Multispectral images have more spectral bands compared to RGB color images and also contain more information. Therefore, multispectral images have a wide range of applications, including atmospheric environment detection, medical diagnostics, agricultural disease detection, and food monitoring. Because acquiring raw multispectral images requires embedding multiple cameras and various mechanical and optical components to image them once, these systems are very heavy and not inexpensive, so their use is limited. In order to solve these problems, a kind of sensor technology called Multispectral Filter Array (MSFA) has become a hot topic and gradually developed. Snapshot multispectral imaging based on MSFA can lead to severe sparsity in each channel of the original captured image. Each pixel on the detector based on MSFA only responds to the optical information of the corresponding spectral band, so the other spectral band information of the pixel is lost. We refer to the original image captured based on MSFA as mosaic image. In order to obtain multiple single spectral band images with full resolution, we need to carry out a process called demosaicking on the original image. In this article, we present a generic demosaicking approach based on inter-channel spectrum correlation. In order to verify the effect of the proposed approach, we conducted some validation experiments on a public database. Experimental results show that the proposed approach is better than the classical methods in spatial reconstruction and spectral accuracy.
Hyperspectral anomaly detection (HAD) is a technique to find observations without prior knowledge, which is of particular interest as a branch of remote sensing object detection. However, the application of HAD is limited by various challenges, such as high-dimensional data, high intraclass variability, redundant information, and limited samples. To overcome these restrictions, we report an unsupervised strategy to implement HAD by dimensionality reduction (DR) and prior-based collaborative representation with adaptive global salient weight. The proposed framework includes three main steps. First, we select the most discriminating bands as the input hyperspectral images for subsequent processing in a DR manner. Then, we apply piecewise-smooth prior and local salient prior to collaborative representation to produce the initial detection map. Finally, to generate the final detection map, a global adaptive salient map is applied to the initial anomaly map to further highlight anomalies. Most importantly, the experimental results show that the proposed method outperforms alternative detectors on several datasets over different scenes. In particular, on the Gulfport dataset, the area under the curve value obtained by the proposed method is 0.9932, which is higher than the second-best method, convolutional neural network detector, by 0.0071.
Anomalous objects detection for hyperspectral imagery is a significant branch in the area of remote sensing. Although enormous advancements have been developed, issues of redundancy of spectral information and correlation between pixels should be further explored and improved. To address these problems, we proposed a method that is on the basis of integrating collaborative representation with multipurification processing and local salient weight. Multipurification processing consists of spectral bands purification (SBP) and background purification (BGP). First, to alleviate the interference of redundant spectral information, we remove unnecessary spectral bands by adopting SBP based on considering the global spectral intensity of each band. Then, we remove the outliers in the local dual window by BGP to avoid the effect of heterogeneous pixels. Simultaneously, we obtain the local salient weight by calculating the similarity and difference of pixels in the dual window. Next, we obtain the initial detection result by a collaborative representation, which has been testified to be very effective. Finally, combined with the local salient weight map, the initial detection map is improved to the final detection map. To demonstrate the superiority of the proposed method, we conducted the comprehensive experiment on three public benchmark datasets that contain 15 hyperspectral images.
Change detection is an important research direction in the field of remote sensing technology. However, for hyperspectral images, the nonlinear relationship between the two temporal images will increase the difficulty of judging whether the pixel is changed or not. To solve this problem, a hyperspectral change detection method is proposed in which the transformation matrices are obtained by using the constraint formula based on the minimum spectral angle, which uses both spectral and spatial information. Further, a kernel function is used to handle the nonlinear points. There are three main steps in the proposed method: first, the two temporal hyperspectral images are transformed into new dimensional space by a nonlinear function; second, in the dimension of observation, all the observations are combined into a vector, and then the two transformation matrices are obtained by using the formula of spectral angle constraint; and third, each pixel is given weight with a spatial weight map, which combined the spectral information and spatial information. Study results on three data sets indicate that the proposed method performs better than most unsupervised methods.
Data imbalance is a common problem in hyperspectral image classification. The imbalanced hyperspectral data will seriously affect the final classification performance. To address this problem, this paper proposes a novel solution based on oversampling method and convolutional neural network. The solution is implemented in two steps. Firstly, SMOTE(Synthetic Minority Oversampling Technique) is used to enhance the data of minority classes. In the minority classes, SMOTE method is used to generate new artificial samples, and then the new artificial samples are added to the minority classes, so that all classes in the training dataset can reach to the balanced distribution. Secondly, According to the data characteristics of hyperspectral image, a convolutional neural network is constructed for classifying the hyperspectral image. The balanced training data set is used to train the convolutional neural network. We experimented with the proposed solution on the Indian Pines, Pavia University dataset. The experimental results show that the proposed solution can effectively solve the problem of imbalanced hyperspectral data and improve the classification performance.
KEYWORDS: Image segmentation, Image processing algorithms and systems, Signal to noise ratio, Binary data, Cameras, Feature extraction, Lithium, Sensors, 3D vision, Stereo vision systems
Low-light stereo vision is a challenging problem because images captured in dark environment usually suffer from strong random noises. Some widely adopted algorithms, such as semiglobal matching, mainly depend on pixel-level information. The accuracy of local feature matching and disparity propagation decreases when pixels become noisy. Focusing on this problem, we proposed a matching algorithm that utilizes regional information to enhance the robustness to local noisy pixels. This algorithm is based on the framework of ADCensus feature and semiglobal matching. It extends the original algorithm in two ways. First, image segmentation information is added to solve the problem of incomplete path and improve the accuracy of cost calculation. Second, the matching cost volume is calculated with AD-SoftCensus measure that minimizes the impact of noise by changing the pattern of the census descriptor from binary to trinary. The robustness of the proposed algorithm is validated on Middlebury datasets, synthetic data, and real world data captured by a low-light camera in darkness. The results show that the proposed algorithm has better performance and higher matching rate among top-ranked algorithms on low signal-to-noise ratio data and high accuracy on the Middlebury benchmark datasets.
Small anomaly detection in ocean evironment is an important problem in airborne remote sensing image processing, especially in hyperspectral data. Traditional algorithms solve this problem by finding the pixels have different appearance pattern with the background. However, these algorithm are not suitable for real-time applications. In this paper, we propose to learn the hyperspectral model of the seawater and localize the targets whose spectral feature do not well fit the trained model. This algorithm only uses historical information and is suitable to be used on airborne line-scanning data. Since hyperspectral property of ocean water is relatively stable, we use Gaussian mixture model to encode the statistical features of the background. Experimental results demonstrated that the proposed algorithm significantly improves processing efficiency in comparison with conventional methods, and maintains high accuracy with regard to other methods.
Using coated mosaic video spectrometer to collect multispectral image which reduce the spectral information redundancy and data volume greatly and achieve real-time data transmission conditions. The mosaic video spectrometer imaging technique use a similar mosaic template to capture all the pixels and output a two-dimensional multi-spectral image with dozens of spectral information. The image is divided into a certain size of matrix in its field, and each pixel in the pixel matrix is only for one wavelength information response and every pixel response for different wavelength. The size of the pixel matrix block depends on the number of spectral segments, which results in a low spatial resolution of the single spectral segment image and the spectral information of each pixel absenting severely. Therefore, to reconstruct the complete multi-spectral image, we must estimate and interpolate the missing spatial information and spectral information by demosaicking multispectral image. In this paper, we present a novel demosaicking method to produce the high resolution multispectral image and reconstruct missing spectrum information in high accuracy. The proposed method computes the first-and second-order derivatives of the original single multispectral image to measure the geometry of edges in the image and the spectrum value of missing pixel. Two metrics are used to evaluate the generic algorithm, including the structural similarity index-measurement system (SSIM) for reconstruction performance and the procession time. Experimental results show that the demosaicked images present higher SSIM (more than 0.9) and comparable calculated time performance as traditional ways. This algorithm brings the greatest advantage that make up for the weakness of mosaick multispectral image and reduce the data transmission process cost and storage needs.
With the development of computer vision and image processing technology, vision measurement has been paid more and more attention. In the aviation field, estimating the relative attitude of aircraft using computer vision is important in aircraft flight-refueling, target tracking and positioning. However, the existing methods to measure the attitude of aircraft have some problems. In this paper, we propose to use binocular vision measurement method to acquire the attitude data of aircraft. This method has the advantages of simple realization and high practical value, which can also be widely used in visional measurement applications.
Target detection and tracking important in many applications including intelligent monitoring system, defense system and terminal guidance system. Aiming to solve the problem of simulated target tracking, this paper proposes an adaptive algorithm which uses the fusion of the spectral and morphological features of multispectral image to realize the target tracking based on the Particle Filter. Firstly, the target area is manually initialized in the multispectral image and the spectral and texture features of the target are extracted. Secondly, we build the adaptive tracking model of multiple features under the framework of Particle Filter. We validate the effectiveness of the proposed approach on the MATLAB platform. The results show that the proposed approach achieves accurate and stable multispectral target tracking in complex scenes by improving the efficiency of particles usage under defective tracking conditions, which is of great theoretical and practical values for the application of multispectral target tracking technology.
Large aperture static interferometer spectrometer (LASIS) use the method of push-boom to get the geometric and spectral characteristics of ground target, the particularity of principle requires the movement of satellite must be in the same direction with spectrometers detectors. Drift angle of satellite leading to abnormal image shifts in the column direction which should be perpendicular to the detector and can seriously affect the spectrum recovery precision of collected data. This paper analyzes the influence mechanism of drift angle for spectrum recovery precision. Simulation based on the actual on-orbit data analyses the effects of different drift angle of relative mean deviation and relative secondary deviation rehabilitation of the spectrum, besides the influence of spectral angle similarity. These studies have shown that, when the lateral deviation due to the drift angle on the across track is less than 0.3 pixel, the effect for the relative mean deviation of the inversive spectra will be no more than 7%. when the lateral deviation due to the drift angle on the across track is larger than one pixel, even though the resampling correction is proceeded, the restored spectral data cube still shows an relative mean error more than 10%, which seriously affect the availability of spectral data.
We propose an approach to correct the data of the airborne large-aperture static image spectrometer (LASIS). LASIS is a kind of stationary interferometer which compromises flux output and device stability. It acquires a series of interferograms to reconstruct the hyperspectral image cube. Reconstruction precision of the airborne LASIS data suffers from the instability of the plane platform. Usually, changes of plane attitudes, such as yaws, pitches, and rolls, can be precisely measured by the inertial measurement unit. However, the along-track and across-track translation errors are difficult to measure precisely. To solve this problem, we propose a co-optimization approach to compute the translation errors between the interferograms using an image registration technique which helps to correct the interferograms with subpixel precision. To demonstrate the effectiveness of our approach, experiments are run on real airborne LASIS data and our results are compared with those of the state-of-the-art approaches.
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.