On-line boosting is one of the most successful on-line algorithms and thus applied in many computervision applications. However, even though boosting, in general, is well known to be susceptible to class-label noise,...
详细信息
Maximally Stable Extremal Regions (MSERs) are one of the most prominent interest region detectors in computervision due to their powerful properties and low computational demands. In general MSERs are detected in sin...
详细信息
Very recently tracking was approached using classification techniques such as support vector machines. The object to be tracked is discriminated by a classifier from the background. In a similar spirit we propose a no...
详细信息
ISBN:
(纸本)1904410146
Very recently tracking was approached using classification techniques such as support vector machines. The object to be tracked is discriminated by a classifier from the background. In a similar spirit we propose a novel on-line AdaBoost feature selection algorithm for tracking. The distinct advantage of our method is its capability of on-line training. This allows to adapt the classifier while tracking the object. Therefore appearance changes of the object (e.g. out of plane rotations, illumination changes) are handled quite naturally. Moreover, depending on the background the algorithm selects the most discriminating features for tracking resulting in stable tracking results. By using fast computable features (e.g. Haar-like wavelets, orientation histograms, local binary patterns) the algorithm runs in real-time. We demonstrate the performance of the algorithm on several (publically available) video sequences.
This paper introduces a method which provides robust tracking results and accurately segmented object boundaries in short computation time. The first step of the algorithm is to apply a novel edge detector on efficien...
详细信息
ISBN:
(纸本)9781901725360
This paper introduces a method which provides robust tracking results and accurately segmented object boundaries in short computation time. The first step of the algorithm is to apply a novel edge detector on efficiently calculated color probability maps in an object-specific Fisher color space. The proposed edge detector exploits context information by finding the maximally stable boundaries of connected regions in threshold results outperforming purely local edge detectors. Finally, based on the estimated edge maps a probabilistic particle filtering framework hypothesizes rigid transformations for initializing an active contour model to provide accurate object segmentations in each frame. Experimental evaluations show that robust tracking results with accurate segmentations are obtained on challenging data sets.
In this paper we address the problem that most face recognition approaches neglect that faces share strong visual similarities, which can be exploited when learning discriminative models. Hence, we propose to model fa...
详细信息
Random Forests (RFs) are frequently used in many computervision and machine learning applications. Their popularity is mainly driven by their high computational efficiency during both training and evaluation while ac...
详细信息
Traditional Structure-from-Motion (SfM) approaches work well for richly textured scenes with a high number of distinctive feature points. Since man-made environments often contain textureless objects, the resulting po...
详细信息
The tasks carried out by modern information workers become increasingly complex and time-consuming. They often require to evaluate, interpret, and compare information from different sources presented in multiple appli...
详细信息
ISBN:
(纸本)9781568817125
The tasks carried out by modern information workers become increasingly complex and time-consuming. They often require to evaluate, interpret, and compare information from different sources presented in multiple application windows. With large, high resolution displays, multiple application windows can be arranged in a way so that a large amount of information is visible simultaneously. However, individual application windows' contents and visual representations are isolated and relations between information items contained in these windows are not explicit. Thus, relating and comparing information across applications has to be executed manually by the user, which is a tedious and error-prone task. In this paper we present visual links connecting related pieces of information across application windows and thereby guiding the user's attention to relevant information. Applications are coordinated by a management application accessible via a light-weight interface. User selections are synchronized across registered applications and visual links are rendered on top of the desktop content by a window manager. Initial user feedback was very positive and indicates that visual links improve task efficiency when analyzing information from multiple sources.
We present a human action recognition system suitable for very short sequences. In particular, we estimate Histograms of Oriented Gradients (HOGs) for the current frame as well as the corresponding dense flow field es...
详细信息
Recently, combining information from multiple cameras has shown to be very beneficial for object detection and tracking. In contrast, the goal of this work is to train detectors exploiting the vast amount of unlabeled...
详细信息
暂无评论