Accurate visual object tracking through long sequences is a challenging task since object's appearance changes and complex motion happens. We present mixture motion model and incorporate observation model within t...
详细信息
Accurate visual object tracking through long sequences is a challenging task since object's appearance changes and complex motion happens. We present mixture motion model and incorporate observation model within the Monte Carlo framework to achieve robust visual tracking. The mixture motion model which employs important history motion information of the target is built according to a motion measurement matrix to model the target's transition state. Meanwhile, the incorporate observation model is established by introducing SVM classification scores into normal tracking observation model. A particles filter's implementation with these mixture models is demonstrated, which leads to robust tracking results, especially in occlusion and complex scene.
According to the conventional hypothesis, the velocity of target in the coherent integration time (CIT) is invariable in the application of utilizing high frequency surface wave radar to detect target. First, this pap...
详细信息
ISBN:
(纸本)9788372077578
According to the conventional hypothesis, the velocity of target in the coherent integration time (CIT) is invariable in the application of utilizing high frequency surface wave radar to detect target. First, this paper proposes a more proper hypothesis in which the velocity and acceleration of target are treated as time-varying. However the acceleration of target can be regarded as invariable within the small fraction of coherent integration time. Then the model of echo signal in the hypothesis is analyzed. Considering the disadvangtages of some conventional methods of time-frequency analysis such as short-time Fourier transform (STFT) and Wigner-Ville distribution (WVD), the paper proposes the method of time-frequency analysis based on chirplets signal decomposition which can improve the time and frequency resolution simultaneously and solve the cross-term problem in WVD method. Firstly, we process the small fraction of coherent integration time with the chirplets signal decomposition. Then according to the differences between target signal and ocean clutter echo, the BP neural network classifier can be exploited to suppress ocean clutter. The different fractions of coherent integration time are composed together with the method of the nearest correlation. Lastly, the feasibility of the method for detecting targets of variable acceleration is proved by its processing the actual data.
In this paper, we present a pedestrian detection approach using spatial histograms of oriented gradients feature. As spatial histograms of oriented gradients consist of marginal distributions of an image over local an...
详细信息
In this paper, we present a pedestrian detection approach using spatial histograms of oriented gradients feature. As spatial histograms of oriented gradients consist of marginal distributions of an image over local and global patches, they can preserve shape and contour of a pedestrian simultaneously. There are two main contributions in this paper. First of all, we expand the histograms of oriented gradients features from single-size to variable-size which can capture local and global feature of pedestrian automatically. We call theses feature as the "spatial histograms of oriented gradients". Secondly, we employ histogram similarity and Fisher criterion to measure discriminability of features and select some discriminative features to identify the pedestrian. SVM classifier is constructed to train the selected features from target and surrounding background. The proposed algorithm is tested on some public database. Experimental results show that the proposed approach is efficient and rapid in pedestrian detection.
Short-term forecasting of travel time is essential for the success of intelligent transportation system. In this paper, we review the state-of-art of short-term traffic forecasting models and outline their basic ideas...
详细信息
Short-term forecasting of travel time is essential for the success of intelligent transportation system. In this paper, we review the state-of-art of short-term traffic forecasting models and outline their basic ideas, related works, advantages and disadvantages of each model. An improved adaptive exponential smoothing (IAES) model is also proposed to overcome the drawbacks of the previous adaptive exponential smoothing model. Then, comparing experiments are carried out under normal traffic condition and abnormal traffic condition to evaluate the performance of four main branches of forecasting models on direct travel time data obtained by license plate matching (LPM). The results of experiments show each model seems to have its own strength and weakness. The forecasting performance of IASE is superior to other models in shorter forecasting horizon (one and two step forecasting) and the IASE is capable of dealing with all kind of traffic conditions.
The development of VLSI technology results in the dramatically improvement of the performance of integrated circuits. However, it brings more challenges to the aspect of reliability. Integrated circuits become more su...
详细信息
The development of VLSI technology results in the dramatically improvement of the performance of integrated circuits. However, it brings more challenges to the aspect of reliability. Integrated circuits become more susceptible to soft errors. Therefore, it is imperative to study the reliability of circuits under the soft error. This paper implements three probabilistic methods (two pass, error propagation probability, and probabilistic transfer matrix) for estimating gate-level circuit reliability on PC. The functions and performance of these methods are compared by experiments using ISCAS85 and 74-series circuits.
Geographic routing has been introduced in mobile ad hoc networks and sensor networks. But its per-formance suffers greatly from mobility-induced location errors that can cause Lost Link (LLNK) and LOOP problems. Thu...
详细信息
Geographic routing has been introduced in mobile ad hoc networks and sensor networks. But its per-formance suffers greatly from mobility-induced location errors that can cause Lost Link (LLNK) and LOOP problems. Thus various mobility prediction algorithms have been proposed to mitigate the errors, but sometimes their prediction errors are substantial. A novel mobility prediction technique that incorpo-rates both mobile positioning information and road topology knowledge was presented. Furthermore, the performance of the scheme was evaluated via simulations, along with two other schemes, namely, Linear Velocity Prediction (LVP) and Weighted Velocity Prediction (WVP) for comparison purpose. The results of simulation under Manhattan mobility model show that the proposed scheme could track the movement of a node well and hence provide noticeable improvement over LVP and MVP.
Collaborative simulation technology is an important factor in improving the efficiency of complex product design. Although High Level Architecture (HLA)-based simulation technology can meet the needs for simulation in...
详细信息
Pair-wise testing is a testing criterion based on specification, which requires that for each pair of parameters, every combination of their valid value should be covered by at least one test case in the test set. Thi...
详细信息
This paper proposes an enhanced scheduling solution to support different quality of service (QoS) for IEEE 802.16e broadband wireless access network. Based on the existing scheduling algorithm M-LWDF, we do deeper res...
详细信息
This paper proposes an enhanced scheduling solution to support different quality of service (QoS) for IEEE 802.16e broadband wireless access network. Based on the existing scheduling algorithm M-LWDF, we do deeper research into how to integrate it into IEEE 802.16e. The proposed scheduling solution combines the keyservice flow parameters defined by IEEE 802.16e standard with M-LWDF scheme. Simulation results show that the delay character is improved for real-time services using the proposed method.
暂无评论