Aiming at the problems of blurred image, large noise, and poor visual perception in the traditional image super-resolution reconstruction methods, a method of image super-resolution reconstruction based on hybrid deep convolutional network was proposed. Firstly, the low-resolution image was scaled down to the specified size in the up-sampling phase. Secondly, the initial features of the low-resolution image were extracted in the feature extraction phase. Thirdly, the extracted initial features were sent to the convolutional coding and decoding structure for image feature denoising. Finally, high-dimensional feature extraction and computation were performed on the reconstruction layer using the dilated convolution in order to reconstruct the high-resolution image, and the residual learning was used to quickly optimize the network in order to reduce the noise and make the reconstructed image have better definition and visual effect. Based on the Set14 dataset and scale of 4x, the proposed method was compared with Bicubic interpolation (Bicubic), Anchored neighborhood regression (A+), Super-Resolution Convolutional Neural Network (SRCNN), Very Deep Super-Resolution network (VDSR), Restoration Encoder-Decoder Network (REDNet). In the super-resolution experiments, compared with the above methods, the proposed method has the Peak Signal-to-Noise Ratio (PSNR) increased by 2.73 dB,1.41 dB,1.24 dB,0.72 dB and 1.15 dB respectively, and the Structural SIMilarity (SSIM) improved by 0.067 3,0.020 9,0.019 7,0.002 6 and 0.004 6 respectively. The experimental results show that the hybrid deep convolutional network can effectively perform super-resolution reconstruction of the image.

In order to realize the robustness of three-Dimensional (3D) face recognition algorithm to expression variations, a multi-region template fusion 3D face recognition algorithm based on semantic alignment was proposed. Firstly, in order to guarantee the semantic alignment of 3D faces, all the 3D face models were densely aligned with a pre-defined standard reference 3D face model. Then, considering the expressions were regional, to be robust to region division, a multi-region template based similarity prediction method was proposed. Finally, all the prediction results of multiple classifiers were fused by majority voting method. The experimental results show that, the proposed algorithm can achieve the rank-1 face recognition rate of 98.69% on FRGC (the Face Recognition Grand Challenge) v2.0 expression 3D face database and rank-1 face recognition rate of 84.36% on Bosphorus database with occlusion change.

The current link prediction algorithms based on network representation learning mainly construct feature vectors by capturing the neighborhood topology information of network nodes for link prediction. However, those algorithms usually only focus on learning information from the single neighborhood topology of network nodes, while ignore the researches on similarity between multiple nodes in link structure. Aiming at these problems, a new Link Prediction model based on Densely connected convolutional Network (DenseNet-LP) was proposed. Firstly, the node representation vectors were generated by the network representation learning algorithm called node2vec, and the structure information of the network nodes was mapped into three dimensional feature information by these vectors. Then, DenseNet was used to to capture the features of link structure and establish a two-category classification model to realize link prediction. The experimental results on four public datasets show that, the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) value of the prediction result of the proposed model is increased by up to 18 percentage points compared to the result of network representation learning algorithm.

Aiming at the poor positioning accuracy of traditional wireless indoor positioning technology, an indoor positioning system based on Ultra Wide Band (UWB) technology was designed and implemented. Firstly, to solve the problem of autonomous localization and navigation, the system architecture of real-time interaction between the location server and the mobile terminal APP was proposed. Secondly, a radio message was added to the Two-Way Ranging (TWR) algorithm to reduce the ranging error caused by clock drift, so as to improve the performance of the algorithm. Finally, the hyperboloid equation set achieved by Time Difference Of Arrival (TDOA) positioning algorithm was linearized and then solved by Jacobi iteration method, which avoids the cases that standard TDOA localization algorithm is difficult to directly solve. The test results show that the system based on this method can work stably and control the range of error within 30 cm in the corridor room scene. Compared with the positioning systems based on WiFi and Bluetooth, the positioning accuracy of this system is improved by about 10 times, which can meet the requirement of precise mobile positioning in complex indoor environment.

Concerning the problem that existing Intra Bock Copy (IBC) algorithm is not well suitable to the screen content with a variety of different sizes and shapes of patterns, an Intra Mini-Block Copy (IMBC) algorithm was proposed to further improve coding efficiency of the screen content. Firstly, the Coding Unit (CU) was divided into a set of L mini-blocks. Secondly, each mini-block was taken as the smallest matching and replication unit, the reference mini-block which matched the mini-block best was found in the reference set R by a mini-block matching optimal selection strategy. And the location of the reference mini-block and its location in the current CU were specified by L Displacement Vectors (DVs). Finally, a prediction algorithm was firstly applied to the L DVs for eliminating the correlation between DVs before entropy encoding. Compared with the IBC algorithm, for the High Efficiency Video Coding (HEVC), Screen Content Coding (SCC) test sequences, IMBC achieved the BD-rate reduction up to 3.4%, 2.9%, 2.6% for All Intra (AI), Random Access (RA) and Low-delay B (LB) configurations in lossy coding respectively, and the Bit-rate saving up to 9.5%, 5.2%, 5.1% for AI, RA, LB configurations in lossless coding respectively. The experimental results show that IMBC algorithm can effectively improve the coding efficiency of screen image at very low additional encoding and decoding complexity.