Since the existing adaptive neighborhood based multi-view clustering algorithms do not consider the noise and the loss of consensus graph information, a Robust Multi-View Graph Clustering(RMVGC) algorithm based on adaptive neighborhood was proposed. Firstly, to avoid the influence of noise and outliers on the data, the Robust Principal Component Analysis(RPCA) model was used to learn multiple clean low-rank data from the original data. Secondly, the adaptive neighborhood learning was employed to directly fuse multiple clean low-rank data to obtain a clean consensus affinity graph, thus reducing the information loss in the process of graph fusion. Experimental results demonstrate that the Normalized Mutual Informations(NMI) of the proposed algorithm RMVGC is improved by 5.2, 1.36, 27.2, 4.66 and 5.85 percentage points, respectively, compared to the current popular multi-view clustering algorithms on MRSCV1, BBCSport, COIL20, ORL and UCI digits datasets. Meanwhile, in the proposed algorithm, the local structure of data is maintained, the robustness against the original data is enhanced, the quality of affinity graph is improved, and such that the proposed algorithm has great clustering performance on multi-view datasets.

Object tracking based on Siamese network has made some progresses, that is it overcomes the limitation of the spatial invariance of Siamese network in the deep network. However, there are still factors such as appearance changes, scale changes, and occlusions that affect tracking performance. Focusing on the problems of large changes in object scale, object motion blur and small scale of object in the specified object tracking of Unmanned Aerial Vehicles (UAV), a new tracking algorithm was proposed based on the Siamese region proposal attention mechanism network, namely Attention-SiamRPN+. Firstly, an improved deep residual network ResNet-50 was employed as a feature extractor to extract feature maps. Secondly, the channel attention mechanism module was used to filter the semantic information of different channel feature maps extracted by the residual network, and the corresponding weights to different channel features were reassigned. Thirdly, a hierarchical fusion of two Region Proposal Networks (RPN) was applied. The RPN module was consisted of channel-by-channel deep cross-correlation of feature maps, classification of positive and negative samples and bounding box regression. Finally, the box of the object position was selected. In the test on the VOT2018 platform, the proposed algorithm had the accuracy of 59.4% and the Expected Average Overlap (EAO) of 39.5%. In the experiment with one-pass evaluation mode on the OTB2015 platform, the algorithm had the success rate and precision of 68.7% and 89.4% respectively. Experimental results show that the evaluation results of the proposed algorithm are better than the results of three excellent correlation filtering tracking and Siamese network tracking algorithms in recent years, and the proposed algorithm has good robustness and real-time processing speed when applying to the tracking of specified objects of UAV.

Due to the instability of network training, the image super-resolution reconstruction based on Generative Adversarial Network (GAN) has a mode collapse phenomenon. To solve this problem, a Spherical double Discriminator Super-Resolution Generative Adversarial Network (SDSRGAN) based on spherical geometric moment matching and feature discrimination was proposed, and the stability of network training was improved by adopting geometric moment matching and discrimination of high-frequency features. First of all, the generator was used to produce a reconstructed image through feature extraction and upsampling. Second, the spherical discriminator was used to map image features to high-dimensional spherical space, so as to make full use of higher-order statistics of feature data. Third, a feature discriminator was added to the traditional discriminator to extract high-frequency features of the image, so as to reconstruct both the characteristic high-frequency component and the structural component. Finally, game training between the generator and double discriminator was carried out to improve the quality of the image reconstructed by the generator. Experimental results show that the proposed algorithm can effectively converge, its network can be stably trained, and has Peak Signal-to-Noise Ratio (PSNR) of 31.28 dB, Structural SIMilarity (SSIM) of 0.872. Compared with Bicubic, Super-Resolution Residual Network (SRResNet), Fast Super-Resolution Convolutional Neural Network (FSRCNN), Super-Resolution using a Generative Adversarial Network (SRGAN), and Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) algorithms, the reconstructed image of the proposed algorithm has more precise structural texture characteristics. The proposed algorithm provides a double discriminant method for spherical moment matching and feature discrimination for the research of image super-resolution based on GAN, which is feasible and effective in practical applications.

Since the methods of multiple kernel subspace spectral clustering do not consider the problem of noise and relation graph structure, a novel Joint Low-rank and Sparse Multiple Kernel Subspace Clustering algorithm (JLSMKC) was proposed. Firstly, with combination of low-rank and sparse representation for subspace learning, the relation graph obtained the attribute of low-rank and sparse structure. Secondly, a robust multiple kernel low-rank and sparsity constraint model was constructed to reduce the influence of noise on the relation graph and handle the nonlinear structure of data. Finally, the quality of relation graph was enhanced by making full use of the consensus kernel matrix by multiple kernel approach. The experimental results on seven datasets show that the proposed JLSMKC is better than five popular multiple kernel clustering algorithms in ACCuracy (ACC), Normalized Mutual Information (NMI) and Purity. Meanwhile, the clustering time is reduced and the block diagonal quality of relation graph is improved. JLSMKC has great advantages in clustering performance.

In order to solve the problem of fixed target size in Kernel Correlation Filtering (KCF) tracker, a scale adaptive tracking method was proposed. Firstly, the Lucas-Kanade optical flow method was used to track the movement of keypoints in the neighbor frames, and the reliable points were obtained by introducing the forward-backward method. Secondly, the reliable points were used to estimate the target changing in scale. Thirdly, the scale estimation was applied to the adjustable Gaussian window. Finally, the forward-backward tracking method was used to determine whether the target was occluded or not, the template updating strategy was revised. The fixed target size limitation in the KCF was solved, the tracker was more accurate and robust. The object tracking datasets were used to test the algorithm. The experimental results show that the proposed method ranks over the original KCF, Tracking-Learning-Detection (TLD), Structured output tracking with kernel (Struck) algorithms both in success plot and precision plot. Compared with the original method, the proposed tracker can be better applied in target tracking with scale variation and occlusion.

The scene of unstructured road is complex and easy to be influenced by many factors. In order to solve the detection difficulty, a road detection algorithm based on contour features and two-dimensional maximum entropy was proposed. Quadratic two-dimensional maximum entropy segmentation method combined with invariant color feature was used for road image segmentation. Afterwards, contour features were extracted from segmentation result by boundary tracking algorithm, and then the maximum contour was chosen. Finally, the improved mid-to-side algorithm was used to search road edge points, then road boundary was reconstructed through road model and road direction was judged. The experimental results show that the detection accuracy rate is improved about 25% in three kinds of unstructured scene compared with traditional algorithm. In addition, this method is robust against shadows and can recognize road direction efficiently.