[서평]「Digital Video Processing」

This paper deals with the problem of position-based visual servoing in a multiarm robotic cell equipped with a hybrid eye-in-hand/eye-to-hand multicamera system. The proposed approach is based on the real-time estimation of the pose of a target object by using the extended Kalman filter. The data provided by all the cameras are selected by a suitable algorithm on the basis of the prediction of the object self-occlusions, as well as of the mutual occlusions caused by the robot links and tools. Only an optimal subset of image features is considered for feature extraction, thus ensuring high estimation accuracy with a computational cost independent of the number of cameras. A salient feature of the paper is the implementation of the proposed approach to the case of a robotic cell composed of two industrial robot manipulators. Two different case studies are presented to test the effectiveness of the hybrid camera configuration and the robustness of the visual servoing algorithm with respect to the occurrence of occlusions

Position-Based Visual Servoing in Industrial Multirobot Cells Using a Hybrid Camera Configuration

A method and system is configured to characterize regions of an environment by the likelihoods of transition of a target from each region to another. The likelihoods of transition between regions is preferably used in combination with conventional object-tracking algorithms to determine the likelihood that a newly-appearing object in a scene corresponds to a recently-disappeared target. The likelihoods of transition may be predefined based on the particular environment, or may be determined based on prior appearances and disappearances in the environment, or a combination of both. The likelihoods of transition may also vary as a function of the time of day, day of the week, and other factors that may affect the likelihoods of transitions between regions in the particular surveillance environment.

Linking tracked objects that undergo temporary occlusion

Video analysis of animal behaviour is widely used in fields such as ecology, ecotoxicology, and evolutionary research. However, when tracking multiple animals, occlusion and crossing are problematic, especially when the identity of each individual needs to be preserved. We present a new algorithm, ToxId, which preserves the identity of multiple animals by linking trajectory segments using their intensity histogram and Hu-moments. We verify the performance and accuracy of our algorithm using video sequences with different animals and experimental conditions. The results show that our algorithm achieves state-of-the-art accuracy using an efficient approach without the need of learning processes, complex feature maps or knowledge of the animal shape. ToxId is also computationally efficient, has low memory requirements, and operates without accessing future or past frames.

/pdf/toxid-an-efficient-algorithm-to-solve-occlusions-when-p0ng4vlqio.pdf

ToxId: an efficient algorithm to solve occlusions when tracking multiple animals

We propose a method that rates the suitability of given templates for template-based tracking in real-time. This is important for applications with online template selection, such as SLAM, where it is essential to track a low number of preferably reliable templates. Our approach is based on simple image features specifically designed to identify texture properties which are problematic for tracking. During a training step, a support vector regresser is learned. It uses a tracking quality measure which considers both convergence rate and speed obtained by simulation of many tracking attempts. Finally, a minimum set of image features is identified to speedup the online selection process. In experiments on real-world video sequences our method improved the detection rate of an existing tracking-by-detection system by 8% on average.

http://far.in.tum.de/pub/hinterstoisser2010template/hinterstoisser2010template.pdf

Rapid selection of reliable templates for visual tracking

A joint probabilistic face detection and tracking algorithm, combining likelihood estimation and a prior probability, is proposed. The likelihood estimation scheme is based on the statistical training of sets of automatically generated feature points and a mutual information tracking cue, while the prior probability estimation is based on a Gaussian temporal model. The likelihood estimation process is the core of a multiple face detection scheme used to initialize the tracking process. The resulting system has been tested on real image sequences and is robust to significant partial occlusion and illumination changes.

/pdf/probabilistic-multiple-face-detection-and-tracking-using-350iltcsob.pdf

Probabilistic multiple face detection and tracking using entropy measures

Object tracking with occlusion prediction using multiple feature correspondences is proposed. The tracking region is defined by a set of point features, tracked using Kanade-Lucas-Tomasi (1991) algorithm. During total occlusion the region position is estimated using motion prediction based on a Kalman filtering scheme applied to the motion model prior to occlusion. During partial occlusion the displacements of the occluded features are predicted based on the motion of the bounding box of the moving object. Experimental results on real and artificial images have shown that the algorithm behaves well under total and partial occlusion.

Occlusion resistant object tracking

4.11 – 2D and 3D Motion Tracking in Digital Video

The efficiency of three tracking reliability metrics based on information theory and normalized correlation is examined in this paper. The two information theory tools used for the metrics construction are the mutual information and the Kullback-Leibler distance. The metrics are applicable to any feature-based tracking scheme. In the context of this work, they are applied for comparison purposes on an object tracking scheme using multiple feature point correspondences. Experimental results have shown that the information theory based metrics perform better than the normalized correlation one.

Evaluation of tracking reliability metrics based on information theory and normalized correlation

A mutual information based articulated object tracking scheme is proposed in this paper Articulation constraints are introduced using a kinematic model Further constraints are introduced based on the human joint anatomy and flexibility The tracking scheme is enhanced by using the tracked object texture map image The tracking history is incorporated in the tracking scheme by using a temporal model or a Kalman filtering scheme The Kalman filtering scheme greatly enhances the tracking scheme provided the suitable initial conditions are set The resulting system was tested on arm and finger tracking cases using real image sequences

/pdf/a-mutual-information-approach-to-articulated-object-tracking-1j4b36agdq.pdf

E. Loutas

Papers

Probabilistic multiple face detection and tracking using entropy measures

Occlusion resistant object tracking

4.11 – 2D and 3D Motion Tracking in Digital Video

Evaluation of tracking reliability metrics based on information theory and normalized correlation

A mutual information approach to articulated object tracking