface defect recognition is used to test product’s quality. The current way of recognition is traditional 2D imagebased method. But 2D image lacks 3D information which results in false inspection and missed inspection, which has become a bottleneck of current classification model. Because of the recent rapid development of 3D measurement technology, we can apply 3D data information in surface defect detection to improve the recognition ability of defects. We propose a new convolutional network model to identify surface defects, and realize the feature depth fusion of 3D point cloud and 2D image in the model. In this work, we introduce an attention network to extract features from a 3D point cloud to generate a 2D attention mask. The high quality feature map is produced by combining the 2D attention mask with a 2D image. We further merge the attention network and the classification network into a single network. The attention network is used to analyze which part of the image should be more concerned by the classification network. Therefore, mutual learning of 2D data and 3D data is realized in the training process, which reduces the dependence on the number of samples and enhances the generalization performance of the model. Experiments on the defect dataset verify that our method can improve the classification effect of the model.
In this paper a method to estimate surface roughness of sand land from multi-angle and multi-waveband polarized detections is presented. Firstly, the polarized bidirectional reflectance distribution function (pBRDF) of the sand land’s surface based on the microfacet theory was established. Then three sand samples with particle sizes of 0.5 mm, 0.7 mm and 1 mm were obtained by a series of sieves. And the polarization information was acquired by full-polarized multispectral imaging system based on Liquid Crystal Variable Retarder (LCVR). We used the nonlinear least squares method to estimate the surface roughness of from the measured data. Lastly, the analysis results show that the accuracy of sand roughness estimation is improved as the number of the angles (i.e., source incident angles and detection angles) and wavebands increase until the estimation accuracy saturates. It is indicated that the method based on polarization imaging detection to estimate sandy land surface roughness is effective.
A new method to detect ship target at sea based on improved segmentation algorithm is proposed in this paper, in which the improved segmentation algorithm is applied to precisely segment land and sea. Firstly, mean value is replaced instead of average variance value in Otsu method in order to improve the adaptability. Secondly, Mean Shift algorithm is performed to separate the original high spatial resolution remote sensing image into several homogeneous regions. At last, the final sea-land segmentation result can be located combined with the regions in preliminary sea-land segmentation result. The proposed segmentation algorithm performs well on the segment between water and land with affluent texture features and background noise, and produces a result that can be well used in shape and context analyses. Ships are detected with settled shape characteristics, including width, length and its compactness. Mean Shift algorithm can smooth the background noise, utilize the wave’s texture features and helps highlight offshore ships. Mean shift algorithm is combined with improved Otsu threshold method in order to maximizes their advantages. Experimental results show that the improved sea-land segmentation algorithm on high spatial resolution remote sensing image with complex texture and background noise performs well in sea-land segmentation, not only enhances the accuracy of land and sea boarder, but also preserves detail characteristic of ships. Compared with traditional methods, this method can achieve accuracy over 90 percent. Experiments on Worldview images show the superior, robustness and precision of the proposed method.
High spectral resolution is the main characteristic of hyperspectral remote sensing. The image of objects includes various
information of space, radiation and spectral information, and we can also construct a continuous spectrum curve in the
imaging range. The purpose of topographic correction is to eliminate the effects of solar light , which may make the
spectral curve not accurate compared with the practical curve, on radiation values of irregular ground object.
This paper is to analysis the advantages and disadvantages of various topographic correction methods, and provide
accurate experimental data for quantitative remote sensing, which based on the area of airborne hyperspectral remote
sensing image and DEM, comparing with the measured spectral curve.
The quantitative evaluation of detection algorithms performance is a key for the advancement of target detection
algorithms. The receiver operator Characteristic (ROC) curve method is purposed to evaluate the detection algorithms
performance for hyperspectral data in the basis of the analysis and comparison of kinds of evaluation methods. A ROC
curve plots the probability of detection (PD) versus the probability of false alarm (PFA) as a function of the threshold,
and the detection performance can be synthetically evaluated using the shape of ROC curve and the area under the curve.
The algorithm and modeling method are presented in our work. The ROC curve is applied to evaluate the performance of
independent component analysis (ICA), RX, gauss markov random field (GMRF), and projection pursuit (PP) algorithms
for hyperspectral remote sensing data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.