A novel reconstruction method to improve the recognition of license plate texts of moving vehicles in real traffic videos is proposed, which fuses complimentary information among low resolution （LR） images to yield a high resolution （HR） image. Based on the regularization super-resolution （SR） reconstruction schemes, this paper first introduces a residual gradient （RG） term as a new regularization term to improve the quality of the reconstructed image. Moreover, L1 norm is used to measure the residual data （RD） term and the RG term in order to improve the robustness of the proposed method. Finally, the steepest descent method is exploited to solve the energy functional. Simulated and real acquired video sequence experiments show the effectiveness and practicability of the proposed method and demonstrate its superiority over the bi-cubic interpolation and discontinuity adaptive Markov random field （DAMRF） SR method in both signal to noise ratios （SNR） and visual effects.
To track the vehicles under occlusion, a vehicle tracking algorithm based on blocks is proposed. The target vehicle is divided into several blocks of uniform size, in which the edge block can overlap its neighboring blocks. All the blocks＇ motion vectors are estimated, and the noise motion vectors are detected and adjusted to decrease the error of motion vector estimation. Then, by moving the blocks based on the adjusted motion vectors, the vehicle is tracked. Aiming at the occlusion between vehicles, a Markov random field is established to describe the relationship between the blocks in the blocked regions. The neighborhood of blocks is defined using the Euclidean distance. An energy function is defined based on the blocks＇ histograms and optimized by the simulated annealing algorithm to segment the occlusion region. Experimental results demonstrate that the proposed algorithm can track vehicles under occlusion accurately.
In order to optimize the signal control system, this paper proposes a method to design an optimized fuzzy logic controller （FLC） with the DNA evolutionary algorithm. Inspired by the DNA molecular operation characteristics, the DNA evolutionary algorithm modifies the corresponding genetic operators. Compared with the traditional genetic algorithm （GA）, the DNA evolutionary algorithm can overcome weak local search capability and premature convergence. The parameters of membership functions are optimized by adopting the quaternary encoding method and performing corresponding DNA genetic operators. The relevant optimized parameters are combined with the FLC for single intersection traffic signal control. Simulation experiments shows the better performance of the FLC with the DNA evolutionary algorithm optimization. The experimental results demonstrate the efficiency of the nrotmsed method.
The integration of the Lab model with the extended histogram of oriented gradients （EHOG） is proposed to improve the accuracy of human appearance matching across disjoint camera views under perturbations such as illumination changes and different viewing angles. For the Lab model that describes the global information of observations, a sorted nearest neighbor clustering method is proposed for color clustering and then a partitioned color matching method is used to calculate the color similarity between observations. The Bhattacharya distance is employed for the textural similarity calculation of the EHOG which describes the local information. The global information, which is robust to different viewing angles and scale changes, describes the observations well. Meanwhile, the use of local information, which is robust to illumination changes, can strengthen the discriminative ability of the method. The integration of global and local information improves the accuracy and robustness of the proposed matching approach. Experiments are carried out indoors, and the results show a high matching accuracy of the proposed method.
An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is judged by their cross-correlation function, which is also used to calculate their transition time distribution. The mutual information of the connected node pair is employed for transition probability calculation. A false link eliminating approach is proposed, along with a topology updating strategy to improve the learned topology. A real monitoring system with five disjoint cameras is built for experiments. Comparative results with traditional methods show that the proposed method is more accurate in topology learning and is more robust to environmental changes.
Due to the fact that the fourth-order partial differential equation （PDE） for noise removal can provide a good trade-off between noise removal and edge preservation and avoid blocky effects often caused by the second-order PDE, a domain-based fourth-order PDE method for noise removal is proposed. First, the proposed method segments the image domain into two domains, a speckle domain and a non-speckle domain, based on the statistical properties of isolated speckles in the Laplacian domain. Then, depending on the domain type, different conductance coefficients in the proposed fourth-order PDE are adopted. Moreover, the frequency approach is used to determine the optimum iteration stopping time. Compared with the existing fourth-order PDEs, the proposed fourth-order PDE can remove isolated speckles and keeps the edges from being blurred. Experimental results show the effectiveness of the proposed method.
Aiming at removing fog from traffic images, a distance field is built according to the characteristics of traffic images, and a novel parameter estimation method based on the traffic image sequence is proposed. The fog model is derived from atmospheric scattering models. The direction of the distance field is parallel to the center line of the road, which increases along a line from the observer to the horizon, and the normalization is carried out to improve the distribution of the distance field model. After parameter initialization, the variations of the average gray values of reference regions are taken as the determining conditions to adjust the parameters. Finally, restorations are made by the fog model. Experimental results show that the proposed method can effectively remove fog from traffic images.
An adaptive human tracking method across spatially separated surveillance cameras with non-overlapping fields of views （FOVs） is proposed. The method relies on the two cues of the human appearance model and spatio-temporal information between cameras. For the human appearance model, an HSV color histogram is extracted from different human body parts （head, torso, and legs）, then a weighted algorithm is used to compute the similarity distance of two people. Finally, a similarity sorting algorithm with two thresholds is exploited to find the correspondence. The spatio- temporal information is established in the learning phase and is updated incrementally according to the latest correspondence. The experimental results prove that the proposed human tracking method is effective without requiring camera calibration and it becomes more accurate over time as new observations are accumulated.
