The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper proposes a hand detection methodbased on statistical learning training way. Using Microsoft's Kinect sensor, to get the depth information. Through the analysis of the characetristics of hands, put out a kind of new features for statistical learning which approximate with Harr-like feature. The new feature is good at describing complex hand shape degeneration. With the help of Adaboost statistical...
This paper presents a novel object detection and segmentation method utilizing an inpainting algorithm. Inpainting is a concept of recovering missing image regions based on their surroundings, which were originally used for restoration of damaged paintings. In this paper, we newly utilize inpainting to judge whether an object candidate region includes the foreground object or not. The key idea is...
We present a new pedestrian detection algorithm that considers multiple information sources. Appearance-based detection methods face difficulties such as appearance variations and occlusions. Shape-based methods can have false positives on shadows since they usually have similar shapes with foreground objects. To deal with these problems, we use appearance, motion, and shadow information simultaneously...
One popular approach for multi-camera detection of pedestrians or other objects of interest in surveillance scenes is to perform background subtraction and project the resulting foreground mask images to a common scene plane using homographies. As the complexity of the scene increases, it is unavoidable that so called "ghost" detections should occur. These are false positives, indicating...
This paper presents a method of learning global and reconfigurable part-based models (RPM) for object detection. Recently, deformable part-based model (DPM) is widely used. A DPM consists of a root node and a collection of part nodes, which is learned under the latent SVM formulation by treating part nodes as hidden variables. Although the configuration of parts (i.e., the shapes, sizes and locations...
This study proposes a method to detect and mark the target object removed from the monitoring scene and the unknown object left in the monitoring scene. The present method uses the timeliness background to extract the foreground object and to mask the part that was unwanted. The foreground object was compared with the current frame, thus, the unreliable pixels were filtered out. By the identification...
The performance of part-based object detectors generally degrades for highly flexible objects. The limited topological structure of models and pre-specified part shapes are two main factors preventing these detectors from fully capturing large deformations. To better capture the deformations, we propose a novel approach to integrate the detections from a family of part-based detectors with patches...
In this paper we propose an approach to holistic scene understanding that reasons jointly about regions, location, class and spatial extent of objects, presence of a class in the image, as well as the scene type. Learning and inference in our model are efficient as we reason at the segment level, and introduce auxiliary variables that allow us to decompose the inherent high-order potentials into pairwise...
We propose a novel shape model for object detection called Fan Shape Model (FSM). We model contour sample points as rays of final length emanating for a reference point. As in folding fan, its slats, which we call rays, are very flexible. This flexibility allows FSM to tolerate large shape variance. However, the order and the adjacency relation of the slats stay invariant during fan deformation, since...
State-of-the-art object detectors typically use shape information as a low level feature representation to capture the local structure of an object. This paper shows that early fusion of shape and color, as is popular in image classification, leads to a significant drop in performance for object detection. Moreover, such approaches also yields suboptimal results for object categories with varying...
We propose a view-based approach for labeling objects in 3D scenes reconstructed from RGB-D (color+depth) videos. We utilize sliding window detectors trained from object views to assign class probabilities to pixels in every RGB-D frame. These probabilities are projected into the reconstructed 3D scene and integrated using a voxel representation. We perform efficient inference on a Markov Random Field...
Traditional bag-of-features approaches often vector-quantise the features into a visual codebook. This process inevitably causes loss of information. Recently codebook-free methods that avoid the vector-quantisation step have become more popular. Used in conjunction with nearest-neighbour approaches these methods have shown remarkable classification performance. In this paper we show how to exploit...
This paper tackles the problem of segmenting things that could move from 3D laser scans of urban scenes. In particular, we wish to detect instances of classes of interest in autonomous driving applications - cars, pedestrians and bicyclists - amongst significant background clutter. Our aim is to provide the layout of an end-to-end pipeline which, when fed by a raw stream of 3D data, produces distinct...
In this paper we present a new system for generic rotation invariant 2D object detection based on circular Fourier HOG features. Our system combines the advantages of a dense voting scheme as it is used in the Holomorphic Filter framework with features based on local orientation statistics. Experiments on two different biological datasets show superior detection performance over four state-of-the-art...
Gathering statistical and geometrical information by processing the shape contours is the common way of feature extraction on object detection and recognition studies. Compactness is an important shape descriptor which specifies the similarity between a shape and a circle. In this study, we propose a new compactness measure based on examining the distribution of the contour moments with respect to...
We propose a novel flexible and hierarchical object representation using heterogeneous feature descriptors for detection of visual objects in real-world scenarios. Our representation is built on a Conditional Random Field (CRF) model that is able to aggregate local, semi-local and global features in one consistent framework. To improve the discriminative power of our model, we incorporate SVM classifiers...
In this paper, we propose a novel approach for object detection via foreground feature selection and part-based shape model. It automatically learns a shape model from cluttered training images without need to explicitly given bounding box on objects. Our approach commences by extracting a set of feature descriptors, and iteratively selects the foreground features using Earth Movers Distances based...
Over the recent years, low-level visual descriptors, among which the most popular is the histogram of oriented gradients (HOG), have shown excellent performance in object detection and categorization. We form a hypothesis that the low-level image descriptors can be improved by learning the statistically relevant edge structures from natural images. We validate this hypothesis by introducing a new...
We propose a novel 3D depth cue-based generic categorical object detection model, which extends our previous 2D feature-based object detection method for object detection with severe occlusions. Since the novel model integrates complementary 3D depth cue with 2D appearance and shape features, it significantly improves the detection performance and robustness of the current 2D-based object detection...
Connected operators are filtering tools that act by merging elementary regions of an image. A popular strategy is based on tree-based image representations: for example, one can compute an attribute on each node of the tree and keep only the nodes for which the attribute is sufficiently strong. This operation can be seen as a thresholding of the tree, seen as a graph whose nodes are weighted by the...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.