Search

Aerial imagery is important in remote sensing applications. Unmanned aerial vehicle (UAV) has a wide range of applications in remote sensing and presents a substantial cost-effective soluti...

Aerial scene classification purposes to automatically label aerial images with specific semantic categories. However, cataloguing presents a fundamental problem for high-resolution remote-sensing imagery HRRS. Recent developments include several approaches and numerous algorithms address the task. This article proposes a convolutional neural network CNN approach that utilizes sparse coding for scene classification applicable for HRRS unmanned aerial vehicle UAV and satellite imagery. The article has two major sections: the first describes the extraction of dense multiscale features multiple scales from the last convolutional layer of a pre-trained CNN models; the second describes the encoding of extracted features into global image features via sparse coding to achieve scene classification. The authors compared experimental outcomes with existing techniques such as Scale-Invariant Feature Transform and demonstrated that features from pre-trained CNNs generalized well with HRRS datasets and were more expressive than low-and mid-level features, exhibiting an overall 90.3% accuracy rate for scene classification compared to 85.4% achieved by SIFT with sparse coding. Thus, the proposed CNN-based sparse coding approach obtained a robust performance that holds promising potential for future applications in satellite and UAV imaging.

Monitoring vegetation encroachment under overhead high voltage power line is a challenging problem for electricity distribution companies. Absence of proper monitoring could result in damage to the power lines and consequently cause blackout. This will affect electric power supply to industries, businesses, and daily life. Therefore, to avoid the blackouts, it is mandatory to monitor the vegetation/trees near power transmission lines. Unfortunately, the existing approaches are more time consuming and expensive. In this paper, we have proposed a novel approach to monitor the vegetation/trees near or under the power transmission poles using satellite stereo images, which were acquired using Pleiades satellites. The 3D depth of vegetation has been measured near power transmission lines using stereo algorithms. The area of interest scanned by Pleiades satellite sensors is 100 square kilometer. Our dataset covers power transmission poles in a state called Sabah in East Malaysia, encompassing a total of 52 poles in the area of 100 km. We have compared the results of Pleiades satellite stereo images using dynamic programming and Graph-Cut algorithms, consequently comparing satellites’ imaging sensors and Depth-estimation Algorithms. Our results show that Graph-Cut Algorithm performs better than dynamic programming (DP) in terms of accuracy and speed.

A novel framework is proposed for mitigating azimuth ambiguities in spaceborne stripmap synthetic aperture radar (SAR) images. The azimuth ambiguities in SAR images are localized by using a local mean SAR image, SAR system parameters, and a defined metric derived from azimuth antenna pattern. The defined metric helps isolate targets lying at locations of ambiguities. The mechanism for restoration of ambiguity regions is selected on the basis of size of ambiguity regions. A compressive imaging technique is employed to restore isolated ambiguity regions (smaller regions of interconnected pixels), whereas clustered regions (relatively bigger regions of interconnected pixels) are filled by using exemplar-based inpainting. The simulation results on a real TerraSAR-X data set demonstrated that the proposed scheme can effectively remove azimuth ambiguities and enhance SAR image quality.

A despeckling technique based on multiple image reconstruction and selective 3-dimensional flltering is proposed. Multiple SAR images are reconstructed from a single SAR image by employing compressive sensing (CS) theory. In order to obtain multiple images from single SAR image, multiple subsets of pixels are selected from input SAR image by imposing restriction that each subset has at least 20% difierent pixels from any other subset. These subsets are taken as measurement vectors in CS framework to obtain multiple SAR images. A despeckled image is obtained by employing selective 3-dimensional flltering to multiple reconstructed SAR image. The proposed technique is tested on single look complex TerraSAT-X data set, and experimental results exhibit that the proposed technique outperformed benchmark despekling methods in terms of visual quality and despeckling quality metrics.

Multi-modal imaging requires image fusion to combine advantages of different types of sensors and requires super-resolution (SR) because of limited spatial resolution of source images. In this study, a novel framework is proposed for unification of image SR and the fusion process to obtain a high-resolution (HR)-fused image from a set of low-resolution (LR) multi-modal images. The jointly trained dictionaries of LR patches and corresponding HR patches are used for sparse representation of LR source image patches and HR-fused image patches, respectively. The sparse coefficients vectors for corresponding patches of source LR images are determined by using orthogonal matching pursuit and a local information content-based metric is employed to fuse these sparse coefficients. The corresponding HR-fused image patch is obtained by combining elements of the HR dictionary as per the fused coefficients of the LR image patches. The experimental results on sets of multi-modal images exhibited that the proposed method outperformed the existing fusion and SR techniques in terms of visual quality and image fusion quality metrics.

Spaceborne synthetic aperture radar (SAR) plays more and more important role in Earth observation science, especially with ScanSAR mode which provides wide-swath coverage with moderate resolution. However, scalloping and inter-scan banding (ISB) are two major artifacts, which signiflcantly degrade the quality of ScanSAR images. In this paper, a novel technique for removal of scalloping and ISB in ScanSAR images is proposed. Scalloping and ISB artifacts are modeled by two-dimensional gain and ofiset parameters varying as function of both azimuth time and range position. The gain and ofiset parameters can be split into azimuth and range components. The variations of gain/ofiset with respect to azimuth and range positions would represent scalloping and ISB artifacts respectively. In the proposed technique, recursive and minimum mean square error (MMSE) estimates of azimuth gain/ofiset parameters are found out by using Kalman fllter for each azimuth location in a subswath by considering corresponding range samples as observation vector. Subsequently, range gain/ofiset parameters causing ISB artifacts are estimated by using Kalman fllter for each range positions by considering azimuth samples as observation vector. The MMSE estimates of gain/ofiset parameters are used to directly remove scalloping and ISB artifacts. The proposed scheme was applied on simulated as well as calibrated real ScanSAR images. The experimental results exhibited the potential of proposed technique to be used as post processing tool for enhancing ScanSAR image quality.

In this paper, design of overcomplete dictionaries based on Discrete Cosine Transform and Discrete Tchebichef Transform using optimization techniques is presented. Further, we optimized our proposed dictionaries based on KSVD algorithm and measured the performance of dictionaries using orthogonal matching pursuit (OMP) and basis pursuit (BP). The result showed that the Dictionary based on Discrete Tchebichef Transform (DTT) performed better as compared to the dictionary based on Discrete Cosine Transform (DCT). The proposed transform is first time introduced to made comparison with the DCT based dictionary generation. The proposed dictionaries are predetermined and optimize using KSVD algorithm. The accuracy will be increase with the slight increase of the computation complexity using Discrete Tchebichef Transform as compared to the Discrete Cosine Transform. The root mean square values are used to measure the accuracy.

In this paper, orthorectification of satellite data from Pleiades satellite sensors based on ground control points (GCPs) is performed. A true orthorectification of satellite data is possible with an accurate digital elevation model (DEM). This study was challenging due to weather condition, hilly, and nonuniform terrain at the city Kota Kinabalu in East Malaysia. First, the geometric accuracy of the sensors is required for 3D mapping of the area of interest. In addition, an accurate DEM for better height calculation of vegetation/trees near power poles is required. For these purposes, first we need the true orthorectification of satellite stereo imagery. The measured GCP is compared with the actual GCPs to evaluate the geometric correction in terms of root mean square error. The comparison was made based on rational polynomial Function (RPC) coefficients and GCP measurements. Results show that the Pleiades satellite sensor is feasible for generating the elevation model for small area. This shows that Pleiades sensor can be used for monitoring the vegetation near poles of high transmission power lines based on the satellite stereo images.

The monitoring of trees and vegetation near high voltage transmission power lines is a tedious job for electrical companies. There are many blackouts occur due to interfering the trees with the power transmission lines in hilly as well as urban areas. This is a big challenge for power distribution companies to monitor the vegetation for avoiding the blackouts and flashovers. To solve these problems, there are many methods are used to monitor the trees and vegetation near transmission power poles. But the existing methods are expensive and time consuming. We proposed the new method based on satellite images to monitor the trees and vegetation. The satellite images provide the cost effective solution to solve the monitoring problem. In this paper, we proposed the stereo matching algorithms to measure the disparity map based on satellite stereo imagery. The height estimation of trees and vegetation near power poles based on depth map which is inversely proportional of the disparity map. For measuring the depth map, the dynamic programming (DP) and block matching with energy minimization has been proposed. These techniques are applied on the satellite stereo images and based on results, our proposed DP algorithm produced more accurate disparity map as compared to the block matching algorithm.

Vegetation encroachment under overhead high voltage power lines and its monitoring is a challenging problem for electricity distribution companies. Blackout can occurs if proper monitoring of vegetation is not done. The uninterrupted electric power supply is vital for industries, businesses, and daily life. Therefore, it is mandatory for electricity companies to monitor the vegetation/trees near power lines to avoid the blackouts. Pulse-coupled neural network (PCNN) considered as differently from converntial neural networks used in many signal and image processing applications. The main step to develop the automatic detection of vegetation is performing an image segmentation which is normally used to identify or marking of vegetation from the acquired images. We apply PCNN for image segmentation on satellite images for vegetation monitoring purposes and compared the performance with a thresholding image segmentation method with Pulse coupled neural network. The results show that PCNN produce outperform as compared to the thresholding method in terms of detection accuracy.

Vegetation encroachment of high voltage power line endorsement space is an exceeding problem for electricity distribution companies. The electrical utilities have responsibility to impose their vegetation management proceeding so as to evade vegetation/ trees near transmission power lines. When the height of trees/vegetation is increased and it makes a contact with the power lines, it may antecedent the power lines in result of blackouts. Blackouts come about due to vegetation encroachments can cause impressive compensation. The uninterrupted electric supply is very imperative for industries, businesses, and populous areas. It is indispensable for electricity companies to monitor the vegetation/trees near power lines, There are many approaches applicable to monitor vegetation/trees near the transmission line poles, but these approaches are time inefficient in terms of time and finance. In this paper, a novel technique for depth estimation of vegetation/trees is proposed. In the study, Dynamic Programming is employed on stereo satellite images to determine depth of vegetation and trees. The experimental results on QuickBird imagery exhibit that the proposed technique performs better compared to block matching technique in terms of accuracy.

Continuous monitoring the vegetation encroachment for high voltage transmission lines is challenging task for electrical distribution authorities. The enchroachment causes interruption which results in blackouts. It also endures great cost to the authorities for maintenance and damage compensation. There are many methods available to monitor growth of vegetation near transmission line poles. However, these methods are constrained with time consumption and cost. In this paper,a new method based estimating 3D height/depth of vegetation or trees near transmission lines using satellite stereo vision is proposed. We have evaluated local methods of stereo matching using Quickbird Satellite stereo images and compare the performance of stereo matching cost functions in terms of processing speed and time. Results show that our proposed algorithm is faster and more accurate than the existing algorithm for disparity calculation.

Vegetation encroachment under overhead high voltage power line and its monitoring is a challenging problem for electricity distribution companies. Blackout can occurs if proper monitoring of vegetation is not done. The uninterrupted electric power supply is vital for industries, businesses, and daily life. Therefore, it is mandatory for electricity companies to monitor the vegetation/trees near power lines to avoid the blackouts. Many approaches are employed to monitor vegetation/trees near the transmission line poles, but these approaches are more time consuming and expensive. In this paper, we have proposed a novel approach to monitor the vegetation near or under the power poles using satellite stereo images which were acquired using QuickBird and IKONOS satellites. 3D depth of vegetation has been measured using stereo algorithm incorporating dynamic programming. We have also compared the results of QuickBird and IKONOS satellite stereo images. Results showed that QuickBird satellite image performs well as compared to IKONOS using stereo vision global optimization dynamic programming algorithm in terms of accuracy and speed.

A new technique based on best bases sparse representation is proposed for fusion of remote sensing images. In order to carry out multi-resolution image fusion, low-resolution image is upscaled to match resolution of high-resolution images. Corresponding patches from remote sensing images are represented by finding out best bases from over-complete dictionaries comprising of elements derived from basis function of DCT, Wavelets, ridgelets, and curvelets. The corresponding bases of image patches are combined based on local information parameter (LIP) derived from respective patches. The use of LIP helps ensure transfer of details in high-resolution image into fused image.

A novel image denoising technique is proposed using compressive reconstruction framework. Multiple subsets of pixels with partial overlap are selected from noisy image. The subsets of pixels are selected in such a way that every subset will have at least 20% different pixels compared to any other subset. Each subset of pixels is considered as vector of compressive samples from noisy image and a complete image is reconstructed in wavelet domain using compressive sensing reconstruction algorithm. The multiple images obtained from these subsets are merged using statistical techniques to obtain clean image. The proposed technique is tested on several images with different noise level and it was observed that proposed technique produced better denoising results compared to other denoising techniques using wavelets representation of noisy image.

Bandelets transform exploits geometric information of image to determine bandelets coefficients. Bandelets basis has been used for compression of geometrical images and image denoising. In this paper, bandelets basis are used for compressive imaging of natural images using benchmark and efficient l1 minimization algorithms. Conventional compressive sampling matrices would not be suitable to extract geometric information required for construction bandelets basis. In this work, a so-called regular point sampling matrix is used to find out the geometric regularity of images. The experimental results on a set of natural images show that natural images can be reconstructed by using bandelet basis with higher PSNR and good visual quality. The bandelets based compressive sampling method outperformed conventional compressive imaging frameworks.

Space invariant object recognition is one of the difficult problems of pattern recognition and has many potential applications. In this paper, a vehicle recognition system is proposed for toll plaza monitoring and auditing. This system recognizes the type of approaching vehicle such as truck, bus, car etc. irrespective of geometrical distortion of vehicles such as scale and rotation. Maximum Average Correlation Height (MACH) filter is used to obtain out-of-plane rotation invariance and Log r-o Mapping is employed to achieve in-plane and scale invariance. Five classes of vehicles are defined: trucks, buses, wagons, cars and motorcycles. MACH filter is trained on log r-o maps of each class of vehicles for range of orientation and correlated sequentially with the log r-o map of region of interest. The type of vehicle is recognized from correlation results. The system analyzes the real time toll plaza video and generates audit report indicating the total count of each type of vehicles during a specified time and the resulted toll collection according to their respective charges. The system also generates monitoring alerts as per given decision rules.

Papers impregnated with zinc silicate have been used for the chromatographic studies of amines taken in the form of their hydrochlorides. Rf values of various amines have been determined and compared with its behaviour on plain papers. Quantitative separations of dimethylamine from methylamine, α-naphthylamine, o-toluidine and o-nitroaniline; o-phenylenediamine from m-phenylenediamine; diphenylamine from piperidine have also been achieved on columns loaded with zinc silicate exchanger.