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.
Boosted forest (BF) is a commonly used method for object detection. With the help of cascade strategy, it can efficiently reject non-object windows and finally, combined with sliding window paradigm, give the locations of target objects in an image. In the literature, many aspects of cascaded boosted forest (CBF) have been well studied, such as image representation, tree split and cascade structure...
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection...
With the increasing proportion of senior citizens, many mobility aid devices have been developed such as the rollator. However, under some circumstances, the latter may cause accidents. The EyeWalker project aims to develop a small and autonomous device for rollators to help elderly people, especially those with some degree of visual impairment, avoiding common dangers like obstacles and hazardous...
When we apply AdaBoost in pedestrian detection, a large number of examples are needed to train a detector. Except for designing features, a reasonable utilization of training examples is also significant to the detection accuracy and training time. In this paper, we propose a new method, named Weight-Loss Control Sampling (WLCS), to deal with the negative training examples by improving the training...
In this paper, we propose a novel approach based on online learning for accurate and effective detection of abandoned objects. Most existing methods for abandoned objects detection only detect abandoned objects without considering of the logic owner of the abandoned object. These methods need an advanced trained human detector to discriminate abandoned objects from still persons frequently. However,...
Object detection is an important and challenging problem in the field of computer vision. Classical object detection approaches such as background subtraction and saliency detection do not require manual collection of training samples, but can be easily affected by noise factors, such as luminance changes and cluttered background. On the other hand, supervised learning based approaches such as Boosting...
This paper describes a pedestrian detection framework that is capable of achieving high detection rate and low false positive rate, especially in a video surveillance system with a clutter background. On the premise that the targets are active in the scene, motion cues are exploited to exclude the background positions from HOG evaluation. Since clutter background may contain gradient information similar...
In object detection, the offline trained detector's performance may be degraded in a particular deployed environment, because of the large variation of different environments. In this work, we propose a data level object detector adaptation method to new environments. By recording a small amount of offline data, it's fully compatible with offline training method and easy to implement. We re-derive...
In this paper we present a cascade-based framework for object detection in which the node classifiers are trained by a learning algorithm based on ranking instead of classification error. Such an approach is particularly suited for facing the asymmetry between positive and negative class, that is a huge problem in object detection applications. Other methods focused on this problem and previously...
Significant progress has been made towards learning a generalized offline object detector. However, when a generalized offline detector is applied on new datasets, it often misses some instances of the object or produces false alarms in the background scene. we propose a novel and efficient incremental learning method, which improves the performance of an offline trained detector. Our approach adjusts...
We propose a generic framework to handle missing weak classifiers at prediction time in a boosted cascade. The contribution is a probabilistic formulation of the cascade structure that considers the uncertainty introduced by missing weak classifiers. This new formulation involves two problems: 1) the approximation of posterior probabilities on each level and 2) the computation of thresholds on these...
A macrofeature layout selection is proposed for object detection. Macrofeatures [2] are mid-level features that jointly encode a set of low-level features in a neighborhood. Our method employs line, triangle, and pyramid layouts, which are composed of several local blocks in a multi-scale feature pyramid. The method is integrated into boosting for detection, where the best layout is selected for a...
In this paper we present a new method for automatic object detection in images and video sequences. As a classifier the popular AdaBoost algorithm is used, that combines several weak classifiers into one strong classifier. To create a detector based on this classifier, the weak classifiers are set into relation during boosting by using a geometric model. All votes of the weak detectors are evaluated...
Swimmer tracking in swimming pools is a challenging vision task due to its varying complex background. Most moving object detection methods are developed for static or partial static backgrounds, and thus can not be applied in swimmer detection problems. This work presents an approach combining mean-shift clustering and cascaded boosting learning algorithm for swimmer detection. There are three main...
Efficient visual object detection is of central interest in computer vision and pattern recognition due to its wide ranges of applications. Viola and Jones' detector has become a de facto framework [1]. In this work, we propose a new method to design a cascade of boosted classifiers for fast object detection, which combines linear asymmetric classification (LAC) into the recent multi-exit cascade...
This paper proposes a method of constructing a contour-based classifier to remove the false positive objects after Haar-based detection. The classifier is learned with the discrete AdaBoost. During the training, the oriented chamfer is introduced to construct strong learners. Experimental results have demonstrated that the proposed method is feasible and promising in the removal of the false positive.
We propose a new algorithm for detecting multiple object categories that exploits the fact that different categories may share common features but with different geometric distributions. This yields an efficient detector which, in contrast to existing approaches, considerably reduces the computation cost at runtime, where the feature computation step is traditionally the most expensive. More specifically,...
This paper presents a new method to detect pedestrian in still image using Sigma sets as image region descriptors in the boosting framework. Sigma set encodes second order statistics of an image region implicitly in the form of a point set. Compared with the covariance matrix, the traditional second order statistics based region descriptor, which requires computationally demanding operations based...
In this paper, a novel feature named adaptive projection LBP (APLBP) is proposed for face detection. To promote discriminative power, the distribution information of training samples is embedded into the proposed feature. APLBP is generated by LDA which maximizes the margin between positive and negative samples adaptively, utilizing characteristics of similarity to Gaussian distribution of the training...
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 data given by geometry information of a specific multiple camera setup. Starting from a small number of positive training samples, we apply a co-training strategy in order to generate...
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.