In order to solve the measurement problem of vehicle driving wandering,an on-line au-tomatic vehicle driving wandering test system was developed.By setting up a binocular vision meas-urement model,the system realized automatic measurement of the vehicle driving wandering quanti-ty.The self-developed wide field of the laser light source solved ambient interference problems when measuring.Data processing algorithm which was optimized solved the problem of lower measurement accuracy.The wireless network test system realized on-line automatic measurement of the vehicle driving wandering.This system has high detection accuracy;it runs stably and reliably.It can be widely used in automatic on-line measurement of vehicle driving wandering quantity in automobile manufacturer and all kinds of vehicle inspection.

Asphalt pavement micro-texture 3D image reconstruction is one of the basic methods to study its microscopic property. Aiming at lack of research about it in China and aboard,by using focusing depth method,the sequential images along the direction perpendicular to the surface of the asphalt specimen are captured by monocular stereo microscope. The sequential images are fused and confirmed the height level of each point in the fused image using the improved Laplacian operator. Then,the exact height of each point is obtained using Gaussian interpolation algorithm,and 3D reconstruction of asphalt pavement micro-texture is achieved. By comparing with the sectional contour measured with laser profilometer,the accuracy and feasibility of the exact height is verified. The result shows that the method can accurately reconstruct the 3D micro-texture of asphalt pavement.

In order to overcome the disadvantages of mean texture depth(MTD)measurement methods,with section method and digital image technology method combined and with the help of laser vision advanced technology,a new MTD measurement method based on laser vision was proposed.Based on triangulation measurement principle,laser vision 3Dmathematical model was established.According to the measurement requirements,the general image processing method was put forward.By using the mean profile depth(MPD)estimation,MTD measurement was realized.Comparative experiments with sand patch method were conducted.The results show that the new method is of simple operation with moderate price equipment,its measuring results are of higher resolution and accuracy and its measuring data are 3Dvisual,which has high value of engineering practicability.

After analysis of the engine ECU commonly used fault detection method of characteristics and shortage,we make out dynamic detection mathod which basis on the signal simulation and the composition of the testing system.Also,we illustrates the key points of development of engine ECU fault detector,and we will focus on ECU detection system of the analog signal.

To realize the fast accurate forward obstacle detection of the intelligent cars,this paper introduces the raster to stereoscopic binocular vision system,establishing the obstacle detection system with merging of both raser and vision sensors,which bands the advantage of both sensors and fills up the shortage of the single sensor detection.Using the stereoscopic binocular vision system to capture the outline of obstacles information,and at the same time using grating projection technology to adjust the partial obstacle information,with the fixed phase image projected out by grating projection,it can quickly recognize the cognominal points in the matching of stereoscopic vision,which can perfectly solve the difficulty of image registration in the stereoscopic vision.

This work expounds the analytic hierarchy process(ahp),analyses and summarizes the shortcomings that the previous using MATLAB to realize analytic hierarchy process(ahp).Based on this,improve and develop this software,make it with interface and concise,operate more convenient,general greatly enhanced.successfully applied this software to the evaluation of university spirit scholarship.