One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose. Most of the work in object detection has been based on single image processing and it...
详细信息
ISBN:
(纸本)9781467356404
One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose. Most of the work in object detection has been based on single image processing and its performance is limited by occlusions and ambiguity in appearance and geometry. This paper proposes an active approach to object detection by controlling the point of view of a mobile depth camera. When an initial static detection phase identifies an object of interest, several hypotheses are made about its class and orientation. The sensor then plans a sequence of viewpoints, which balances the amount of energy used to move with the chance of identifying the correct hypothesis. We formulate an active M-ary hypothesis testing problem, which includes sensor mobility, and solve it using a point-based approximate POMDP algorithm. The validity of our approach is verified through simulation and experiments with real scenes captured by a kinect sensor. The results suggest a significant improvement over static object detection.
This paper presents a hybrid optimization algorithm referred to as Hybrid spiral dynamics bacterial foraging (HSDBF). The algorithm synergizes spiral adaptive simplified bacterial foraging algorithm (BFA) and spiral d...
详细信息
A novel type of discrete-time fractional-power nonlinear autoregressive with exogenous input (FPNARX) model is introduced for system identification, modeling and prediction. Parameter estimation of such a model is a n...
详细信息
This paper presents a hybrid optimization algorithm, referred to as hybrid spiral dynamics bacterial chemotaxis (HSDBC) algorithm. HSDBC synergizes bacterial foraging algorithm (BFA) chemotaxis strategy and spiral dyn...
详细信息
In this paper, in order to address the well-known 'sensitivity' problems associated with K-means clustering, a real-coded Genetic Algorithms (GA) is incorporated into K-means clustering. The result of the hybr...
详细信息
This paper proposes a singular perturbation approximation for semistable linear systems. In particular, we derive a novel expression of error systems in the Laplace domain. As a result, we obtain an ℋ 2 -error bound i...
详细信息
ISBN:
(纸本)9781479901890
This paper proposes a singular perturbation approximation for semistable linear systems. In particular, we derive a novel expression of error systems in the Laplace domain. As a result, we obtain an ℋ 2 -error bound in terms of the sum of eigenvalues of an index matrix, which coincides with a controllability gramian of the state-derivative. Furthermore, we show that the singular perturbation model appropriately preserves the semistability of the original system and also guarantees the stability of the error system. The efficiency of the proposed method is shown through a numerical example of a Markov chain model approximation.
A novel design of two-wheeled double inverted pendulum-like vehicle with a movable payload is presented in this paper. The developed design extends the abilities of the vehicle with five degrees of freedom. The increa...
详细信息
作者：
Bogdan D. CiubotaruMarcel StaroswieckiNicolai D. ChristovAPCC
Automatic Process Control and Computers Laboratory Department of Automatic Control and Systems Engineering University Politehnica of Bucharest 060042 Bucharest Romania SATIE
Systemes et Applications des Technologies de l'Information et de l'Energie Laboratory Ecole Normale Superieure de Cachan 94235 Cachan Cedex France LAGIS
Laboratoire d'Automatique Genie Informatique et Signal Universite des Sciences et Technologies de Lille 59655 Villeneuve d'Ascq Cedex France
The Exact Model Matching (EMM) problem knows an Approximate Model Matching (AMM) solution in the Fault Tolerant control (FTC) context, solution obtained using either the Modified Pseudo-Inverse Method (MPIM) or the Cl...
详细信息
ISBN:
(纸本)9781479901777
The Exact Model Matching (EMM) problem knows an Approximate Model Matching (AMM) solution in the Fault Tolerant control (FTC) context, solution obtained using either the Modified Pseudo-Inverse Method (MPIM) or the Classical Robust Optimal Model Matching (CROMM) technique. In this paper, the authors reiterate the AMM solution with MPIM-CROMM and propose another hybrid technique of MPIM with Generalized Linear Quadratic Regulator (GLQR) stabilization and control correction using one of the ROMM variants, called the Extended approach (EROMM). The specificity of the MPIM-GLQR-EROMM as an AMM solution for FTC is also shown in its application on the B747 short-period model impaired with two structural and actuator faults.
Object tracking algorithm based on Meanshift algorithm with fixed kernel bandwidth does not realize object tracking correctly with the scale of object changed. According to this, a scheme of kernel bandwidth adaptive ...
详细信息
Object tracking algorithm based on Meanshift algorithm with fixed kernel bandwidth does not realize object tracking correctly with the scale of object changed. According to this, a scheme of kernel bandwidth adaptive adjustment and predictions of object cancroids based on Kalman filter is proposed in this paper. In this algorithm, Object location predicted based on Kalman filter is used to initialize the Meanshift algorithm. The variation tendency of the kernel bandwidth is also determined based on Kalman filter. Experiment results demonstrate that this algorithm can realize the kernel bandwidth adaptive adjustment and object location prediction. The robustness of the tracking algorithm is also enhanced.
暂无评论