Guoyun Zhang

Sub-Pixel Level Defect Detection Based on Notch Filter and Image Registration

General machine vision algorithms are difficult to detect LCD sub-pixel level defects. By studying the LCD screen images, we found that the pixels in the LCD screen are regularly arranged. The spectrum distribution of LCD images, which is obtained by the Fourier transform, is relatively consistent. According to this feature, a method of sub-pixel defect detection based on notch filter and image registration is proposed. First, we take a defect-free template image to establish registration template and notch-filtering template; then we take the defect images for image registration with registration template, and solve the offset problem. After the notch-filter template filtering the background texture, the defect is more obvious; Finally the defects are obtained by the threshold segmentation method. The experiment results show that the proposed method can detect sub-pixel defects accurately and quickly.

Temporal–Spatial Symmetric Distributed Multi-View Video Coding Scheme

To improve the rate stability and make a balance for different viewpoints in distributed multi-view video coding (DMVC) system, a novel symmetric DMVC (SDMVC) scheme is proposed in this paper. In the proposed scheme, every frame from all views adopts the same encoding mode and stable output rates are achieved, which are significant to improve the transmission efficiency in the channel. Both temporal and spatial correlations are exploited, in addition, a novel side information (SI) generation algorithm aiming at better exploring the correlations of proposed scheme has been proposed to obtain better performance. The simulation results show that the proposed SDMVC scheme gets a much more stable rate than the asymmetric scheme, only with neglectable bit-rate increasing. Meanwhile, the proposed SI generation algorithm significantly improves the coding performance.

Spectral-Spatial Hyperspectral Image Classification via Adaptive Total Variation Filtering

It is unavoidable that existing noise interference in hyperspectral image (HSI). In order to reduce the noise in HSI and obtain a higher classification result, a spectral-spatial HSI classification via adaptive total variation filtering (ATVF) is proposed in this paper, which consists of the following steps: first, the principal component analysis (PCA) method is used for dimension reduction of HSI. Then, the adaptive total variation filtering is performed on the principal components so as to reduce the sensitiveness of noise and obtain a coarse contour feature. Next, the ensemble empirical mode decomposition is used to decompose each spectrum band into serial components, the characteristics of HSI can be further integrated in a transform domain. Finally, a pixel-level classifier (such as SVM) is used for classification of the processed image. The paper analyzes the effect of different parameters of ATVF method on the classification performance in detail, tests the proposed algorithm on the real hyperspectral data sets, and finally verifies the superiority of the proposed algorithm based on a contrastive analysis of different algorithms.

Study of multiple moving targets’ detection in fisheye video based on the moving blob model

This paper discussed some improved algorithms for multiple moving targets detection and tracking in fisheye video sequences which based on the moving blob model. The view field of fisheye lens achieved 183 degree which used in our system, so it has more effective in the no blind surveillance system. However, the fisheye image has a big distortion that makes it difficult to achieve an intelligent function. In this paper we try to establish a moving blob model to detect and track multiple moving targets in the fisheye video sequences, in order to achieve the automation and intelligent ability for no blind surveillance system. It is divided into three steps. Firstly, the distortion model of fisheye lens was established, we are discussing the character of the imaging principle of fisheye lens, and calculate the distortion coefficient which can be used in the moving blob model. Secondly, the principle of the moving blob model was analyzed in detail which based on the fisheye distortion model. It was included four main algorithms, which the first is the traditional algorithm of background extraction; and the background updating algorithm; the algorithm of the fisheye video sequence with the background subtracted in order to get the moving blobs; the algorithm of removing the shadow of blobs in RGB space. Thirdly, we determined that every extracted blob is a real moving target by calculating the pixels with a threshold, which can discard the faulty moving targets. Lastly, we designed the algorithm for tracking the moving targets based on the moving blobs selected through calculating the geometry center. The experiment indicated that every algorithm has a better processing efficiency of multiple moving targets in fisheye video sequences. Compared the traditional algorithm, the improved algorithm can be detected the moving target in a circular fisheye image effectively and stably.

Adaptive total variation-based spectral-spatial feature extraction of hyperspectral image

Abstract In this paper, a simple yet quite useful hyperspectral images (HSI) classification method based on adaptive total variation filtering (ATVF) is proposed. The proposed method consists of the following steps: First, the spectral dimension of the HSI is reduced with principal component analysis (PCA). Then, ATVF is employed to extract image features which not only reduces the noise in the image, but also effectively exploits spatial–spectral information. Therefore, it can provide an improved representation. Finally, the efficient extreme learning machine (ELM) with a very simple structure is used for classification. This paper analyzes the influence of different parameters of the ATVF and ELM algorithm on the classification performance in detail. Experiments are performed on three hyperspectral urban data sets. By comparing with other HSI classification methods and other different feature extraction methods, the proposed method based on the ATVF algorithm shows outstanding performance in terms of classification accuracy and computational efficiency when compared with other hyperspectral classification methods.

Study of Motion Detection Technology Based on DaVinci Platform

A motion detection method is presented based on Davinci platform. This paper adopts color histogram algorithm to detect moving target, which is operated on TMS320DM6446. The results indicate that the method presented has good accuracy and quick speed for real time application.

Research of Face Detection Based on Davinci Platform

A face detection method is presented based on Davinci platform. This paper adopts Adaboost algorithm to identify face, which is operated on TI TMS320DM6467. The results indicate that the method has good accuracy and quick speed for real time application.

Study of face detection technology based on Davinci platform

A face detection method is presented based on Davinci platform. This paper adopts Adaboost algorithm to locate face, which is operated on TI TMS320DM6446. The results indicate that the method presented has good accuracy and quick speed for realtime application.

Study of FPGA technology applied for stepping motor subdivision drive

Limited by the manufacture technics, the stepping motor has big step angles and low frequency vibration, and can only be applied to those situations with low demand. This paper designs a method to realize subdivision drive for the stepping motor based on FPGA chip. Firstly, PWM control waveform data table are stored in embedded memory module of FPGA. Secondly, multiple PWM control signals are produced by the digital comparator synchronously. Finally, we realize subdivision control for the step angles of stepping motor. Test result shows that the stepping motor subdivision drive technology can decrease the stepping angle of stepping motor, improve the stabilization and flexibility and has preferable practical value.

Study of measurement technology for abrasion of the coupler based on digital image processing

An automatically inspecting method is presented to check the abrasion of the coupler with non-contact measurement technology. This paper adopts the method of digital image processing to analyze the coupler illustration. The results indicate that the method presented has good accuracy for engineering measurement.