Earticle

With the aim to solve the problems of large amount of image data transmission and low accuracy of the initial background image extracted in traditional vehicle detecting system, this article proposes a road vehicle detecting algorithm based on compressive sensing. Image signals are sparse in a wavelet basis and the Gaussian random measurement matrix is adopted to compress videos, which reduce the amount of image data transmission. This article uses the proposed improved initial background extracting method and selective background updating method to obtain the initial background image and background updating which improves the accuracy of the initial background image. The vehicle detection and selective reconstruction of foreground image of vehicle are achieved by integrated background subtraction and the orthogonal matching pursuit algorithm. Through many experiments in video monitoring of real scenes, the article proves the correctness and efficiency of the algorithm. It not only improves the accuracy of the initial background image extracted but also reduces the amount of image data transmission and power consumption as well as the price of video transmission.

Image enhancement plays an important role in vision applications. Recently much work is performed in the field of images enhancement. Many techniques have already been proposed up to now for enhancing the digital images. The overall objective of this proposed work is to evaluate the performance of existing image enhancement techniques like Histogram equalization, adaptive histogram equalization and Fuzzy image enhancement technique. It has been found that the value of contrast parameter ‘K’ in fuzzy method was taken statically as 128. To overcome this, to make contrast dynamic a new optimized fuzzy method have been proposed. Here different optimization techniques ACO, PSO and ABC have been used to optimize the contrast and the technique with best optimized contrast value is selected. The newest approach has the ability to boost the contrast in digital images in efficient manner by utilizing the histogram based fuzzy image enhancement algorithm with optimized Contrast value. The proposed technique is designed and implemented in MATLAB using image processing toolbox.

With the increase of voltage level and more and more secondary devices are located in field, the secondary circuit of substation is in a strong electromagnetic environment. Because the secondary circuit is affected by the interference of switch operations, there are many trip accidents happened in substations without any fault in recently years, which constitutes a serious threat to the power network and harms the safe operation of the electric power system. It is of great theoretical significance and practical value to study the Electromagnetic Compatibility problem of the transformer substations substation secondary circuit. In this paper, the abnormal phenomenon of one 110kV intelligent substation merging unit is described. And the reason of the abnormal phenomenon is analyzed. Firstly, the Electromagnetic Compatibility experiments specified by the IEC61000-4 standard are carried out. Furthermore, to verify the anti–interference performance of the merging unit, the Electromagnetic Compatibility experiments above the standard are carried out. The structure of merging unit is improved until the merging unit operates normally. Secondly, to quantitatively analyze the disturbance strength, the electromagnetic disturbance signal is recorded, and the characteristics of amplitude and time-frequency of the recorded signal are analyzed. Thirdly, the characteristics of the logged signal are compared to the IEC61000-4 standard. Finally, this paper puts forward some suggestions about improving the Electromagnetic Compatibility performance of merging unit.

The performance of ear recognition is influenced by pose variation. For the similar position of ear and profile face, a multimodal recognition method is proposed based on the feature fusion of ear and profile face information. A model for ear and profile face feature fusion and recognition is built. The Log-Gabor features of ear and profile face are first extracted separately, and two features are integrated into a combined feature after two Log-Gabor features are standardized. Then combined feature is mapped to kernel space to fuse further, and acquired stronger discriminant feature for classification by kernel Fisher discriminant analysis (KFDA). The minimum distance classifier is finally used in recognition. Experimental results on the profile face database of Notre Dame University show that the fused method improves the recognition rate of pose variation, and the performance of multimodal recognition is better than unimodal recognition using either ear or profile face alone. The method of ear and profile face feature fusion and recognition is effective and robust for the pose variation.

The text localization and recognition in real time scene text images is still a big issue in current application. Mobile application and digitization in real world gives a vital and broad impact on real time scene text images. However, the efficiency of recognition rate depends upon the text localization, i.e., higher the purity of text background segmentation and decomposition, higher the rate of accuracy for the image recognition. In this paper, we present a new scene text detection algorithm based on Stroke detection and Hog Transform method. The method introduces an approach for character detection and recognition which combines the advantages of Hog Transform and Connected Component methods. Characters are detected and recognized on the basis of image regions which contain strokes of specific orientations in a specific relative position, where the strokes are efficiently detected by convolving the image gradient field with a set of oriented bar filters. The method was evaluated on a standard dataset consisting mostly real time images where it achieves state-of-the-art results in both text localization and recognition. The results clearly depict the higher bit of accuracy in terms of localization and recognition for a collected dataset.

The traditional image retrieval method is based on single feature retrieval method like color, texture, shape or multi feature weighted fusion method. The retrieval rate of existing methods is not high. This paper presents fusion multi feature image retrieval. Two kinds of feature play a complementary effect in retrieval. Most color feature can not reflect the spatial information of image. Texture is a regional characteristics which contains important spatial information of image. Fusing the color and texture feature can play their respective advantages. At the same time, avoiding the one-sidedness of single feature retrieval. Improving the retrieval accuracy and flexibility well.

Intel RealSense™ is an exciting new technology that offers innovative multimodal human computer interaction with hand tracking, face tracking, emotion detection, speech synthesis and voice recognition. The technology supports real time background separation by combining the depth and RGB streams of RealSense™ camera. Several past works have provided robust techniques for background separation. Background separated frame is used to augment segmented user photo in an artificial scene. In this work we propose a novel real time technique for augmenting the user in an artificial scene and apply various image filters on the constructed scene. We also propose a “Split Grid” based novel hand gesture driven UI control system that enables the user an intuitive way of working with the system with on-air hand movement and gesture. The system can be used in a wide range of applications like puppetry, photo retouching, and video recording on augmented scene .Usability tests performed by both amateur as well as professional digital photo artists proves ease and efficiency of the tool in generating quick wonderful photo effect in multimodal environment.

From the perspective of the two-dimensional image processing threshold departure, combining the fuzzy theory and two-dimensional entropy algorithm, collecting and processing trees image contained calibration information point, to determine the optimum threshold value, achieve precise image information extraction point of trees. During the experiment,will be gathering information points marked red rectangle on the image of the trees, and the use of binocular vision platform for the collection, then using the membership based on fuzzy theory merge trees image smoothing, the principle of maximum degree of membership criteria for the selection of the pixel template, optimized calibration point boundary and details, combined with the two-dimensional entropy algorithm to determine the optimal threshold, realize precise point of the image information extraction. The results show that the information point for calibration, image processing method adopted fuzzy theory and two-dimensional entropy algorithm combining, extracting information points is more accurate, clear, can better reflect the characteristics of the image information points, and can achieve the wireless remote monitoring studies of trees, and promote the rapid development of information technology forestry laid a good technical and theoretical foundation.

Now a days, because of enhancement in high speed computing elements, high voltage controlled semi-conductor devices and emergence of new power circuit topologies, the Voltage Source Converter (VSC) based Active Power Filter (APF) is finding applications for compensating harmonic currents drawn by the various loads. As the active filter consists of semi-conductor devices alone, the response time of this device is very fast and it doesn’t suffer from resonance and other stability problems as faced by the normal passive filters. The Active filters are generally used at harmonic producing loads. Among all APF’s the Shunt Active Power Filter (SAPF) is more prominent at medium/high voltage applications, and also it provides higher efficiency. SAPF in the power circuit can be used either by using the voltage-sourced PWM converter equipped with a DC capacitor or a current-sourced PWM converter equipped with a DC inductor. This paper presents an approach to determine reference compensation currents of the three-phase SAPF under distorted and/or unbalanced source voltages in steady state. It is planned to design a Synchronous Reference Frame (SRF) controller for Voltage Source Converter (VSC) based Shunt active power filter for harmonic compensation. The simulation results have been obtained by using MATLAB/ SIMULINK.

Power quality (PQ) disturbances recognition is the foundation of power quality analysis and improvement. In order to improve the classification accuracy and efficiency, a new classification approach based on modified Fourier neural networks (FNN) and Hyperbolic S-transform (HST) was designed for PQ disturbances classification. HST has better a time-frequency resolution than S-transform. The features extracted from HST results compose the input vectors of classifier. The DFP emendatory Quasi-Newton method is used to improve the learning ability of FNN and avoid local minimum problem. Three modified FNNs were used to construct a classifier with the structure of decision tree. Six types of disturbances with different noise ratio were simulated to test the classification ability of the new approach. Simulation results show that the new classifier has better classification accuracy than other classifiers based on BP neural networks and Fourier neural networks. The new approach is effective.

To remove the impact of noise on the ultrasonic testing signals of standing trees, wavelet transform method was used to eliminate the noise in the collected ultrasonic signals in the field. In order to achieve the best denoising effect, four kinds of wavelet base denoising parameters including Daubechies (db), Symlets (sym), Coiflets (coif), and Discrete Meyer (dmey) were compared, and the best denoising effect was obtained with db3 wavelet base. The variations of denoising parameters corresponding to the number of db3 wavelet decomposition levels (1- 8) were further analyzed and the decomposition level 4 was demonstrated the best. Meanwhile, the effects of wavelet denoising under different threshold states were compared and the hard rigrsure threshold was demonstrated the best. Experimental results showed that the wavelet transform can effectively remove noise hidden in the ultrasonic signal and improve the denoising effect by selecting reasonable parameters, which laid some initial groundwork for efficient extraction of useful information from the ultrasonic signals.

Unified power quality conditioner is one of the advanced forms of power conditioning device, which is a combination of back to back connected series APF and shunt active power filter (SAPF) connected to a common DC link voltage. This topology will facilitates this device to have a reduced dc-link voltage without reducing its compensation capability. This device is mainly used in improving the power quality. For the improvement of power quality (PQ) complications in a 3-phase 4-wire distribution system, two topologies are presented. In this paper a four-leg voltage source inverter (VSI) based topology of a four-wire UPQC is discussed in this work. The performance of each topology of this device is evaluated for different PQ problems such as voltage harmonic mitigation, load balancing, source neutral current mitigation, current harmonic mitigation, and power-factor correction. The main purpose this device is to compensate load current and supply voltage imperfections. Converter and control analysis is presented together with the results showing the modes of operation. Detailed design aspect of the series capacitor and VSI parameters has been discussed in this paper. For better power quality improvement the PI controller is replaced by the fuzzy controller and the results are verified. The proposed topology enables UPQC to compensate current harmonics, voltage sags, and voltage swells with a reduced DC-link voltage without reducing its compensation capability by resolving the circuit in MATLAB/SIMULINK software.

The traditional dual differential luminance algorithm was influenced by the surrounding environment, and was not applicable to accurate detection at night. In view of the interference factors of reality, this paper improved the dual differential luminance algorithm by using the method of amending coefficient. Meanwhile, combined with the traffic emergency control measures under different visibility, ten detection modes were subdivided. The next, an experimental system was built in the Meteorological Observatory of Beijing, and the detection software was developed. At last, the experimental data was compared with the correlation values of scatterometer. The results show that the detection accuracies are raised, and the optimized algorithm and system can be used for highway network visibility detection.

Image denoising is the manipulation of the image data to produce a visually high quality image. At present there are a variety of methods to remove noise from digital images. There are different types of filters like mean filter, median filter, bilateral filter, wiener filter etc. to remove a single type of noise such as salt and pepper noise, speckle noise, Gaussian noise etc. But if the image is corrupted by mixed noise then these filters do not remove the noise exactly. Here a white flower image has been taken for denoising purpose. The white flower image is corrupted by mixed noise at zero mean and different variances to produce different noisy images at zero mean and respective variances. Noisy image is denoised by discrete wavelet transform (DWT) denoising technique using ‘Haar’ wavelet and different filters like median filter, wiener filter and bilateral filter one-by-one to produce noise free image as much as possible. Different parameters like MSE (mean square error), PSNR (peak signal to noise ratio), RMSE (root mean square error), SNR (signal to noise ratio) and SSIM (structural similarity index) estimate the performance of all filters. Special filter is designed with the help of these performance estimations so that a better filter for mixed noise image denoising purpose can be implemented. All mixed noisy images are denoised by the special filters and their performance parameters are estimated. The special filter is a combination of various filters and denoising techniques to remove of mixed noise from a digital image. The comparisons between noisy and denoised images of the special filter and other filters are presented in the form of graphs and tables.

Key events in football videos are fetched on the basis of accurate detection of shots. A quick and effective algorithm for detecting football video shots has very important meanings. Here it focuses on features of football videos by combining with a few basic shot detection methods to propose one shot detection method applicable for football videos. The experiment shows the feasibility of the proposed algorithm, and the experimental data shows that the algorithm has a good effect for soccer video shot detection and key frame extraction

In this paper, we propose a novel method to solve the problem of targets association and tracking across multiple cameras of non-overlapping views. The method is divided into two parts. One is an improvement on appearance transfer model, another is an improvement on spatio-temporal transfer model. To learn inter-camera appearance transfer models, lαβ color space is used to calibrate images. By this way, the overall and local information can be used, which has advantage to color transform correction. To learn spatio-temporal transfer model, entry/exit zones of a non-overlapping topology can be effectively estimated by defining valid link and using clustering method. Then a kind of time constrain is set between two nodes to judge whether there is correlation of observations. Experiments show the effectiveness of the proposed method.

Images include information about human body which is used for different purpose such as medical examination security and other plans Compression of images is used in some applications such as profiling information and transmission systems. Regard to importance of images information, lossless or loss compression is preferred. Lossless compressions are JPEG, JPEG-LS and JPEG2000 are few well-known methods for lossless compression. We will use differential pulse code modulation for image compression with Huffman encoder, which is one of the latest and provides good compression ratio, peak signal to noise ratio and minimum mean square error. In real time application which needs hardware implementation, low complex algorithm accelerate compression process. In this paper, we use differential pulse code modulation for image compression lossless and near-lossless compression method is introduced which is efficient due to its high compression ratio and simplicity. This method is consists of a new transformation method called Enhanced DPCM Transformation (EDT) which has a good energy compaction and a suitable Huffman encoding. After introducing this compression method it is applied on different images from Corel dataset for experimental results and analysis. Also we compare it with other existing methods with respect to parameter compression ratio, peak signal noise ratio and mean square error.

A novel approach of Content Based Image Retrieval(CBIR), which combines color, texture and shape descriptors to represent the features of the image, is discussed in this paper. The proposed scheme is based on three noticeable algorithms: color distribution entropy(CDE), color level co-occurrence(CLCM) and invariant moments. CDE takes the correlation of the color spatial distribution in an image into consideration. CLCM matrix is the texture feature of the image, which is a new proposed descriptor that is grounded on co-occurrence matrix to seize the alteration of the texture. Hu invariant moments are frequently used owing to its invariance under translation, changes in scale, and also rotation. The proposed scheme achieves a modest retrieval result by utilizing these diverse and primitive image descriptors, at the same time, the retrieval result is better when use the texture feature alone which we proposed than use gray level co-occurrence. The similarity measure matrix is based upon Euclidean distance.

A 4th-Order Wideband Sigma Delta modulator structure is proposed in this paper, which uses linear system theory technique. There are many implementation techniques to improve the performance of Sigma Delta ADCs, such as noise coupling, differential sampling and dynamic elements matching. An extra loop delay is needed to be added in the system. This paper explains how to make the modulator stable with the addition of feed-forward and feed-back branches which are used to compensate the extra loop delay. Next, we restore the signal and noise transfer functions. A 4th-Order Wideband delta-sigma modulator have been designed and simulated to verify the method.

With the fast development of data analysis and computer science technology, the design and implementation of image retrieval system has been a hot topic. The prior research focus more on image-size based approaches which are not intelligent or convenient. In this paper, we present a novel modified evolutionary algorithm based image retrieval framework theoretically with applications. To achieve more accuracy in less number of iteration, this paper, proposed a new approach to enhance the performance of content guided retrieval methodology by improving the performance of RF through Particle Swarm Optimization, Genetic Algorithm and Support Vector Machine. The objective of using Genetic Algorithm and Particle Swarm Optimization is to increase the number of images in relevant set where SVM is used to classify the relevant and irrelevant images. The experimental and numerical simulation indicate the efficiency of our method which means the presented technique is helpful in the fields where high accuracy rate of image retrieval is required. Further work of interest is also discussed in the final section.

According to the requirements of structure and communications of Body Area Network, a study is made on the node energy control strategy of Body Area Network. On the basis of dynamic routing protocol DSR, energy saving self-adaptive route E-DSR of Body Area Network has been designed, and the simulation analysis has also been made. The results show that effectively utilizing the node energy can improve the communication efficiency and lifecycle of Body Area Network by adopting E-DSR route.

This paper presents a literature survey on Digital Watermarking within an image. It describes the early work carried out on digital watermarks, including the brief analysis of various watermarking schemes and its applications. This paper also makes a comparison between various watermarking schemes .This paper also gives us a brief introduction about the procedure of digital watermarking.

This paper addresses the problem of independent component extraction of complex-valued signals in convolutive mixtures. Most previous research focused on real-valued convolutive ICA, and corresponding solution methods are generally computationally complex and inefficient for real application. In order to solve the problem, we propose a novel method based on first-order statistics, which includes several single-step and iterative separators to satisfy different demands of engineering applications. We also provided the theoretical performance analysis, which is validated by experimental simulations. It is observed from the simulations that various factors (especially the noncircularity) affect the extraction performance of separators; hence we offer some advice on how to choose separators properly. Besides, the proposed iterative separators generally perform better and converge faster compared to two complex FastICA algorithms.

The discrete curvature is sensitive to the noise and heavy computation of feature value. In order to extract the segmentation lines of 3D meshes, this paper presents a novel and efficient algorithm which is based on regional discrete curvature. Extract prominent feature points, pre-segmentation and then obtain the constraint region. Calculate the curvature degree extremal points within the constraint region, finally utilize the curvature degree extremal points to fit plane which guaid extracting the segmentation lines. This algorithm does not need to wipe off the noise at initial stage, the experiment results show that the proposed algorithm can accurately and frequently yield meaningful segmentation lines for models which has an evident branch structure.

A MANET Is Defined As A Collection of Wireless Mobile Nodes That Are Capable Of Communicating With Each Other Without The Use Of A Network Infrastructure Or Any Centralized Administration. Nodes Are Connected By A Wireless Channel. There Are Need Of Routing Protocols For Communication In Such Networks. The Work Of Routing Protocol Is Efficient And Timely Delivery of Message. MANET Offers Versatility for Certain Environments and Certain Applications. In This Paper The Comparison of AODV And DSR Has Analyzed At Different Transmission Power.

This paper focuses on the detection of the abnormal motion behaviour recognition of the crowd, and proposes an innovation method which is consist of three steps, i.e. SIFT flow + weighted orientation histogram + Hidden Markov Model(HMM). Analogous to optical flow, which is used to get the motion information of the pixels from two adjacent frames, SIFT flow is of higher precision. Next, we build up a a weighted orientation histogram as a statistical measurement for the SIFT flow features from the first step. Finally, the derived histogram is taken as the input for HMM in preparation for the detection of abnormal crowd motion. Experimental results show that compared to the existing method, our proposed one can detect the abnormal motion behaviour more effectively.

Optical code division multiple access system (OCDMA) has been important with increasing demands of high capacity and speed for communication in optical networks. Due to OCDMA technique high efficiency is achieved, hence fiber bandwidth is fully used. In this paper we will focus on different codes i.e MD (Multi Diagonal) FCC (Flexible cross correlation), DCS (Dynamic cyclic shift) code with BER parameter. Due to this codes we will eliminated MAI (multiple access interference) and improve BER (bit error rate), PIIN (Phase induced intensity noise) and make orthogonality between users in the system .We will use AND subtraction detection technique to implement these codes with technique of OCDMA using optiwave system design tool.

In order to improve the association matching of multiple pedestrians in occlusion scene, an improved algorithm is proposed in this paper that combines the similarity matching of pedestrian object’s major color spectrum histogram combination with joint probabilistic data association. The similarity to major color spectrum histogram of pedestrian’s object is calculated between the previous and the frame that current frames in this algorithm. And take the centroid location of pedestrian’s target which is with the most largest similarity to correct the state vector of the JPDA algorithm in the current frame. The experimental results show that the proposed algorithm could make the number of the targets’ label adhesion reduced to 40%, the number of the targets’ label confusion decreased about 33%, the recall rate of targets is increased by 6.8%, and the tracking accuracy is improved by 9.2% compared with the classical JPDA algorithm when the occlusion rate between pedestrians and intensity are not very high.