Hardware implementation of an improved HOG descriptor for pedestrian detection

Hardware implementation of human detection is a challenging task for embedded designs. This paper presents a real-time image-based field-programmable gate array (FPGA) implementation of human detection. Our implementation is based on the histograms of oriented gradients (HOG) feature and linear support vector machine (SVM) classifier. The novelty of this work is that we replace normalization process of HOG with a modified binarization process. Therefore, during classification process with SVM classifier, all multiplication operations are replaced by addition operations. All these modifications result in reduction of hardware resource. Experimental evaluation reveals that 293 fps can be achieved on a low-end Xilinx Spartan-3e FPGA. Moreover, a detection accuracy of 1.97% miss rate and 1% false positive rate is achieved. For further demonstration, a prototype system is developed with an OV7670 camera device. Restricted to the speed of camera, a detection rate of 30 fps is achieved.

This paper describes a close to real-time scale invariant implementation of a pedestrian detector system which is based on the Histogram of Oriented Gradients (HOG) principle. Salient HOG features are first selected from a manually created very large database of samples with an evolutionary optimization procedure that directly trains a polynomial Support Vector Machine (SVM). Real-time operation is achieved by a cascaded 2-step classifier which uses first a very fast linear SVM (with the same features as the polynomial SVM) to reject most of the irrelevant detections and then computes the decision function with a polynomial SVM on the remaining set of candidate detections. Scale invariance is achieved by running the detector of constant size on scaled versions of the original input images and by clustering the results over all resolutions. The pedestrian detection system has been implemented in two versions: i) fully body detection, and ii) upper body only detection. The latter is especially suited for very busy and crowded scenarios. On a state-of-the-art PC it is able to run at a frequency of 8 - 20 frames/sec.

Pedestrian detection in a single image takes more time than that in a video due to the requirement of scanning the whole image. In this paper, an improved pedestrian detection system based on region of interest (ROI) is proposed for single images. In the improved pedestrian detection system, principal component analysis (PCA) is introduced to improve the detection rate and accuracy of histogram of oriented gradients (HOG) based support vector machine (SVM) classifier for pedestrian detection. PCA eliminates the redundant HOG feature dimensions that have no contribution for the pedestrian classification. A novel ROI extraction method based on fuzzy C-means (FCM) clustering algorithm is used to select the regions that possibly contain pedestrians in a single image. ROI extraction reduces the number of detection windows, resulting in a significant reduction in detection time of a single image. Computer experiments show that the proposed pedestrian detection system can correctly detect the positions of pedestrians in single images in real time.

Communication is the ultimate of man’s search for conveying his ideas, emotions, and concepts. Dance is one of the media of communication through which dancers share notion of feelings, with the spectators through gestures, i.e., mudra. Gesture recognition propagates a concept without verbal speech or listening, and in dance recognition, the notion is transferred through various dance poses and actions. This activity in a way really paves way to enhance Indian Sign Language. This study focuses to solve the mudra resemblance in Bharatanatyam through a new system developed with image processing and classification technique using histogram of oriented gradient (HOG) feature extraction techniques and support vector machine (SVM) classifier. SVM classifies the features of HOG into mudras as text labels. Popular feature vectors such as scale-invariant feature transform (SIFT), speed up robust feature (SURF), and local binary pattern (LBP) are hardened against HOG for accuracy and speediness, and this innovative proposed concept is useful for online dance learners.

Histogram of oriented gradient (HOG) feature has been widely used in vehicle detection. In this paper, a modified version of HOG is proposed by introducing compass gradient into the HOG calculation. Three different versions of the modified HOG features are used as an input for linear and nonlinear support vector machine (SVM). The modified HOG variants proved to have better classification performance than that of the standard HOG. The classification results of modified HOG and nonlinear SVM are compared to the classification results of YOLO object detector. Finally, a vehicle detection system based on the best performing classifiers is introduced.

More than 90% of traffic accidents are caused by humans. Therefore, the wide adoption of autonomous vehicles and advanced driver assistance systems (ADAS) is expected to save hundreds of thousands of lives in the next decades. One important capability of autonomous vehicles and ADAS is pedestrian detection. However, such detection becomes very challenging in scenarios where pedestrians are partially occluded, resulting in high rates of non-detection. In this paper, we improve the performance of a pedestrian classifier by proposing frameworks composed of Histogram of Oriented Gradients (HOG) feature extraction, combined with Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost) learning models. In order to validate the performance of the improved approach, we consider the PSU and the INRIA pedestrian datasets. The state-of-the-art detection rates for the PSU and INRIA datasets are 55% and 54%, respectively. The proposed approach achieves detection rates of 86% and 82%, respectively, considerably outperforming the state-of-the-art results.

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.

Pedestrian detection is an important but challenging component of an Intelligent Transportation System. In this paper, we describe a pedestrian detection system based on a monocular vision with a Far-Infrared camera (FIR). We propose an original feature representation, called Intensity Self Similarity (ISS), adapted to pedestrian detection in FIR images. The ISS representation is based on the relative intensity self similarity within a pedestrian region of interest (ROI) hypothesis. Our system consists of two components. The first component generates pedestrian ROI hypothesis by exploiting the specific characteristics of FIR images, where pedestrian shapes may vary in large scale, but heads appear usually as light regions. Pedestrian ROI are detected, with high recall rate, due to a Hierarchical Codebook (HC) of Speeded-Up Robust Features (SURF) located in light head regions. The second component consists of pedestrian hypothesis validation, by using a pedestrian full-body classification based on the ISS representation, with Support Vector Machine (SVM). For classification, we retained two feature descriptors: the Histogram of Oriented Gradients (HOG) descriptor and the original ISS feature representation that we proposed for FIR images. The early fusion of these two features enhances significantly the system precision, attaining an F-measure for the pedestrian class of 97.7%. Moreover, this feature fusion outperforms the state-of-the-art SURF descriptor proposed previously. The experimental evaluation shows that our pedestrian detector is also robust, since it performs well in detecting pedestrians even in large scale and crowded real-world scenes.

In order for a driverless car to drive safe, it is important to accurately estimate information about any obstacles near the car and especially the existence and position of pedestrians. A histogram of oriented gradient (HOG) support vector machine (SVM) is widely used in pedestrian detection algorithms but can cause a false positive problem. This paper will suggest an improved pedestrian detecting means that is using Euclidean distance of coordinate values of the center in extracted foreground objectives after removing ground and background and in the extracted HOG based SVM from an input sequence through V-disparity map to achieve safe pedestrian detecting in dynamic conditions. Its superior performance compared to the existing HOG-based SVM was proven through the results of an image sequence.

Considering the importance of pedestrian detection in a variety of applications such as advanced robots and intelligent surveillance systems, this paper presents an improved pedestrian detection method through integrating Haar-like features, AdaBoost algorithm, histogram of oriented gradients (HOG) descriptor, and support vector machine (SVM) classifiers, in which the head and shoulder information is utilized especially. Due to the fast training speed of Haar-like features and the high detection efficiency of HOG features, the proposed method can classify pedestrians precisely with higher speed. Experimental results validated the efficiency and effectiveness of the proposed algorithm.

Abstract: A significant challenge in women’s health is posed by Polycystic Ovary Syndrome (PCOS) because it is a difficult disorder to comprehend and exhibits various symptoms. Thisresearch project suggests the creation of a computerized prediction scheme for PCOS using machine learning algorithms and bioinformatics tools. The aim of this system is to give personalized risk assessment to women thus enabling early detection, and proactive management of PCOS. It combines other intelligible probabilities about PCOS with the use of user provided health data with Machine Learning models such as Random Forest, Logistic Regression, Support Vector Machine, Naive Bayes, Radial SVM, Linear SVM and KNeighbours Classifier. Additionally, it provides intuitive predictions regarding PCOS likelihood through ML models, which are based on Random Forest, Logistic Regression, Support Vector Machine (SVM), Naive Bayes (NB), Radial SVM (RSVM), Linear SVM (LSVM) and KNeighbours Classifier (KNC). By way of thorough assessment as well as comparison within these models the system intends to improve precision together with reliability during prediction of PCOS. The major objective is therefore to enable timely intervention along with individualized healthcare strategies that will promote better health outcomes for all women.

Histograms of oriented gradients (HOG) is the most successful feature descriptor in pedestrian detection; however, it is limited because of only considering the gradient. It has a certain false-positive rate on some examples, which have a lot of parallel vertical components (looks like a leg or a body) due to lacking of texture feature. This paper proposes a method to combine a cell-structured HOG feature and adaptive local binary pattern feature to solve the problem that HOG is vulnerable to the interference of vertical background gradient information in pedestrian detection. In addition, we use a fast method to utilize sub-cell-based interpolation to efficiently compute HOG feature for each block. Training the combination feature to get a discriminative model by bootstrapped linear support vector machine. Experimental results on the INRIA dataset have demonstrated the effectiveness and efficiency of the proposed method.

Traffic signal detection has long been an important function in an advanced driver assistance system (ADAS). This paper presents a complete system design based on the techniques of blob detection, histogram of oriented gradients (HOG) and support vector machine (SVM). Blob detection is applied to detect potential candidates, and then HOG and SVM is for feature classification. A novel hardware/software co-design architecture is developed for traffic light recognition at real-time. With well-balanced workload on FPGA fabric and the on-chip ARM processor, the entire system-on-chip can achieve a processing rate of 60 fps for XGA 1024-by-768 video. The system can achieve an accuracy rate of over 90% on both red lights and green lights. The proposed system can be improved by replacing HOG with more advanced feature algorithm to obtain higher accuracy.

Pedestrian detection reliability is a key problem for autonomous or aided driving, and methods that use Histogram of Oriented Gradients (HOG) are very popular. Embedded Graphics Processing Units (GPUs) are exploited to run HOG in a very efficient manner. Unfortunately, GPUs architecture has been shown to be particularly vulnerable to radiation-induced failures. This article presents an experimental evaluation and analytical study of HOG reliability. We aim at quantifying and qualifying the radiation-induced errors on pedestrian detection applications executed in embedded GPUs. We analyze experimental results obtained executing HOG on embedded GPUs from two different vendors, exposed for about 100 hours to a controlled neutron beam at Los Alamos National Laboratory. We consider the number and position of detected objects as well as precision and recall to discriminate critical erroneous computations. The reported analysis shows that, while being intrinsically resilient (65% to 85% of output errors only slightly impact detection), HOG experienced some particularly critical errors that could result in undetected pedestrians or unnecessary vehicle stops. Additionally, we perform a fault-injection campaign to identify HOG critical procedures. We observe that Resize and Normalize are the most sensitive and critical phases, as about 20% of injections generate an output error that significantly impacts HOG detection. With our insights, we are able to find those limited portions of HOG that, if hardened, are more likely to increase reliability without introducing unnecessary overhead.

A two-stage pipeline architecture for pedestrian detection processor, which embeds the support vector machine (SVM) classifier into the Histogram of Oriented Gradients (HOG) normalization module is proposed. This architecture can effectively reduce hardware resource consumption and can perform pedestrian detection task real-timely. Also, an algorithm is proposed to avoid duplicated detection automatically. The architecture is verified on Spartan-6 FPGA for SVGA resolution video (800×600) at 47 fps/100MHz.