No abstract

Abstract-A video-based traffic monitoring system must be capable of working in various weather and illumination conditions. In this paper, we will propose an example-based algorithm for moving vehicle detection. Different from previous works, this algorithm learns from examples and does not rely on any a priori model for vehicles. First, a novel scheme for adaptive background estimation is introduced. Then, the image is divided into many small nonoverlapped blocks. The candidates of the vehicle part can be found from the blocks if there is some change in gray level between the current image and the background. A lowdimensional feature is produced by applying principal component analysis to two histograms of each candidate, and a classifier based on a support vector machine is designed to classify it as a part of a real vehicle or not. Finally, all classified results are combined, and a parallelogram is built to represent the shape of each vehicle. Experimental results show that our algorithm has a satisfying performance under varied conditions, which can robustly and effectively eliminate the influence of casting shadows, headlights, or bad illumination.Index Terms-Principal component analysis (PCA), statistical learning, support vector machine (SVM), video-based traffic monitoring.

This paper proposes a new distributed Kalman filtering fusion with random state transition and measurement matrices, i.e., random parameter matrices Kalman filtering. It is proved that under a mild condition the fused state estimate is equivalent to the centralized Kalman filtering using all sensor measurements; therefore, it achieves the best performance. More importantly, this result can be applied to Kalman filtering with uncertain observations including the measurement with a false alarm probability as a special case, as well as, randomly variant dynamic systems with multiple models. Numerical examples are given which support our analysis and show significant performance loss of ignoring the randomness of the parameter matrices.

No abstract

Abstract