Songhao Zhu

Statistical background model-based target detection

This paper proposes a statistical background modeling framework to deal with the issue of target detection, where the global and local information is utilized to achieve more accurate detection of moving objects. Specifically, for the target detection problem under illumination change conditions, a novel self-adaptive Gaussian mixture model mixed with the global information is utilized to construct a statistical background model to detect moving objects; for the target detection problem under dynamic background conditions, the self-tuning spectral clustering method is first utilized to cluster background images, and then the kernel density estimation method mixed with the local information is utilized to construct a statistical background model to detect moving objects. Experimental results demonstrate that the proposed framework can improve the detection performance under illumination change conditions or dynamic background conditions.

Optical flow and spatio-temporal gradient based abnormal behavior detection

To improve the accuracy of the detection of local abnormal behavior, a novel method is here proposed. The main idea of the proposed method is described as follows: firstly, a video sequence is divided into spatio-temporal blobs; then, a statistical method based on the semi-parametric model is adopted to detect these blobs where abnormal behaviors most likely to appear; finally, maximum optical flow energy and local nearest descriptor are utilized to determinate whether these suspicious blobs really contain abnormal behaviors. The experimental results conducted on UCSD dataset demonstrate the effectiveness of the proposed method.

Target tracking via improved TLD algorithm

As one of the core content of intelligent monitoring, target detection and tracking is the basis for video content analysis and understanding. Tracking-Learning-Detection is considered as a highly efficient algorithm for tracking a single target. Although this algorithm can re-track a target when the target is occluded by other targets, there still exists many shortcomings. This paper deals with the issue of target tracking by fusing kalman filter with tracking-learning-detection algorithm. Specifically, an improved Kalman filter is first utilized to enhance the reliability of tracking-learning-detection algorithm; then, the area of the target is estimated to reduce the detection region and to increase the processing speed. Experimental results conducted on PETS2009/2010 benchmark video library demonstrate that the proposed method can detect properly and track accurately an target in complex scenes.

Image classification via multi-view model

With the massive growth of digital image data uploaded to the Internet, classifying each image into appropriate semantic category based on the image content for image index and image retrieval has become an increasingly difficult and laborious task. To deal with this issue, we propose a novel multi-view semi-supervised learning framework which leverages the information contained in pseudo-labeled images to improve the prediction performance of image classification using multiple views of an image. In the training process, labeled images are first adopted to train view-specific classifiers independently using uncorrelated and sufficient views, and each view-specific classifier is then interactively re-trained using initial labeled samples and additional pseudo-labeled samples based on a measure of confidence. In the classification process, the maximum entropy principle is utilized to assign appropriate category label to each unlabeled image using optimally trained view-specific classifiers. Experimental results on a general-purpose image database demonstrate the effectiveness and efficiency of the proposed multi-view semi-supervised scheme.

Improved balanced binary tree based action recognition

Action recognition is one of the core content of intelligent monitoring, and also the basis of video content analysis and understanding. A novel method is here proposed to enhance the accuracy of human behavior recognition. First, each video image is divided into five sub-regions based on the motion mechanism; then, the frequency information of optical flow within each sub-region is extracted to describe the motion characteristics of each sub-region; finally, an improved balanced binary decision tree-support vector machine is utilized to complete the task of behavior recognition. Experimental results conducted on KTH database demonstrate the proposed algorithm can improve the accuracy of behavior recognition.

Improved hierarchical association model based mult-target tracking

To deal with the issue of multi-target tracking, this paper proposes a hierarchical correlation multi-target tracking trajectory generation method. On the basis of target detection and initial trajectory, the AdBoost algorithm combined with online discriminant analysis apparent model is first utilized to achieve initial tracking trajectories; then, the Hungarian algorithm is here utilized to optimize fragmented and discontinuous tracking trajectories to achieve stable and accurate trajectories fragments; finally, the intelligent extrapolation based on energy minimization here utilized to achieve the final smoother and longer tracking trajectories. Experimental results on PETS 2009/2010 benchmark and TUD-Stadtmitte video database demonstrate the effectiveness and efficiency of the proposed scheme.

Target detection via improved ViBe algorithm

Due to the complexity of human motion, the target detection results by using traditional ViBe algorithm are not so satisfactory. Therefore, this paper proposes a method to deal with the target detection issue by fusing an improved Canny operator with Vibe algorithm. Specifically, the ViBe algorithm is utilized to achieve the initial foreground region of a moving object; then, the improved Canny operator is applied to extract the edge information of a moving object; finally, the extracted foreground region and edge information are fused to obtain more accurate foreground region. The experimental results performed on KTH human behavior database demonstrate the effectiveness of the proposed scheme.

BP neural network control for a class of nonlinear systems

A method based on BP neural network is proposed for a class of nonlinear SISO systems. It fits the nonlinear part of the system by learning the weight coefficients of the network on-line, designs the control rules to linearize the system, and assure the global stability. In this paper, the method is popularized in the MIMO systems. Experimental Results of two examples demonstrate the performance of our approach .