In complex environment, existing pedestrian detection methods can not be very good to achieve high recall rate and efficient detection. To solve this problem, a pedestrian detection method based on Convolutional Neural Network (CNN) was proposed. Firstly, pedestrian locations in input images were initially detected with single step detection upgrade network (YOLOv2) derived from CNN. Secondly, a network with target classification and bounding box regression was designed to cascade with YOLOv2 network, which made reclassification and regression of pedestrian location initially detected by YOLOv2, to reduce error detections and increase recall rate. Finally, a Non-Maximum Suppression (NMS) method was used to remove redundant bounding boxes. The experimental results show that, in INRIA and Caltech dataset, the proposed method increases recall rate by 3.3 percentage points, and the accuracy is increased by 5.1 percentage points compared with original YOLOv2. It also reached a speed of 11.6FPS (Frames Per Second) to realize real-time detection. Compared with the existing six popular pedestrian detection methods, the proposed method has better overall performance.

To eliminate the zigzagging and blocky effects in homogeneous areas in an interpolated image, a variable exponent variational method was proposed for image interpolation. An exponent function with diffusion characteristic of image interpolution was introduced by analyzing the diffusion characteristic of variable exponent variational model. Two parameters in the exponent function act on interpolation: the one controlled the intensity of diffusion which eliminated the width of image edges while the other controlled the intensity of smoothness which retained the fine textures in the image. The new variable exponent variatonal model made the Total Variation (TV) variational diffuse along image contours and the heat diffusion on smooth areas. The numerical experiment results on real images show that image interpolated by the proposed method has better interpolated edges, especially for fine textures. Compared to the method proposed by Chen et al. (CHEN Y M, LEVINE S, RAO M. Variable exponent, linear growth functionals in image restoration. SIAM Journal on Applied Mathematics, 2006, 66(4): 1383-1406) and robust soft-decision interpolation method, the visual improvement is prominent for retaining fine textures, and the Mean Structural SIMilarity (MSSIM) is increased by 0.03 in average. The proposed model is helpful to further study variable exponent variational model for specifical image processing and worthy to practical applications such as image network communication and print.

Concerning the problem that the efficiency of serial PageRank algorithm is low in dealing with mass Web data, a PageRank parallel algorithm based on Web link classification was proposed. Firstly, the Web was classified according to its Web link, and the weights of different Web which was from diverse websites were set variously. Secondly, with the Hadoop parallel computation platform and MapReduce which has the characteristics of dividing and conquering, the Webpage ranks were computed parallel. At last, a data compression method of three layers including data layer, pretreatment layer and computation layer was adopted to optimize the parallel algorithm. The experimental results show that, compared with the serial PageRank algorithm, the accuracy of the proposed algorithm is improved by 12% and the efficiency is improved by 33% in the best case.