Showing papers on "Histogram of oriented gradients published in 2005"

Histograms of oriented gradients for human detection

Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

Vehicle detection methods for surveillance applications

Abstract: The efficient monitoring of traffic flow as well as related surveillance and detection applications demand an increasingly robust recognition of vehicles in image and video data. This paper describes two different methods for vehicle detection in real world situations: Principal Component Analysis and the Histogram of Gradients principle. Both methods are described and their detection capabilities as well as advantages and disadvantages are compared. A large sample dataset which contains images of cars from the backside and frontside in day and night conditions is the basis for creating and optimizing both variants of the proposed algorithms. The resulting two detectors allow recognition of vehicles in frontal view +- 30 deg and views from behind +- 30 deg. The paper demonstrates that both detection methods can operate effectively even under difficult lighting situations with high detection rates and a low number of false positives.

Feature optimization and creation of a real time pattern matching system

Abstract: State of the art algorithms for people or vehicle detection should not only be accurate in terms of detection performance and low false alarm rate, but also fast enough for real time applications. Accurate algorithms are usually very complex and tend to have a lot of calculated features to be used or parameters available for adjustments. So one big goal is to decrease the amount of necessary features used for object detection while increasing the speed of the algorithm and overall performance by finding an optimum set of classifier variables. In this paper we describe algorithms for feature selection, parameter optimisation and pattern matching especially for the task of pedestrian detection based on Histograms of Oriented Gradients and Support Vector Machine classifiers. Shape features were derived with the Histogram of Oriented Gradients algorithm which resulted in a feature vector of 6318 elements. To decrease computation time to an acceptable limit for real-time detection we reduced the full feature vector to sizes of 1000, 500, 300, 200, and 160 elements with a genetic feature selection method. With the remaining features a Support Vector Machine classifier was build and its classification parameters further optimized to result in less support vectors for further improvements in processing speed. This paper compares the classification performance, of the different SVM's on real videos (some sample images), visualizes the chosen features (which histogram bins on which location in the image search feature) and analyses the performance of the final system with respect to execution time and frame rate.

On the Use of Edge Orientation and Distance for Content-Based Image Retrieval

Abstract: Recently, various features for content-based image retrieval (CBIR) have been proposed, such as texture, color, shape, and spatial features. In this paper we propose a new feature, called orientation-distance histogram for CBIR. Firstly, we transform the RGB color model of a given image to the HSI color model and detect edge points by using the H-vector information. Secondly, we evaluate the orientation-distance histogram from the edge points to form a feature vector. After normalization of feature, our proposed method can cope with most problems of variations in image. Finally, we show some results of query for real life images with the precision and recall rates to measure the performance. The experimental results show that the proposed retrieval method is efficient and effective