To improve the reliability and accuracy of visual tracker,a robust visual tracking algorithm based on multi-cues fusion under Bayesian framework is proposed.The weighed color and texture cues of the object are applied...To improve the reliability and accuracy of visual tracker,a robust visual tracking algorithm based on multi-cues fusion under Bayesian framework is proposed.The weighed color and texture cues of the object are applied to describe the moving object.An adjustable observation model is incorporated into particle filtering,which utilizes the properties of particle filter for coping with non-linear,non-Gaussian assumption and the ability to predict the position of the moving object in a cluttered environment and two complementary attributes are employed to estimate the matching similarity dynamically in term of the likelihood ratio factors;furthermore tunes the weight values according to the confidence map of the color and texture feature on-line adaptively to reconfigure the optimal observation likelihood model,which ensured attaining the maximum likelihood ratio in the tracking scenario even if in the situations where the object is occluded or illumination,pose and scale are time-variant.The experimental result shows that the algorithm can track a moving object accurately while the reliability of tracking in a challenging case is validated in the experimentation.展开更多
The naive, Bayes （NB） model has been successfully used to tackle spare, and is very accurate. However, there is still room for improwment. We use a train on or near error （TONE） method in online NB to enhance the ...The naive, Bayes （NB） model has been successfully used to tackle spare, and is very accurate. However, there is still room for improwment. We use a train on or near error （TONE） method in online NB to enhance the perfornmnee of NB and reduce the number of training emails. We conducted an experiment to determine the performanee of the improved algorithm by plotting （I-ROCA）% curves. The resuhs show that the proposed method improves the performanee of original NB.展开更多
Context-aware is becoming standard on the most mobile navigation devices. The performance of MEMS IMU/GNSS gains significant benefits from context information in terms of improvement of filter＇ s adaptive capability....Context-aware is becoming standard on the most mobile navigation devices. The performance of MEMS IMU/GNSS gains significant benefits from context information in terms of improvement of filter＇ s adaptive capability. A context-aware algorithm using differential carrier phase was proposed to recognize a molile MEMS IMU/GNSS equipped vehicle＇ s stationary, slow moving or fast moving status. The corresponding context error in awarding was analyzed and consequently conducted two fading factors based on the analysis The factors were applied in the system＇ s adaptive filter with targeting applications in deep urban where severe multipath presents. The dense urban field test shows that the false alarm of proposed context-aware algorithm is less than 5% and the adaptive filtering can achieve around 15% improvement in terms of lo in two-dimension position accuracy.展开更多
文摘To improve the reliability and accuracy of visual tracker,a robust visual tracking algorithm based on multi-cues fusion under Bayesian framework is proposed.The weighed color and texture cues of the object are applied to describe the moving object.An adjustable observation model is incorporated into particle filtering,which utilizes the properties of particle filter for coping with non-linear,non-Gaussian assumption and the ability to predict the position of the moving object in a cluttered environment and two complementary attributes are employed to estimate the matching similarity dynamically in term of the likelihood ratio factors;furthermore tunes the weight values according to the confidence map of the color and texture feature on-line adaptively to reconfigure the optimal observation likelihood model,which ensured attaining the maximum likelihood ratio in the tracking scenario even if in the situations where the object is occluded or illumination,pose and scale are time-variant.The experimental result shows that the algorithm can track a moving object accurately while the reliability of tracking in a challenging case is validated in the experimentation.
基金supported by National Natural Science Foundation of China under Grant NO. 60903083Research fund for the doctoral program of higher education of China under Grant NO.20092303120005the Research Fund of ZTE Corporation
文摘The naive, Bayes （NB） model has been successfully used to tackle spare, and is very accurate. However, there is still room for improwment. We use a train on or near error （TONE） method in online NB to enhance the perfornmnee of NB and reduce the number of training emails. We conducted an experiment to determine the performanee of the improved algorithm by plotting （I-ROCA）% curves. The resuhs show that the proposed method improves the performanee of original NB.
基金Sponsored by the National Natural Science Foundation of China(Grant No.61173076)
文摘Context-aware is becoming standard on the most mobile navigation devices. The performance of MEMS IMU/GNSS gains significant benefits from context information in terms of improvement of filter＇ s adaptive capability. A context-aware algorithm using differential carrier phase was proposed to recognize a molile MEMS IMU/GNSS equipped vehicle＇ s stationary, slow moving or fast moving status. The corresponding context error in awarding was analyzed and consequently conducted two fading factors based on the analysis The factors were applied in the system＇ s adaptive filter with targeting applications in deep urban where severe multipath presents. The dense urban field test shows that the false alarm of proposed context-aware algorithm is less than 5% and the adaptive filtering can achieve around 15% improvement in terms of lo in two-dimension position accuracy.
