Histogram of oriented gradients

About: Histogram of oriented gradients is a research topic. Over the lifetime, 2037 publications have been published within this topic receiving 55881 citations. The topic is also known as: HOG.

A Joint Multi-Feature and Scale-Adaptive Correlation Filter Tracker

Abstract: Traditional tracking-by-detection trackers may fail to track targets owing to interferences, such as deformation, occlusion, fast or irregular motion, and background clutter. To improve the process of feature extraction, sample training, and the performance of the traditional kernelized correlation filter (KCF), this paper proposes a new joint multi-feature and scale-adaptive correlation filter tracking algorithm based on histogram of oriented gradients (HOG) and color-naming features. The new algorithm is composed of a position correlation filter tracker and a scale correlation filter tracker. It first uses a mask matrix to cut the training samples, obtains a higher proportion of real samples, and then trains the two correlation filter trackers. One is a position tracker that uses HOG and color-naming features to train two correlation filters, and then combines the results of the two correlation filters to calculate the target position. The second tracker is used to identify the scale with the maximum response size to select the target scale. The proposed algorithm achieves a competitive performance compared with algorithms, such as KCF, compressive tracking, and circulant structure kernel. The results show that this algorithm achieves a better performance when faced with occlusion, deformation, background clutter, and fast or irregular motion, and is able to track changes in target scale.

Gradient-Based Feature Extraction From Raw Bayer Pattern Images

Abstract: In this paper, the impact of demosaicing on gradient extraction is studied and a gradient-based feature extraction pipeline based on raw Bayer pattern images is proposed. It is shown both theoretically and experimentally that the Bayer pattern images are applicable to the central difference gradient-based feature extraction algorithms with negligible performance degradation, as long as the arrangement of color filter array (CFA) patterns matches the gradient operators. The color difference constancy assumption, which is widely used in various demosaicing algorithms, is applied in the proposed Bayer pattern image-based gradient extraction pipeline. Experimental results show that the gradients extracted from Bayer pattern images are robust enough to be used in histogram of oriented gradients (HOG)-based pedestrian detection algorithms and shift-invariant feature transform (SIFT)-based matching algorithms. By skipping most of the steps in the image signal processing (ISP) pipeline, the computational complexity and power consumption of a computer vision system can be reduced significantly.

Dirt road segmentation using color and texture features in color imagery

Abstract: This paper proposes a method for segmenting an unstructured dirt road in color space images using color and texture analysis. A support vector machine (SVM) classifier was trained on samples of on and off road patches from a similar road. Image patches were classified at sparse intervals at a fixed distance from the vehicle. Each patch is described by the Histogram of oriented gradients (HOG), the Local Binary Patters (LBP), a histogram of the color channel, and a histogram of a non linear color transform. The classified patches were transformed to the next frame of the sequence using the scale invariant feature transform (SIFT) to reduce reclassification of image patches. Morphological opening and closing were used to transform the points into a mask, and reduce errors. Experimental results indicated that the algorithm can accurately segment road images given a set of training data from similar road utilizing only color imagery.

Vision sensory substitution to aid the blind in reading and object recognition

Abstract: Vision Sensory Substitution is a non-invasive rehabilitating procedure for the blind, which provides visual information to them via any of their functioning senses. In this paper, the authors propose a more engaging, interactive and integrated technology which will enable the visually impaired ‘to read’ the text and ‘to see’ their surroundings with the aid of computer vision. For reading of the text, Optical Character Recognition engine is utilized so that the blind can listen to the text which was intended to be read. For seeing objects and captioning them, features are extracted using Histogram of Oriented Gradients and the classification and labelling of the object via its features is done using K-Nearest Neighbor classifier. Results show that a high accuracies of 92% and 88% have been achieved for text extraction and caption generation respectively. The text and captions (also in text form) are finally converted into audio signals using text to speech converters.

Computer vision and laser scanner road environment perception

Abstract: Data fusion procedure is presented to enhance classical Advanced Driver Assistance Systems (ADAS). The novel vehicle safety approach, combines two classical sensors: computer vision and laser scanner. Laser scanner algorithm performs detection of vehicles and pedestrians based on pattern matching algorithms. Computer vision approach is based on Haar-Like features for vehicles and Histogram of Oriented Gradients (HOG) features for pedestrians. The high level fusion procedure uses Kalman Filter and Joint Probabilistic Data Association (JPDA) algorithm to provide high level detection. Results proved that by means of data fusion, the performance of the system is enhanced.