Showing papers on "Histogram of oriented gradients published in 2010"

Making action recognition robust to occlusions and viewpoint changes

Abstract: Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single location independent histogram. This limits their performance in presence of occlusions and when running on multiple viewpoints. We propose a novel approach to providing robustness to both occlusions and viewpoint changes that yields significant improvements over existing techniques. At its heart is a local partitioning and hierarchical classification of the 3D Histogram of Oriented Gradients (HOG) descriptor to represent sequences of images that have been concatenated into a data volume. We achieve robustness to occlusions and viewpoint changes by combining training data from all viewpoints to train classifiers that estimate action labels independently over sets of HOG blocks. A top level classifier combines these local labels into a global action class decision.

Color exploitation in hog-based traffic sign detection

Abstract: We study traffic sign detection on a challenging large-scale real-world dataset of panoramic images. The core processing is based on the Histogram of Oriented Gradients (HOG) algorithm which is extended by incorporating color information in the feature vector. The choice of the color space has a large influence on the performance, where we have found that the CIELab and YCbCr color spaces give the best results. The use of color significantly improves the detection performance. We compare the performance of a specific and HOG algorithm, and show that HOG outperforms the specific algorithm by up to tens of percents in most cases. In addition, we propose a new iterative SVM training paradigm to deal with the large variation in background appearance. This reduces memory consumption and increases utilization of background information.

Person Following Using Histograms of Oriented Gradients

Abstract: A method for using a remote vehicle having a stereo vision camera to detect, track, and follow a person, the method comprising: detecting a person using a video stream from the stereo vision camera and histogram of oriented gradient descriptors; estimating a distance from the remote vehicle to the person using depth data from the stereo vision camera; tracking a path of the person and estimating a heading of the person; and navigating the remote vehicle to an appropriate location relative to the person.

Visual classification of coarse vehicle orientation using Histogram of Oriented Gradients features

Abstract: For an autonomous vehicle, detecting and tracking other vehicles is a critical task. Determining the orientation of a detected vehicle is necessary for assessing whether the vehicle is a potential hazard. If a detected vehicle is moving, the orientation can be inferred from its trajectory, but if the vehicle is stationary, the orientation must be determined directly. In this paper, we focus on vision-based algorithms for determining vehicle orientation of vehicles in images. We train a set of Histogram of Oriented Gradients (HOG) classifiers to recognize different orientations of vehicles detected in imagery. We find that these orientation-specific classifiers perform well, achieving a 88% classification accuracy on a test database of 284 images. We also investigate how combinations of orientation-specific classifiers can be employed to distinguish subsets of orientations, such as driver's side versus passenger's side views. Finally, we compare a vehicle detector formed from orientation-specific classifiers to an orientation-independent classifier and find that, counter-intuitively, the orientation-independent classifier outperforms the set of orientation-specific classifiers.

Text Detection Using Edge Gradient and Graph Spectrum

Abstract: In this paper, we propose a new unsupervised text detection approach which is based on Histogram of Oriented Gradient and Graph Spectrum. By investigating the properties of text edges, the proposed approach first extracts text edges from an image and localize candidate character blocks using Histogram of Oriented Gradients, then Graph Spectrum is utilized to capture global relationship among candidate blocks and cluster candidate blocks into groups to generate bounding boxes of text objects in the image. The proposed method is robust to the color and size of text. ICDAR 2003 text locating dataset and video frames were used to evaluate the performance of the proposed approach. Experimental results demonstrated the validity of our approach.

HOG-based approach for leaf classification

Abstract: In this paper, we propose a new approach for plant leaf classification, which treat histogram of oriented gradients (HOG) as a new representation of shape, and use the Maximum Margin Criterion (MMC) for dimensionality reduction. We compare this algorithm with a classic shape classification method Inner-Distance Shape Context (IDSC) on Swedish leaf dataset and ICL dataset. The proposed method achieves better performance compared with IDSC.

Comparison of local feature descriptors for mobile visual search

Abstract: We evaluate the performance of MPEG-7 image signatures, Compressed Histogram of Gradients descriptor (CHoG) and Scale Invariant Feature Transform (SIFT) descriptors for mobile visual search applications. We observe that SIFT and CHoG outperform MPEG-7 image signatures greatly in terms of feature-level Receiver Operating Characteristic (ROC) performance and image-level matching. Moreover, CHoG descriptors demonstrate such gains while being comparable with MPEG-7 image signatures in bit-rate.

Histograms of Oriented Gradients for 3D Object Retrieval

Abstract: 3D object retrieval has received much research attention during the last years. To automatically determine the similarity between 3D objects, the global descriptor approach is very popular, and many competing methods for extracting global descriptors have been proposed to date. However, no single descriptor has yet shown to outperform all other descriptors on all retrieval benchmarks or benchmark classes. Instead, combinations of different descriptors usually yield improved performance over any single method. Therefore, enhancing the set of candidate descriptors is an important prerequisite for implementing effective 3D object retrieval systems. Inspired by promising recent results from image processing, in this paper we adapt the Histogram of Oriented Gradients (HOG) 2D image descriptor to the 3D domain. We introduce a concept for transferring the HOG descriptor extraction algorithm from 2D to 3D. We provide an implementation framework for extracting 3D HOG features from 3D mesh models, and present a systematic experimental evaluation of the retrieval effectiveness of this novel 3D descriptor. The results show that our 3D HOG implementation provides competitive retrieval performance, and is able to boost the performance of one of the best existing 3D object descriptors when used in a combined descriptor.

Quantization schemes for low bitrate Compressed Histogram of Gradients descriptors

Abstract: We study different quantization schemes for the Compressed Histogram of Gradients (CHoG) image feature descriptor. We propose a scheme for compressing distributions called Type Coding, which offers lower complexity and higher compression efficiency compared to tree-based quantization schemes proposed in prior work. We construct optimal Entropy Constrained Vector Quantization (ECVQ) code-books and show that Type Coding comes close to achieving optimal performance. The proposed descriptors are 16× smaller than SIFT and perform on par. We implement the descriptor in a mobile image retrieval system and for a database of 1 million CD, DVD and book covers, we achieve 96% retrieval accuracy using only 4 kilobytes of data per query image.

Off‐line signature verification and identification by pyramid histogram of oriented gradients

Abstract: Purpose – The purpose of this paper is to propose an effective method to perform off‐line signature verification and identification by applying a local shape descriptor pyramid histogram of oriented gradients (PHOGs), which represents local shape of an image by a histogram of edge orientations computed for each image sub‐region, quantized into a number of bins. Each bin in the PHOG histogram represents the number of edges that have orientations within a certain angular range.Design/methodology/approach – Automatic signature verification and identification are then studied in the general binary and multi‐class pattern classification framework, with five different common applied classifiers thoroughly compared.Findings – Simulation experiments show that PHOG has obvious advantages in the extraction of discriminating information from handwriting signature images compared with many previously proposed signature feature extraction approaches. The experiments also demonstrate that several classifiers, including...

Multiple Pedestrian Tracking Using Colour and Motion Models

Abstract: This paper presents a method that combines colour and motion information to track pedestrians in video sequences captured by a fixed camera. Pedestrians are firstly detected using the human detector proposed by Dalal and Triggs which involves computing the histogram of oriented gradients descriptors and classification using a linear support vector machine. For the colour-based model, we extract a 4-dimensional colour histogram for each detected pedestrian window and compare these colour histograms between consecutive video frames using the Bhattacharyya coefficient. For the motion model, we use a Kalman filter which recursively predicts and updates the estimates of the positions of pedestrians in the video frames. We evaluate our tracking method using videos from two pedestrian video datasets from the web. Our experimental results show that our tracking method outperforms one that uses only colour information and can handle partial occlusion.

Human detection using Histogram of oriented gradients and Human body ratio estimation

Abstract: Recent research has been devoted to detecting people in images and videos. In this paper, a human detection method based on Histogram of Oriented Gradients (HoG) features and human body ratio estimation is presented. We utilized the discriminative power of HoG features for human detection, and implemented motion detection and local regions sliding window classifier, to obtain a rich descriptor set. Our human detection system consists of two stages. The initial stage involves image preprocessing and image segmentation, whereas the second stage classifies the integral image as human or non-human using human body ratio estimation, local region sliding window method and HoG Human Descriptor. Subsequently, it increases the detection rate and reduces the false alarm by deducting the overlapping window. In our experiments, DaimlerChrysler pedestrian benchmark data set is used to train a standard descriptor and the results showed an overall detection rate of 80% above.

Extended Histogram of Gradients feature for human detection

Abstract: Unsigned Histogram of Gradients (UHoG) is a popular feature used for human detection. Despite its superior performance as reported in recent literature, an inherent limitation of UHoG is that gradients of opposite directions in a cell are mapped into the same histogram bin. This is undesirable as it will produce the same UHoG feature for two different patterns. To address this problem, we propose a new feature named the Extended Histogram of Gradients (ExHoG) in this paper. It comprises two components: UHoG and a histogram of absolute bin value differences of opposite gradient directions computed from Histogram of Gradients (HoG). Our experimental results show that the proposed ExHoG consistently outperforms the standard HoG and UHoG for human detection.

Automatic vehicle detection in aerial image sequences of urban areas using 3d hog features

Abstract: With the development of low cost aerial optical sensors having a spatial resolution in the range of few centimetres, the traffic monitoring by plane receives a new boost. The gained traffic data are very useful in various fields. Near real-time applications in the case of traffic management of mass events or catastrophes and non time critical applications in the wide field of general transport planning are considerable. A major processing step for automatically provided traffic data is the automatic vehicle detection. In this paper we present a new processing chain to improve this task. First achievement is limiting the search space for the detector by applying a fast and simple pre-processing algorithm. Second achievement is generating a reliable detector. This is done by the use of HoG features (Histogram of Oriented Gradients) and their appliance on two consecutive images. A smart selection of this features and their combination is done by the Real AdaBoost (Adaptive Boosting) algorithm. Our dataset consists of images from the 3K camera system acquired over the city of Munich, Germany. First results show a high detection rate and good reliability.

Robust motion detection using histogram of oriented gradients for illumination variations

Abstract: This paper proposes a robust motion detection method for illumination variations which uses histogram of oriented gradients The detection process is divided into two phases: coarse detection and refinement In the coarse detection phase, first, a texture-based background model is built which implements a group of adaptive histograms of oriented gradients; then, by comparing the histogram of oriented gradients of each pixel between current frame and background model, a foreground is segmented based on texture feature which is not susceptible to illumination variations, whereas some missing foreground regions exist; finally, the result based on texture is optimized by combining the pixel-wise detection result produced by Gaussian Mixture Model (GMM) algorithm, which greatly improves the detection performance by incorporating efficient morphological operations In the refinement phase, the above detection result is refined based on the distinction in color feature to eliminate errors like shadows, noises, redundant contour, etc Experimental results show the effectiveness and robustness of our approach in detecting moving objects in varying illumination conditions

Track Initialization in Low Frame Rate and Low Resolution Videos

Abstract: The problem of object detection and tracking has received relatively less attention in low frame rate and low resolution videos. Here we focus on motion segmentation in videos where objects appear small (less than 30-pixel tall people) and have low frame rate (less than 5 Hz). We study challenging cases where some of the, otherwise successful, approaches may break down. We investigate a number of popular techniques in computer vision that have been shown to be useful for discriminating various spatio-temporal signatures. These include: Histogram of oriented Gradients (HOG), Histogram of oriented optical Flow (HOF) and Haar-features (Viola and Jones). We use these feature to classify the motion segmentations into person vs. other and vehicle vs. other. We rely on aligned motion history images to create a more consistent object representation across frames. We present results on these features using webcam data and wide-area aerial video sequences.

Human tracking in the complicated background by Particle Filter using color-histogram and HOG

Abstract: Human tracking [1] based on computer vision, is a challenging and crucial problem in intelligent video surveillance [2] system. As is known to all, human motion [3] is usually non-linear and non-Gaussian, many prevalent frameworks are not appropriate, such as Kalman Filter [4], etc. Nevertheless, the Particle Filter [5][6][7][8] could still have good performance even when the system is nonlinear and non-Gaussian. This paper is based on Particle Filter, too. In many cases, the Particle Filter always uses single-human-feature (such as color-histogram, edge gradient, Histogram of Oriented Gradients [14] (HOG), etc) to track human objects. But using single-human-feature will lose a lot of information in the process of tracking human objects. In order to avoid this drawback, this paper proposes to fuse the information of color-histogram and HOG to track. This method keeps both color and shape information, consequently, it is more robust and steady. Experiment results demonstrate that this method is effective to improve the performance of tracking.

A complex system for football player detection in broadcasted video

Abstract: 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 of HOG and SVM seems to be a promising technique for locating and segmenting players in broadcasted video. Proposed detection system is a complex solution incorporating a dominant color based segmentation technique of a football playfield, a 3D playfield modeling algorithm based on Hough transform and a dedicated algorithm for player tracking. Evaluation of the system is carried out using SD (720×576) and HD (1280×720) resolution test material. Additionally, performance of the proposed system is tested with different lighting conditions (including non-uniform pith lightning and multiple player shadows) and various camera positions.

Football player detection in video broadcast

Abstract: The paper describes a novel segmentation system based on the combination of Histogram of Oriented Gradients (HOG) descriptors and linear Support Vector Machine (SVM) classification for football video. Recently, HOG methods were widely used for pedestrian detection. However, presented experimental results show that combination of HOG and SVM is very promising for locating and segmenting players. In proposed system a dominant color based segmentation for football playfield detection and a 3D playfield modeling based on Hough transform is introduced. Experimental evaluation of the system is done for SD (720×576) and HD (1280×720) test sequences. Additionally, we test proposed system performance for different lighting conditions (non-uniform pith lightning, multiple player shadows) as well as for various positions of the cameras used for acquisition.

Histogram of oriented gradient detector with color-invariant gradients in Gaussian color space

Abstract: The histogram of oriented gradients has been proven to be a successful method of object detection, especially for pedestrian detection in images and videos. However, the question of how to make maximal use of color information for gradient calculation has not been thoroughly investigated. We propose a simple yet effective adaption that uses a combination of grayscale-based gradient and color-invariant-based gradients (after Geusebroek et al.) to replace the original gradient definition. Our experiments show that such a combination achieves a 30% reduction in miss rate, using the same experiment setting and the same evaluation criteria as Dalal et al. We have also measured the trade-off between the performance and computational cost by using a more sophisticated quadratic kernel instead of a linear kernel. While it can reduce the miss rate further by 10% to 20%, using a quadratic kernel can take as much as 70 times more running time for the original (Dalal et al. 2006) dataset.

Fast quantization and matching of histogram-based image features

Abstract: We review construction of a Compressed Histogram of Gradients (CHoG) image feature descriptor, and study quantization problem that arises in its design. We explain our choice of algorithms for solving it, addressing both complexity and performance aspects. We also study design of algorithms for decoding and matching of compressed descriptors, and offer several techniques for speeding up these operations.

Classification of vehicles for urban traffic scenes

Abstract: An investigation into detection and classification of vehicles and pedestrians from video in urban traffic scenes is presented. The final aim is to produce systems to guide surveillance operators and reduce human resources for observing hundreds of cameras in urban traffic surveillance. Cameras are a well established means for traffic managers to observe traffic states and improve journey experiences. Firstly, per frame vehicle detection and classification is performed using 3D models on calibrated cameras. Motion silhouettes (from background estimation) are extracted and compared to a projected model silhouette to identify the ground plane position and class of vehicles and pedestrians. The system has been evaluated with the reference i-LIDS data sets from the UK Home Office. Performance has been compared for varying numbers of classes, for three different weather conditions and for different video input filters. The full system including detection and classification achieves a recall of 87% at a precision of 85.5% outperforming similar systems in the literature. To improve robustness, the use of local image patches to incorporate object appearance is investigated for surveillance applications. As an example, a novel texture saliency classifier has been proposed to detect people in a video frame by identifying salient texture regions. The image is classified into foreground and background in real- time.No temporal image information is used during the classification. The system, used for the task of detecting people entering a sterile zone, a common scenario for visual surveillance. Testing has been performed on the i-LIDS sterile zone benchmark data set of the UK Home Qffice. The basic detector is extended by fusing its output with simple motion infonriation, which significantly outperforms standard motion tracking. Lower detection time can be achieved by combining texture classification with Kalman filtering. The fusion approach running on 10 frames per second gives the highest result of Fl=O.92 for the 24 hour test data set. Based on the good results for local features, a novel classifier has been introduced by combining the concept of 3D models with local features to overcome limitations of conventional silhouette-based methods and local features in 2D. The appearance of vehicles varies substantially with the viewing angle and local features may often be occluded. In this thesis, full 3D models are used for the object categories to be detected and the feature patches are defined over these models. A calibrated camera allows an affine transformation of the observation into a normalised representation from which '3DHOG' features (3D extended histogram of oriented gradients) are defined. A variable set of interest points is used in the detection and classification processes, depending on which points in the 3D model are visible. The 3DHOG feature is compared with features based on FFf and simple histograms and also to the motion silhouette baseline on the same data. The results demonstrate that the proposed method achieves comparable performance. In particular, an advantage of .the proposed, method is that it is robust against miss-Shaped motion silhouettes which can be caused by variable lighting, camera quality and occlusions from other objects. The proposed algorithms are evaluated further on a new data set from a different camera with higher resolution, which demonstrates the portability of the training data to novel camera views. Kalman filter tracking is introduced to gain trajectory information, is used for behaviour analysis. Correctly detected tracks of 94% outperforming a baseline motion tracker (OpenCV) tested under the same conditions. A demonstrator for bus lane monitoring is introduced using the output of the detection and classification system. The thesis concludes with a critical analysis of the work and the outlook for future research opportunities.

A descriptor combining MHI and PCOG for human motion classification

Abstract: The performance of human motion classification and recognition systems is highly dependent on the distinctiveness and robustness of the feature descriptor. In this paper, a new descriptor containing motion, shape and spatial layout information is proposed, therefore it is more effective for action modeling and is suitable for detecting and recognizing a variety of actions. Experiments show that the proposed descriptor outperforms other existing methods, such as Moment Invariants and Histogram of Oriented Gradients, on recognizing human motions in an indoor environment with a stationary camera.

Permutable descriptors for orientation-invariant image matching

Abstract: Orientation-invariant feature descriptors are widely used for image matching. We propose a new method of computing and comparing Histogram of Gradients (HoG) descriptors which allows for re-orientation through permutation. We do so by moving the orientation processing to the distance comparison, rather than the descriptor computation. This improves upon prior work by increasing spatial distinctiveness. Our method method allows for very fast descriptor computation, which is advantageous since many mobile applications of HoG descriptors require fast descriptor computation on hand-held devices.

HOG feature and vocabulary tree for Content-based Image Retrieval

Abstract: Histogram of Oriented Gradients (HOG) feature descriptor is very effective to represent objects and is widely used in human and face detection. In this paper, HOG feature descriptor is applied for Content-based Image Retrieval (CBIR). For handling similarity measurement of large amount of database, vocabulary tree is used. Experimental results illustrate the comparative analysis of retrieval system based on HOG feature descriptor and Gabor transform feature descriptor. It is verified that HOG-based retrieval system improves Average Precision (AP) and Average Recall (AR) (56.75% and 38.45%, respectively) from Gabor-transform-based retrieval system (41.20% and 25.41%, respectively). All the experiments are performed on Corel 1000 natural image database.