Earticle

One of most important issue in research for unmanned ground vehicle is detecting signal lights at crossroads. This paper presents new algorithm for signal light detection. It has high detection rate with real time and fast processing at low price. Experimental environment is built in real vehicle and real urban road. , and we shall show that the proposed algorithm realizes driving with reliability in unmanned ground vehicle.

In the paper, we propose method to obtain the range and velocity with improved error depending on each distance (long, middle, and short) of the target for the automotive Frequency Modulation Continuous Wave (FMCW) radars. While target is in the long distance, the range and velocity are roughly extracted, for near-range target with the high collision probability, the de-interleaved method in the time domain and frequency interpolation in the frequency domain are applied to obtain more accurate range and velocity.

In this paper, we proposed a progressive time varying source channel coding system for transmitting image over wireless channels. Transmission of compressed image data over noisy channel is an important problem and has been investigated in a variety of scenarios. the core results obtained by a systematic method of instantaneous rate allocation between the progressive source coder and progressive channel coder .It is developed by closed form of expression for end-to-end distortion , rate allocation respectively in static channels. It is extended the static result to an algorithm for fading channels. It is introduced set DCT (blocks) approach is adapted to perform sub band decomposition followed by SPIHT (Set partitioning in Hierarchical tree)

Visual inspection and classification of cigarettes packaged in a tin container is very important in manufacturing cigarette products that require high quality package presentation. For accurate automated inspection and classification, computer vision has been deployed widely in manufacturing. We present the detection of the defective packaging of tins of cigarettes by identifying individual objects in the cigarette tins. Object identification information is used for the classification of the acceptable cases (correctly packaged tins) or defective cases (incorrectly packaged tins). This paper investigates the problem of identifying the individual cigarettes and a paper spoon in the packaged tin using image processing and morphology operations. The segmentation performance was evaluated on 500 images including examples of both good cases and defective cases.

This paper analyzes the detection performance of new Transmitted-Reference (TR) automotive UWB radar using unequaled amplitude for vehicles. To improve the detection performance of a traditional TR-UWB system, the amplitude of a reference pulse can be changed to increase the energy-to-noise ratio. Finally, the characteristics of the proposed TR-UWB radar are evaluated by simulation. And the performances of the proposed radar are compared with a coherent matched filter and a traditional TR-UWB system. For special case when SNR=3dB and  =6, we can assert that the detection probability of the proposed TR receiver is approximately a 19% increase compared with that of the conventional TR receiver when the probability of false alarm is 0.5.

Feature selection (FS) is a global optimization problem in machine learning, which reduces the number of features, removes irrelevant, noisy and redundant data, and results in acceptable recognition accuracy. It is the most important step that affects the performance of a pattern recognition system. This paper presents a novel feature selection algorithm based on particle swarm optimization (PSO). PSO is a computational paradigm based on the idea of collaborative behavior inspired by the social behavior of bird flocking or fish schooling. The algorithm is applied to coefficients extracted by two feature extraction techniques: the discrete cosine transforms (DCT) and the discrete wavelet transform (DWT). The proposed PSO-based feature selection algorithm is utilized to search the feature space for the optimal feature subset where features are carefully selected according to a well defined discrimination criterion. Evolution is driven by a fitness function defined in terms of maximizing the class separation (scatter index). The classifier performance and the length of selected feature vector are considered for performance evaluation using the ORL face database. Experimental results show that the PSO-based feature selection algorithm was found to generate excellent recognition results with the minimal set of selected features.

Environmental robustness is an important area of research in speech recognition. Mismatch between trained speech models and actual speech to be recognized is due to factors like background noise. It can cause severe degradation in the accuracy of recognizers which are based on commonly used features like mel-frequency cepstral co-efficient (MFCC) and linear predictive coding (LPC). It is well understood that all previous auditory based feature extraction methods perform extremely well in terms of robustness due to the dominantfrequency information present in them. But these methods suffer from high computational cost. Another method called sub-band spectral centroid histograms (SSCH) integrates dominant-frequency information with sub-band power information. This method is based on sub-band spectral centroids (SSC) which are closely related to spectral peaks for both clean and noisy speech. Since SSC can be computed efficiently from short-term speech power spectrum estimate, SSCH method is quite robust to background additive noise at a lower computational cost. It has been noted that MFCC method outperforms SSCH method in the case of clean speech. However in the case of speech with additive noise, MFCC method degrades substantially. In this paper, both MFCC and SSCH feature extraction have been implemented in Carnegie Melon University (CMU) Sphinx 4.0 and trained and tested on AN4 database for clean and noisy speech. Finally, a robust speech recognizer which automatically employs either MFCC or SSCH feature extraction methods based on the variance of shortterm power of the input utterance is suggested.

image sequences. Our proposed algorithm uses adaptive weights based on a triangular membership function: Symmetrical, Continuous Function. In this algorithm median filter is used to suppress noise. Experimental results show when the images are corrupted by highdensity Salt and Pepper noise, our fuzzy based algorithm for noise filtering of image sequences, is much more effective in suppressing noise and preserving edges than the previously reported algorithms such as [1-13]. Indeed, assigned weights to noisy pixels are very adaptive so that it well makes use of correlation of pixels. On the other hand, the motion estimation methods are erroneous and in high-density noise they may degrade the filter performance. Therefore, our proposed fuzzy algorithm doesn’t need any estimation of motion trajectory. The proposed algorithm admissibly removes noise without having any knowledge of Salt and Pepper noise density.

Directly embedding the secret data into the VQ-compressed domain is practical for reducing storage and transmittal bandwidth. Many steganography techniques are currently exploited for the VQ index table. However, embedding strategies extend the amount of compression needed for embedding secret data and distort the original quality of the VQ decompressed image. To satisfy the essentials of increasing the secret payload, preserve the VQ index table without loss, and reduce the compression rate, the proposed scheme utilizes search order coding to find the correlation between the VQ indices and neighboring indices. Due to the similarity of adjacent indices, the new scheme can effectively embed the secret stream into the index table and encode the embedded index table with fewer bits. The experimental results indicate that the new scheme can achieve superior outcomes of the compression rate and embedding efficiency than related steganography techniques.