Motivated by the converse Lyapunov technique for investigating converse results of semistable switched systems in control theory,this paper utilizes a constructive induction method to identify a cost function for perf...Motivated by the converse Lyapunov technique for investigating converse results of semistable switched systems in control theory,this paper utilizes a constructive induction method to identify a cost function for performance gauge of an average,multi-cue multi-choice(MCMC),cognitive decision making model over a switching time interval.It shows that such a constructive cost function can be evaluated through an abstract energy called Lyapunov function at initial conditions.Hence,the performance gauge problem for the average MCMC model becomes the issue of finding such a Lyapunov function,leading to a possible way for designing corresponding computational algorithms via iterative methods such as adaptive dynamic programming.In order to reach this goal,a series of technical results are presented for the construction of such a Lyapunov function and its mathematical properties are discussed in details.Finally,a major result of guaranteeing the existence of such a Lyapunov function is rigorously proved.展开更多
In visual tracking,integrating multiple cues will increase the reliability and robustness of the tracking system in situations where no single cue is reliable.In this paper,a novel multi-cue based tracking method is p...In visual tracking,integrating multiple cues will increase the reliability and robustness of the tracking system in situations where no single cue is reliable.In this paper,a novel multi-cue based tracking method is presented under the particle filter framework.Considering both practical distance and Bhattacharyya distance between particles and the target,a parameter called relative discriminant coefficient(RDC)is designed to measure the tracking ability for different features.Multi-cue fusion is carried out in a reweighing manner based on this parameter.Experimental results demonstrate the high robustness and effectiveness of our method in handling appearance changes,cluttered background,illumination changes and occlusions.展开更多
在多目标跟踪任务中,外界噪声的干扰会导致传统方法的系统建模不可靠,从而降低目标位置预测的准确性;而密集人群引起的拥挤和遮挡问题则会严重影响目标外观的可靠性,导致错误的身份关联.为了解决这些问题,本文提出一种多目标跟踪算法Ecs...在多目标跟踪任务中,外界噪声的干扰会导致传统方法的系统建模不可靠,从而降低目标位置预测的准确性;而密集人群引起的拥挤和遮挡问题则会严重影响目标外观的可靠性,导致错误的身份关联.为了解决这些问题,本文提出一种多目标跟踪算法Ecsort.该算法在传统运动预测的基础上,引入噪声补偿模块,降低噪声干扰引起的误差,提高位置预测的准确性.其次,引入特征相似度匹配模块,通过学习目标的判别性外观特征,并结合运动线索和判别性外观特征的优势,从而实现精确的身份关联.通过在多目标跟踪基准数据集上进行的大量实验结果表明,与基线模型相比,该方法在MOT17测试集上的IDF1 (ID F1 score)、HOTA (higher order tracking accuracy)、AssA(association accuracy)、DetA (detection accuracy)分别提高了1.1%、0.5%、0.6%、0.3%,在MOT20测试集上的IDF1、HOTA、AssA、DetA分别提高了2.3%、1.9%、3.4%、0.2%.展开更多
分割运动手部时,为了不依赖不合理的假设和解决手脸遮挡问题,该文提出一种基于肤色、灰度、深度和运动线索的分割方法。首先,利用灰度与深度光流的方差信息来自适应提取运动感兴趣区域(Motion Region of Interest,MRoI),以定位人体运动...分割运动手部时,为了不依赖不合理的假设和解决手脸遮挡问题,该文提出一种基于肤色、灰度、深度和运动线索的分割方法。首先,利用灰度与深度光流的方差信息来自适应提取运动感兴趣区域(Motion Region of Interest,MRoI),以定位人体运动部位。然后,在MRoI中检测满足肤色与自适应运动约束的角点作为皮肤种子点。接着,根据肤色、深度与运动准则将皮肤种子点生长为候选手部区域。最后,通过边缘深度梯度、骨架提取和最优路径搜索从候选手部区域中分割出运动手部区域。实验结果表明,在不同情形下,特别是手脸遮挡时,该方法可以有效和准确地分割出运动手部区域。展开更多
文摘Motivated by the converse Lyapunov technique for investigating converse results of semistable switched systems in control theory,this paper utilizes a constructive induction method to identify a cost function for performance gauge of an average,multi-cue multi-choice(MCMC),cognitive decision making model over a switching time interval.It shows that such a constructive cost function can be evaluated through an abstract energy called Lyapunov function at initial conditions.Hence,the performance gauge problem for the average MCMC model becomes the issue of finding such a Lyapunov function,leading to a possible way for designing corresponding computational algorithms via iterative methods such as adaptive dynamic programming.In order to reach this goal,a series of technical results are presented for the construction of such a Lyapunov function and its mathematical properties are discussed in details.Finally,a major result of guaranteeing the existence of such a Lyapunov function is rigorously proved.
基金supported by the National Natural Science Foundation of China (Grant Nos.60472060 and 60632050).
文摘In visual tracking,integrating multiple cues will increase the reliability and robustness of the tracking system in situations where no single cue is reliable.In this paper,a novel multi-cue based tracking method is presented under the particle filter framework.Considering both practical distance and Bhattacharyya distance between particles and the target,a parameter called relative discriminant coefficient(RDC)is designed to measure the tracking ability for different features.Multi-cue fusion is carried out in a reweighing manner based on this parameter.Experimental results demonstrate the high robustness and effectiveness of our method in handling appearance changes,cluttered background,illumination changes and occlusions.
文摘在多目标跟踪任务中,外界噪声的干扰会导致传统方法的系统建模不可靠,从而降低目标位置预测的准确性;而密集人群引起的拥挤和遮挡问题则会严重影响目标外观的可靠性,导致错误的身份关联.为了解决这些问题,本文提出一种多目标跟踪算法Ecsort.该算法在传统运动预测的基础上,引入噪声补偿模块,降低噪声干扰引起的误差,提高位置预测的准确性.其次,引入特征相似度匹配模块,通过学习目标的判别性外观特征,并结合运动线索和判别性外观特征的优势,从而实现精确的身份关联.通过在多目标跟踪基准数据集上进行的大量实验结果表明,与基线模型相比,该方法在MOT17测试集上的IDF1 (ID F1 score)、HOTA (higher order tracking accuracy)、AssA(association accuracy)、DetA (detection accuracy)分别提高了1.1%、0.5%、0.6%、0.3%,在MOT20测试集上的IDF1、HOTA、AssA、DetA分别提高了2.3%、1.9%、3.4%、0.2%.
文摘分割运动手部时,为了不依赖不合理的假设和解决手脸遮挡问题,该文提出一种基于肤色、灰度、深度和运动线索的分割方法。首先,利用灰度与深度光流的方差信息来自适应提取运动感兴趣区域(Motion Region of Interest,MRoI),以定位人体运动部位。然后,在MRoI中检测满足肤色与自适应运动约束的角点作为皮肤种子点。接着,根据肤色、深度与运动准则将皮肤种子点生长为候选手部区域。最后,通过边缘深度梯度、骨架提取和最优路径搜索从候选手部区域中分割出运动手部区域。实验结果表明,在不同情形下,特别是手脸遮挡时,该方法可以有效和准确地分割出运动手部区域。
