Showing papers on "Histogram of oriented gradients published in 2008"

Fast Pedestrian Detection Using a Cascade of Boosted Covariance Features

Abstract: Efficiently and accurately detecting pedestrians plays a very important role in many computer vision applications such as video surveillance and smart cars. In order to find the right feature for this task, we first present a comprehensive experimental study on pedestrian detection using state-of-the-art locally extracted features (e.g., local receptive fields, histogram of oriented gradients, and region covariance). Building upon the findings of our experiments, we propose a new, simpler pedestrian detector using the covariance features. Unlike the work in [1], where the feature selection and weak classifier training are performed on the Riemannian manifold, we select features and train weak classifiers in the Euclidean space for faster computation. To this end, AdaBoost with weighted Fisher linear discriminant analysis-based weak classifiers are designed. A cascaded classifier structure is constructed for efficiency in the detection phase. Experiments on different datasets prove that the new pedestrian detector is not only comparable to the state-of-the-art pedestrian detectors but it also performs at a faster speed. To further accelerate the detection, we adopt a faster strategy-multiple layer boosting with heterogeneous features-to exploit the efficiency of the Haar feature and the discriminative power of the covariance feature. Experiments show that, by combining the Haar and covariance features, we speed up the original covariance feature detector [1] by up to an order of magnitude in detection time with a slight drop in detection performance.

Local features based facial expression recognition with face registration errors

Abstract: In this paper, we extensively investigate local features based facial expression recognition with face registration errors, which has never been addressed before. Our contributions are three fold. Firstly, we propose and experimentally study the histogram of oriented gradients (HOG) descriptors for facial representation. Secondly, we present facial representations based on local binary patterns (LBP) and local ternary patterns (LTP) extracted from overlapping local regions. Thirdly, we quantitatively study the impact of face registration errors on facial expression recognition using different facial representations. Overall LBP with overlapping gives the best performance (92.9% recognition rate on the Cohn-Kanade database), while maintaining a compact feature vector and best robustness against face registration errors.

Performance evaluation of local features in human classification and detection

Abstract: Detecting pedestrians accurately is the first fundamental step for many computer vision applications such as video surveillance, smart vehicles, intersection traffic analysis and so on. The authors present an experimental study on pedestrian detection using state-of-the-art local feature extraction and support vector machine (SVM) classifiers. The performance of pedestrian detection using region covariance, histogram of oriented gradients (HOG) and local receptive fields (LRF) feature descriptors is experimentally evaluated. The experiments are performed on the DaimlerChrysler benchmarking data set, the MIT CBCL data set and 'Intitut National de Recherche en Informatique et Automatique (INRIA) data set. All can be publicly accessed. The experimental results show that region covariance features with radial basis function kernel SVM and HOG features with quadratic kernel SVM outperform the combination of LRF features with quadratic kernel SVM. Furthermore, the results reveal that both covariance and HOG features perform very well in the context of pedestrian detection.

Scale Space Histogram of Oriented Gradients for Human Detection

Abstract: Human detection is the task of finding presence and position of human beings in images, In this paper, we apply scale space theory to detection human in still images. By integrating scale space theory with histogram of oriented gradients(HOG), we designed a new feature descriptor called scale space histogam of oriented gradients (SS-HOG). SS-HOG focus on the multiple scale property of describe an object. Using HOGs at multiple scale, SS-HOG encodes more information to discriminate human bodies from other object types than traditional uni-scale HOGs Experiments on INRIA person dataset demonstrate the effectiveness of our method.

People detection in low resolution infrared videos

Abstract: In this paper we present a method for detecting people in low resolution infrared videos. We further explore the feature set based on histogram of gradients beyond the well received HOG descriptors. Our approach is based on extracting gradient histograms from recursively generated patches and subsequently computing histogram ratios between the patches. Each set of patches is defined in terms of relative position within the search window, and each set is then recursively applied to extract smaller patches. The histogram of gradient ratios between patches become the feature vector. We adopted a linear SVM classifier as it provides a fast and effective framework for feature descriptor processing with minimal parameter tuning. Experimental results are presented on various OTCBVS datasets.

Graph cut video object segmentation using histogram of oriented gradients

Abstract: This paper introduces a novel way to implement graph cut for video object segmentation with shape information. Graph Cut is a very efficient algorithm for image segmentation and histogram of oriented gradients (HOG) is useful in detecting humans. We combine the HOG feature to incorporate a shape prior into graph cut algorithm as a new way to enhance video object segmentation accuracy. In previous work, we used a fully connected 3-D that is slow and is subject to weak edges, inconsistent luminance. The new method is compared with old methods to show that it helps by introducing a shape prior for segmentation of pre-trained objects such as humans.

On Integration of Features and Classifiers for Robust Vehicle Detection

Abstract: Some researches have demonstrated that a single recognition system is not usually able to deal with the diversity of environment situations in images. In this paper, with the aim of finding a robust method to compensate single classifier inability under certain circumstances, an extensive study on how to combine features and classifiers is performed. Two ways of integrating features and classifiers are proposed: concatenated vector and ensemble architecture. These two methods are composed by Histogram of Oriented Gradients and Local Receptive Fields as feature extractors, and a Multi Layer Perceptron and Support Vector Machines as classifiers. A thorough analysis with respect to the robustness of the proposed methods over artificial illumination changing has been experimentally carried out at a front and rear vehicle recognition task. Results have demonstrated that the ensemble architecture with a heuristic Majority Voting presented the best performance (other four classification fusion methods based on majority voting and fuzzy integral were also evaluated). The ensemble classifier obtained an average hit rate of 92.4% and less than 1% of false alarm rate under multiple datasets and environment conditions.

An experimental study on pedestrian classification using local features

Abstract: This paper presents an experimental study on pedestrian detection using state-of-the-art local feature extraction and support vector machine (SVM) classifiers. The performance of pedestrian detection using region covariance, histogram of oriented gradients (HOG) and local receptive fields (LRF) feature descriptors is experimentally evaluated. The experiments are performed on both the benchmarking dataset used in [1] and the MIT CBCL dataset. Both can be publicly accessed. The experimental results show that region covariance features with radial basis function (RBF) kernel SVM and HOG features with quadratic kernel SVM outperform the combination of LRF features with quadratic kernel SVM reported in [1].

Pedestrian detection using improved histogram of oriented gradients

Abstract: Histogram of oriented gradients (HOG) has been proved to be an effective way of solving pedestrian detection in real scenes, but great computation amount makes it far from practical application. So we propose a new detection system based on improved HOG features with faster detecting speed. While calculating HOG, the pixels irrelevant to object contour shape are neglected. Then we decrease dimension number of the feature vector by 80%, making the SVM classification model much more simplified. Although the accuracy only drops down no more than 5%, our improved method performs over 5 times faster than the previous one. After entirely scanning a image, we use mean shift clustering algorithm to merge multiple positive responses belonging to same one positive case. Experiments show our method's performance on both test dataset and in real scene images.

Pedestrian recognition using stereo vision and Histogram of Oriented Gradients

Abstract: In this paper, we propose a fast and stable pedestrian recognition approach using the features from both stereo vision and HOG (Histogram of Oriented Gradient) filter. It inquires the histogram of disparity from the stereo images and builds a mask image to extract the features from foreground regions exclusively. HOG and PCA (Principal Component Analysis) are then applied to the foreground edge image and pedestrian recognition is performed by Naive Bayes classifier to achieve the real-time performance. The real road experiments showed effectiveness and efficiency of the proposed approach.

Shape-based image retrieval

Abstract: Content-based image retrieval (CBIR) is an important issue in the computer vision community. Shape feature is one of the most important visual features. The shape feature is essential as it corresponds to the region of interest in images. Low-level visual features are used for representation and retrieval of images. Each object/region within an image is indexed by object/region-based shape feature vector. The shape feature vector is invariant to translation, rotation and scaling.

Boosted parametric model for human detection

Abstract: In this paper we discuss the issue of classifiers combined with histogram of oriented gradients (HOG) descriptors for human detection. And we present a method that combines AdaBoost learning with HOG descriptors. The weak learners used in our algorithm are based on weighted modified quadratic discriminant functions (MQDF) which is a parametric model. We evaluate our algorithm on the INRIA person dataset. And the experimental results show that our approach achieves a comparable performance with the state of art methods both on accuracy and speed.

Comparison of linear feature spaces for classi¯cation of face sequences in movie videos

Abstract: We consider classification problem of face sequences extracted from actual movie videos. At first all faces are extracted from each frame of the given movie videos by applying the popular face detector proposed by Viola and Jones. Then they are merged as a face sequences if the faces in the consecutive frames belong to the same shot and have similar size and location. Histogram of Oriented Gradients (HOG) features are extracted from each face image in the sequences and they are used to compare the similarity of the face sequences. In this paper, we compare the performance of the several dimension reduction methods, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Locality Preserving Projection (LPP).