Focusing on the issue of target motion feature extraction of video sequences in complex scene, and referring to the motion perception of biological vision system to the moving video targets, the traditional primary Visual cortex (V1) cell model of visual cortex was improved and a novel method of random-dot motion feature extraction based on the mechanism of biological visual cortex was proposed. Firstly, the spatial-temporal filter and half-squaring operation combined with normalization were adopted to simulate the linearity and nonlinearity of neuron's receptive field. Then, a universal V1 cell model was obtained by adding a directional selectivity adjustable parameter to the output weight, which solved the problem of the single direction selectivity and the disability to respond correctly to multi-direction motion in the traditional model. The simulation results show that the analog outputs of proposed model are almost consistent with the experimental data of biology, which indicates that the proposed model can simulate the V1 neurons of different direction selectivity and extract motion features well from random-dot video sequences with complex motion morphs. The proposed method can provide new idea for processing feature information of optical flow, extract motion feature of video sequence and track its object effectively.

The deformation such as translation, rotation and random scaling of local images in image recognition tasks is a complicated problem. An algorithm based on pre-training convolutional filters and Multi-Scale block Convolutional Neural Network (MS-CNN) was proposed to solve these problems. Firstly, the training dataset without labels was used to train a sparse autoencoder and get a collection of convolutional filters with characteristics in accord with the dataset and good initial values. To enhance the robustness and reduce the impact of the pooling layer for the feature extraction, a new Convolutional Neural Network (CNN) structure with multiple channels was proposed. The multi-scale block operation was applied to input image to form several channels, and each channel was convolved with corresponding size of filter. Then the convolutional layer, a local contrast normalization layer and a pooling layer were set to obtain invariability. The feature maps were put in the full connected layer and final features were exported for target recognition. The recognition rates of STL-10 database and remote sensing airplane images were both improved compared to traditional CNN. The experimental results show that the proposed method has robust performance when dealing with deformations such as translation, rotation and scaling.

Aiming at improving the robustness in pre-processing and extracting features sufficiently for Synthetic Aperture Radar (SAR) images, an automatic target recognition algorithm for SAR images based on Deep Belief Network (DBN) was proposed. Firstly, a non-local means image despeckling algorithm was proposed based on Dual-Tree Complex Wavelet Transformation (DT-CWT); then combined with the estimation of the object azimuth, a robust process on original data was achieved; finally a multi-layer DBN was applied to extract the deeply abstract visual information as features to complete target recognition. The experiments were conducted on three Moving and Stationary Target Acquisition and Recognition (MSTAR) databases. The results show that the algorithm performs efficiently with high accuracy and robustness.

Traditional image object detection algorithm based on local feature is sensitive to rotation and occlusion; meanwhile, it also obtains low detection precision and speed in many cases. In order to improve the performance of this algorithm, a new image objects detection method applying objects’ local feature to sparse representation theory was introduced. Employing supervised random tree method to learn local features of sample images, a dictionary could be formed. The combination of sub-image blocks of test image and well trained dictionary in first stage could predict the location of the object in the test image, in this way it could obtain a sparse representation of the test image as well as the object detection goal. The experimental results demonstrate that the proposed method achieves robust detection results in rotation, occlusion condition and intricate background. What’s more, the method obtains higher detection precision and speed.

In this paper, an adaptive color image enhancement method was proposed: Firstly, color image was transformed from RGB to HSV color space and the H component was kept invariable, while the illumination component of brightness image could be estimated through Adaptive Bidimensional Empirical Mode Decomposition (ABEMD); Secondly, reflection component was figured out by the method of center/surround Retinex algorithm, and the illumination and reflection components were controlled through Gamma emendation and Weber's law and processed with weighted average method; Thirdly, the S component was adjusted adaptively based on characteristics of the whole image, and then image was transformed back to RGB color space. The method could be evaluated by subjective effects and objective image quality assessment, and the experiment results show that the proposed algorithm is better in mean value, square variation, entropy and resolution than MSR algorithm and Meylan's algorithm.