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.
In most convolutional neural networks (CNNs), the output is a single classification result by combining all the neuron activations in the last layer. As we know, local connectivity is an important characteristic of CNNs. Each neuron in the network corresponds to a local region in the original image. Hence, it is possible to simultaneously obtain local visibility of a target object by analyzing neuron...
In our previous work, we have proposed a new approach to detect rotated object at distinct angles using the ViolaJones detector. This approach consists in feeding the groups of Haar features presented by Viola & Jones, Lienhart and others by other features which are rotated by any angle. In this paper we have extended this set of features by others called normal and rotated asymmetric Haar features...
Convolutional neural networks are a popular choice for current object detection and classification systems. Their performance improves constantly but for effective training, large, hand-labeled datasets are required. We address the problem of obtaining customized, yet large enough datasets for CNN training by synthesizing them in a virtual world, thus eliminating the need for tedious human interaction...
This paper presents the detection and localization methods of entrance and staircase markers for the team E-Mobile in TechX Challenge 2013. Autonomous vehicles are required to detect and locate traffic cones beside the indoor entrance and staircase. One big challenge is from the unpredictable lighting conditions and environment. Different practical techniques such as color space selection, segmentation,...
We propose a novel object detection approach that combines the discriminative power of object category classifiers with a simple pixel level focus of attention mechanism. The pixel-level foreground/background detectors evolve to classify each pixel as either being part of an object of interest or noise. Unlike background subtraction algorithms, the decision of what is foreground is influenced by object...
Landmark detection has proven to be a very challenging task in biometrics. In this paper, we address the task of facial component-landmark detection. By “component” we refer to a rectangular subregion of the face, containing an anatomical component (e.g., “eye”). We present a fully-automated system for facial component-landmark detection based on multi-resolution isotropic analysis and adaptive bag-of-words...
In many visual multi-object tracking applications, the question when to add or remove a target is not trivial due to, for example, erroneous outputs of object detectors or observation models that cannot describe the full variability of the objects to track. In this paper, we present a real-time, online multi-face tracking algorithm that effectively deals with missing or uncertain detections in a principled...
Detecting humans in an image sequence is one of the most difficult problems in object recognition. It is necessary to define a robust descriptor which can extract human features from images, to improve the detecting performance. Histograms of Oriented Gradients(HOG) descriptor significantly outperforms compared with the others on human detection. The descriptor is known as a robustness descriptor...
The proposed classifier is a novel skin detector that outperforms most of the existing approaches by dropping most of the non-skin pixels in its earlier stages of weak classifiers. Only the pixels with maximum skin likelihood are processed in later adaptive classifier. Parametric background modelling and validation based online training significantly improves the robustness of the whole classifier...
We present a novel visual obstacle detection and tracking system based on stereo vision. A robust stereo matcher, an obstacle detector and a tracker module are implemented and tested under actual driving conditions. Implemented system shows reliable range estimation, detection and tracking performance. Our system has showed 82.4 percent correctly detected rate in complex traffic situations.
While local patches recognition is a key component of modern approaches to affine transformation detection and object detection, existing learning-based approaches just identify the patches based on a set of randomly picked and combined binary features, which will lose some strong correlations between features and can not provide stable and remarkable identification ability. In this paper, we proposed...
The study of traffic sign recognition system has been of great interests for many years. This problem is often addressed by a three-stage procedure involving detection, tracking and classification. In this paper, a novel approach combining detection and classification of circular traffic signs is proposed. The position and scale of sign candidates within the scene are captured by detecting the center...
Cast shadows add additional difficulties on detecting objects because they locally modify image intensity and color. Shadows may appear or disappear in an image when the object, the camera, or both are free to move through a scene. This work evaluates the performance of an object detection method based on boosted HOG paired with three different image representations in outdoor video sequences. We...
This paper presents a novel approach to discovering particular objects from a set of unannotated images. We aim to find discriminative feature sets that can effectively represent particular object classes (as opposed to object categories). We achieve this by mining correlated visual word sets from the bag-of-features model. Specifically, we consider that a visual word set belongs to the same object...
In using image analysis to assist a driver to avoid obstacles on the road, traditional approaches rely on various detectors designed to detect different types of objects. We propose a framework that is different from traditional approaches in that it focuses on finding a clear path ahead. We assume that the video camera is calibrated offline (with known intrinsic and extrinsic parameters) and vehicle...
In this paper a novel segmentation system for football player detection in broadcasted video is presented. The system is based on the combination of Histogram of Oriented Gradients (HOG) descriptors and linear Support Vector Machine (SVM) classification. Although recently HOG-based methods were successfully used for pedestrian detection, experimental results presented in this paper show that combination...
Automatic face recognition system based on local feature detection and feature extraction techniques is presented. The method works on color face images and performs face localization initially. It then detects and selects important fiducial facial points and characterizes them by bank of Gabor filters (jets). A well known PCA technique is used to reduce the dimensionality of jets and recognition...
We report on an image classification task originated from the video observation of beehives. Biologists desire to have an automatic support to identify individual bees which are labelled with badges. Current state of the art in object detection and evaluation of classifiers is briefly reviewed. Different algorithms are evaluated. ROC- as well as precision-recall analysis show that a gradient based...
With increases in computing power, the once computationally expensive sampling-based methods have been successfully applied to solve many hard vision problems of combinatorial nature, such as image segmentation, video tracking, and object detection. In this paper, we perform pedestrian detection using the reversible jump Markov chain Monte Carlo (RJMCMC) sampling method. A crowd scene is viewed as...
In this paper we propose a formalization of change detection as a Bayesian order-consistency test, based on the assumption that disturbance factors such as illumination changes and variations of camera parameters do not change the ordering between noiseless intensities within a neighborhood of pixels. The assumption of additive, zero-mean, i.i.d. gaussian noise allows for testing the composite order-consistency...
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.