Image matching has been a central research topic in computervision over the last decades. Typical approaches to correspondence involve matching features between images. In this paper, we present a novel problem for e...
详细信息
Image matching has been a central research topic in computervision over the last decades. Typical approaches to correspondence involve matching features between images. In this paper, we present a novel problem for establishing correspondences between a sparse set of image features and a previously learned subspace model. We formulate the matching task as an energy minimization, and jointly optimize over all possible feature assignments and parameters of the subspace model. This problem is in general NP-hard. We propose a convex relaxation approximation, and develop two optimization strategies: naive gradient-descent and quadratic programming. Alternatively, we reformulate the optimization criterion as a sparse eigenvalue problem, and solve it using a recently proposed backward greedy algorithm. Experimental results on facial feature detection show that the quadratic programming solution provides better selection mechanism for relevant features.
This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential Structure from Motion, where a 3D model of ...
Detecting changes between images of the same scene taken at different times is of great interest for monitoring and understanding the environment. It is widely used for on-land application but suffers from different c...
详细信息
We present an algorithm that allows swarms of robots to navigate in environments containing unknown obstacles, moving towards and spreading along 2D shapes given by implicit functions. Basically, a gradient descent ap...
详细信息
Finding correspondences of two images taken from largely different camera configuration is a challenging problem because appearance information such as color, intensity and edge orientation histogram cannot be used. A...
详细信息
We propose the use of imaging polarimetry for general photography, which is a relatively young technique allowing the determination of polarized components of the light coming from extended objects or scenes. In this ...
详细信息
Background modeling is an essential and important part of many high-level video processing applications. Recently, the Support Vector Data Description (SVDD) has been introduced for novelty detection when only one cla...
详细信息
This paper presents an adaptive framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature...
详细信息
This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature o...
详细信息
This paper proposes a field application of a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot in a cable tracking task. The learning system is chara...
详细信息
This paper proposes a field application of a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot in a cable tracking task. The learning system is characterized by using a Direct Policy Search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV .
暂无评论