Advanced Materials Research Vols. 317-319

Abstract: This paper proposed a simple and robust lane markers detection method for intelligent vehicle navigation. It needs not calculate inverse perspective map. The method uses multiple threshold segmentation instead of single threshold segmentation. And straight and curve lane markers are directly extracted in Run-Length accumulation (RLA) images. It performs well in various complex conditions and costs less than 50 ms for a 352 by 288 image. Experiments on many kinds of real complex image sequences demonstrate the effectiveness and efficiency of the proposed method.

Abstract: In his article, we explore a method for measuring position and attitude parameters of protable three-coordinate equipment based on monocular vision. The T-Probe of Laica is used as the experiment equipment and its four coplanar LEDs are chosen as feature points. While measuring, the probe contacts the measured point, the CCD camera takes the image of four coplanar feature points, the image coordinate of the feature points are accurately obtained by image processing programs. Using the linear idea for solving the P4P question, the coordinate of these feature points and attitude of object are gotten. Eventually, the measured points' coordinates are derived.

Abstract: The traditional centroid tracking method over-relies on the accuracy of segment, which easily lead to loss of underwater moving target. This paper presents an object tracking method based on circular contour extraction, combining region feature and contour feature. Through the correction to circle features, the problem of multiple solutions causing by Hough transform circle detection is avoided. A new motion prediction model is constructed to make up the deficiency that three-order motion prediction model has disadvantage of high dimension and large calculation. The predicted position of object centroid is updated and corrected by circle contour, forming prediction-measurement-updating closed-loop target tracking system. To reduce system processing time, on the premise of the tracking accuracy, a dynamic detection method based on target state prediction model is proposed. The results of contour extraction and underwater moving target experiments demonstrate the effectiveness of the proposed method.

Abstract: A novel illumination compensate method is proposed in this paper to improve recognition performance. A modified lighting model called Lambertin which includes additive noise and multiplicative noise are presented firstly. Then, additive noise is removed by using wavelet packet transformation. Next, the processed image is transformed into logarithm domain and the multiplicative noise, which has been named additive noise, is removed by means of the same above algorithm. Finally, a compensated face image is obtained. We examine the proposed method on Yale extended B database compared with other methods. Experimental results show that our algorithm improves by 3%~12% recognition rate. It can effectively adjust the facial images for varying illumination conditions and also improve the recognition performance and robustness.

Abstract: A method based on Bernoulli mixtures is presented in this paper for the purpose of describing the pattern of probability distribution for each of the data sets of handwritten numerals (0-9), and then classifiers are formed from these. The test samples are recognized by their posterior probabilities conditioned on every classifier. Experimental results show that our method is superior to conventional methods on robustness and accuracy.

Abstract: Liquid column manometers are widely used in fluid mechanics experiments, so the design and implementation of a remote experimental setup for performing experiments on fluid mechanics, the on-line reading of liquid column manometer is necessary. Firstly, through comparing computer vision reading with manual reading, the former accuracy is much higher in the ideal case. Secondly, computer vision based reading scheme is confirmed according to the experimental progress. Then, the imaging geometric model of manometer is approximated by pin-hole imaging model. While the vertical relationship between camera viewpoint and liquid level is changed, for reducing the imaging error, view fixed reading with software algorithm is discussed to correct the identified water head. Lastly, according to the proportional relations between invariable inside diameter of manometer and water head image, the upper boundary line coordinate value is determined. The experimental results show that the method is effective and feasible.

Abstract: Agricultural products quality which included intrinsic attribute and extrinsic characteristic, closely related to the health of consumer and the exported cost. Now, imaging (machine vision) and spectrum are two main nondestructive inspection technologies to be applied. Hyperspectral imaging, a new emerging technology developed for detecting quality of the food and agricultural products in recent years, combined techniques of conventional imaging and spectroscopy to obtain both spatial and spectral information from an objective simultaneously. This paper compared the advantage and disadvantage of imaging, spectrum and hyperspectral imaging technique, and provided a description to basic principle, feature of hyperspectral imaging system and calibration of hyperspectral reflectance images. In addition, the recent advances for the application of hyperspectral imaging to agricultural products quality inspection were reviewed in other countries and China.

Abstract: A defeat detection method for quill using the finite ridgelet transform is mentioned. This method reduce the average gray values of quill and analytic statistics methods are used in ridgelet transform according to points of quill. After ridgelet transform the linear singularity is further highlighted and the quantization errors caused by cutting image of quill is overcomed. With this method the differences between background and quill are eliminated too and automaticly adjusting the sub-image size for transformation according to the width of quill is realized. The experiment results show that this method can effectively detect smaller linear defects and hence satisfy the industrial production needs.

Abstract: Several moving objects detection methods were compared and an improved method on the basis of consecutive frames difference was proposed. Color images captured with camera were transformed into gray ones and the gray ones were processed with median filter. The adjacent frames of any three consecutive ones were handled with differential operation to obtain two difference images and threshold value was set to transform difference images into binary ones. The binary images were dealt with by using opening operation. The location of moving aircraft was determined by performing two difference images with AND operation. The simulation results show that the improved method can effectively detect and locate the moving aircraft in intelligent surveillance system.

Abstract: A noncontact inspection system for gear based on machine vision is developed in this work, according to the mathematical model of lens distortion; the calibration of the camera was realized by the MATLAB calibration toolbox, obtained the distortion coefficients, by which the pixel is proofread. After then the key parameters of gear could be automatically acquired with proposed algorithm. In this work, the algorithm is applied to a practical case of a standard spur gear; the experimental results reported here confirm the effectiveness of the approach.