Human Detection Algorithm Research Articles

Development of a Laser-Range-Finder-Based Human Tracking and Control Algorithm for a Marathoner Service Robot

This paper presents a human detection algorithm and an obstacle avoidance algorithm for a marathoner service robot (MSR) that provides a service to a marathoner while training. To be used as a MSR, the mobile robot should have the abilities to follow a running human and avoid dynamically moving obstacles in an unstructured outdoor environment. To detect a human by a laser range finder (LRF), we defined features of the human body in LRF data and employed a support vector data description method. In order to avoid moving obstacles while tracking a running person, we defined a weighted radius for each obstacle using the relative velocity between the robot and an obstacle. For smoothly bypassing obstacles without collision, a dynamic obstacle avoidance algorithm for the MSR is implemented, which directly employed a real-time position vector between the robot and the shortest path around the obstacle. We verified the feasibility of these proposed algorithms through experimentation in different outdoor environments.

Auto Face Detection and Tracking Algorithm Combining Color and Texture Features Based on Particle Filter

In this paper, an auto human face detection and tracking algorithm combining color and texture features based on particle filter is proposed. Firstly, the proposed approach makes use of AdaBoost algorithm based on skin color to detect the human face, and implements the initial face location. Secondly, the particle filter algorithm based on the weighted color histogram and the histogram of oriented gradients is used to track the human face. Finally, an adaptive window size adjustment strategy can be fused under the particle filter framework to solve the problem of fixed tracking window size. The experimental results show the robustness and accuracy of the algorithm.

Kinects and human kinetics: A new approach for studying pedestrian behavior

Microscopic pedestrian simulation models can be used to investigate pedestrian movement at the urban block and building model scale. In order to develop, calibrate and validate such microscopic models, highly accurate and detailed data on pedestrian movement and interaction behavior (e.g. collision avoidance) is required. We present a data collection approach for studying pedestrian behavior which uses the increasingly popular low-cost sensor Microsoft Kinect. The Kinect captures both standard camera data and a three-dimensional depth map. Our human detection and tracking algorithm is based on agglomerative clustering of privacy-preserving Kinect depth data captured from an elevated view – in contrast to the lateral view used for gesture recognition in Kinect gaming applications. Our approach transforms local Kinect 3D data to a common world coordinate system in order to obtain human trajectories from multiple Kinects, which allows for a scalable and flexible capturing area. At a testbed with real-world pedestrian traffic we demonstrate that our approach can provide accurate trajectories from three Kinects with a Pedestrian Detection Rate of up to 94% and a Multiple Object Tracking Precision of 4cm. Using a comprehensive dataset of 2674 captured human trajectories we calibrate three variations of the Social Force model. Data for model calibration and validation was recorded without any script and without actors behaving according to scripted situations. Various conditions have been covered in the dataset, such as walking at different densities, walking-stopping-walking, abrupt changes of direction and random movement. The results of our model validations indicate their particular ability to reproduce the observed pedestrian behavior in microscopic simulations.

고해상도 CCTV 카메라를 위한 빠른 사람 검출 알고리즘

본 논문은 사람 검출 알고리즘을 고해상도 CCTV 카메라에 적용할 수 있도록 빠른 사람 검출 알고리즘을 제안한다. HOG 디텍터를 이용한 사람 검출 알고리즘은 영상처리 분야의 최신 기술로 높은 성능을 보인다. 그러나 HOG 특징 추출과정에서 연산 속도가 느려 실시간 고해상도 영상에 적용하기 어렵다. 이러한 문제를 해결하기 위해 2단계 검출 방법을 제안한다. 먼저 전처리 과정으로 배경 차감법(Background subtraction)을 이용하여 사람 후보 영역을 찾는다. 이후 사람 후보영역에서만 HOG 디텍터를 이용하여 사람/비사람 구분을 수행한다. 이러한 두 단계의 실험 결과 약 2.5배의 검출 속도 향상을 보였으며, 성능 저하는 거의 없음을 확인할 수 있었다. This paper suggests a fast human detection algorithm that can be applied to a high-resolution CCTV camera. Human detection algorithms, which used a HOG detector show high performance in the region of image processing. On the other hand, it is difficult to apply to real-time high resolution imaging because of its slow processing speed in the extracting figures of HOG. To resolve this problems, we suggest how to detect humans into two stages. First, candidates of a human region are found using background subtraction, and humans and non-humans are distinguished using a HOG detector only. This process increases the detection speed by approximately 2.5 times without any degradation in performance.

HUMAN DETECTION IN VIDEO AND IMAGES — A STATE-OF-THE-ART SURVEY

The aim of this paper is to give an overview of state-of-the-art human detection methods, classify them into reasonable categories and listing new trends in this field. Human detection in static images or video sequences is a challenging area of research with its main application in surveillance, defence, intelligent vehicles and robotics. In this survey paper, we classify the human detection methods based upon the mode of data acquisition and features used for detection of human. The review of different algorithms reported in last few years for human detection is tabulated. Also, we reviewed standard dataset for evaluation of human detection and studied the statistics about these dataset such as number of frames, challenging environments conditions, ground truth structure, camera details, etc. Different performance measures for human detection algorithms both qualitative and quantitative are listed out. Our survey gauges the gap between the present research and future requirements.

Intelligent optimal control of thermal vision-based Person-Following Robot Platform

In this paper the supervisory control of the Person-Following Robot Platform is presented. The main part of the high level control loop of mobile robot platform is a real-time robust algorithm for human detection and tracking. The main goal was to enable mobile robot platform to recognize the person in indoor environment, and to localize it with accuracy high enough to allow adequate human-robot interaction. The developed computationally intelligent control algorithm enables robust and reliable human tracking by mobile robot platform. The core of the recognition methods proposed is genetic optimization of threshold segmentation and classification of detected regions of interests in every frame acquired by thermal vision camera. The support vector machine classifier determines whether the segmented object is human or not based on features extracted from the processed thermal image independently from current light conditions and in situations where no skin color is visible. Variation in temperature across same objects, air flow with different temperature gradients, person overlap while crossing each other and reflections, put challenges in thermal imaging and will have to be handled intelligently in order to obtain the efficient performance from motion tracking system.

Research on a Fast Human-Detection Algorithm for Unmanned Surveillance Area in Bulk Ports

With the development of port automation, most operational fields utilizing heavy equipment have gradually become unmanned. It is therefore imperative to monitor these fields in an effective and real-time manner. In this paper, a fast human-detection algorithm is proposed based on image processing. To speed up the detection process, the optimized histograms of oriented gradients (HOG) algorithm that can avoid the large number of double calculations of the original HOG and ignore insignificant features is used to describe the contour of the human body in real time. Based on the HOG features, using a training sample set consisting of scene images of a bulk port, a support vector machine (SVM) classifier combined with the AdaBoost classifier is trained to detect human. Finally, the results of the human detection experiments on Tianjin Port show that the accuracy of the proposed optimized algorithm has roughly the same accuracy as a traditional algorithm, while the proposed algorithm only takes 1/7 the amount of time. The accuracy and computing time of the proposed fast human-detection algorithm were verified to meet the security requirements of unmanned port areas.

Integrating the enriched feature with machine learning algorithms for human movement and fall detection

Movement detection is gaining more and more attention among various pattern recognition problems. Recognizing human movement activity types is extremely useful for fall detection for elderly people...

Human Detection Algorithm by Meanshift Based on Depth Map

This paper presents a method of human detection by Meanshift based on depth map. By analyzing and comprehensively applying segmentation method based on height information to extract moving target and remove the background information from depth map, then find the region of interest (ROIs) with moving target, thus through mean shift method to achieve real-time detection of targets (pedestrian). Depth image has nothing to do with color space and not suffer from the factors such as illumination, shadow effect. In this paper, using the depth image pattern recognition is a good way to overcome the difficulties of visible light image pattern recognition often encountered.

Research of Human Body Detection and Tracking Algorithm

In this paper, the proposed algorithm regards the human body object character symbol using Support Vector Machine (SVM) classifier to train and classify Histogram of Oriented Gradient (HOG) features, which improve the accuracy of human body detection. We use optical flow tracking algorithm based on corner points of the contour for tracking. Kalman filter is regarded as the predictor to predict the size and location of the searching object. Also, the size and location of track window is real-time updated. In this paper, we present an object tracking algorithm for multi-media teaching video shoot. Target tracking technology is used for the video image processing analysis. By extracting moving object, we can get information in the subsequent frames to determine the trajectory and size of moving objects. After analysis of a large number of experiments, we can draw the conclusion that the algorithm is effective.

A Novel Human Detection Algorithm Based on Foreground Segmentation

In computer vision applications, human detection occupies an important position. HOG (Histograms of Oriented Gradient) is a classical algorithm which was used in the area of object detection. But the complex background would greatly affect the test accuracy when taking HOG as a human characteristic for human detection. In order to improve the accuracy of human detection, this paper applied a new algorithm which was based on foreground segmentation. We could get each closed region by Oriented Watershed Transform and Ultrametric Contour Map, then the foreground and the background could be distinguished. Finally we removed the background and calculated the foreground characteristic. The experimental results show that this approach was effective in improving detection accuracy. c 2013 Binary Information Press a Textile Bioengineering and Informatics Society September 2013.

Cascade Classifier Using Combination of Histograms of Oriented Gradients for Rapid Pedestrian Detection

Accurate and efficient human detection has become an important area for research in computer vision. In order to solve problems in the past human detection algorithms such as features with fixed sizes, fixed positions and fixed number, the human detection based on united Hogs algorithm was proposed. This algorithm can dynamically generate the features closer to human body contours. Basically maintaining the detection speed, the detection accuracy was improved by our algorithm. We demonstrate that comparing with human detection algorithm using haar, traditional hogs and hogs with variable-size blocks, our algorithm is better in both of detection rate and false positive rate.

HoGG: Gabor and HoG-based human detection for surveillance in non-controlled environments

A new method (HoGG) for human detection based on Gabor filters and Histograms of Oriented Gradients is presented in this paper. The effect of Gabor preprocessing is analyzed in detail, in particular the improvement experienced by the image's information and the influence exerted over the extracted feature. To compare the performance of the proposed method, several alternative algorithms for human detection have been considered. In order to evaluate these techniques in non-controlled environments, a collection of standard databases, well known in the surveillance research community, has been used: PETS 2006, PETS 2007, PETS 2009 and CAVIAR. An exhaustive test design has been built based on two complementary evaluations: an evaluation oriented to counting people and a novel evaluation oriented to identification. Moreover, with the purpose of studying the performance of the Gabor-based preprocessing, a test adding Gabor filters to other local feature extraction methods, such as Steerable filters and the SIFT method, has been implemented. The HoGG method has achieved a good performance regardless of the difficulty of the images (occlusions, overlapping, carrying baggage, etc.). The proposed method has surpassed the alternative techniques in most of the analyzed situations. When the Gabor preprocessing is introduced into other local feature extraction methods, they achieve a better detection of the relevant information by enhancing the human shape. The results show that using Gabor preprocessing in techniques based on features like orientation or magnitude of gradient improve their performance. Given the excellent results obtained by HoGG at the identification-oriented evaluation, the method presented in this paper should be taken into account in the future design of intelligent surveillance systems.

영상디지털도어록용 단일 사람 검출 알고리즘 구현

영상디지털도어록(Video digital door lock, VDDL) 시스템은 문으로 출입하는 사람을 검출하고 사람 영상을 획득한다. 도어록 설계 시 고려할 사항은 배터리 기반으로 동작하므로 속도가 빠른 사람 검출 알고리즘을 적용하여 전류소모를 최소화해야 한다. 그리고 도어록은 고정된 카메라에서 영상을 촬영하므로 배경영상을 이용한 사람 검출이 높은 신뢰성을 얻을 수 있다. 본 논문에서는 이러한 요구조건에 충족하며 VDDL에 적합한 단일 사람검출 알고리즘을 다루고 있는데, 획득한 영상에서 이동하는 물체를 감지하고 영상처리를 통해 물체가 사람인지를 판별한다. 제안된 영상처리 알고리즘은 두 단계로 이루어져 있다. 첫째, 배경영상과 피부색 정보를 통해 사람 이미지 영역을 구한다. 둘째, 인체비례 정보를 기반으로 폴라 히스토그램을 이용하여 사람 유무를 판단한다. 개발된 알고리즘은 도어록에 설치하고 실험을 통해 성능을 확인하였다. Video digital door lock(VDDL) system detects people who access to the door and acquires the human image. Design considerations is that current consumption must be minimized by applying fast human detection algorithm because of battery-based operation. Since the digital door lock takes an image through a fixed camera, detection of a person based on background image leads to high degree of reliability. This paper deals with a single human detection algorithm suitable for VDDL with fulfilling these requirements such that it detects a moving object in an image, then identifies whether the object is a person or not using image processing. The proposed image processing algorithm consists of two steps: Firstly, it detects the human image region using both background image and skin color information. Secondly, it identifies the person using polar histogram based on proportional information of human body. Proposed algorithm is implemented in VDDL and is verified the performance through experiments.

Security System and Surveillance Using Real Time Object Tracking and Multiple Cameras

In this paper we propose multiple cameras using real time tracking for surveillance and security system. It is extensively used in the research field of computer vision applications, like that video surveillance, authentication systems, robotics, pre-stage of MPEG4 image compression and user inter faces by gestures. The key components of tracking for surveillance system are extracting the feature, background subtraction and identification of extracted object. Video surveillance, object detection and tracking have drawn a successful increased interest in recent years. A object tracking can be understood as the problem of finding the path (i.e. trajectory) and it can be defined as a procedure to identify the different positions of the object in each frame of a video. Based on the previous work on single detection using single stationary camera, we extend the concept to enable the tracking of multiple object detection under multiple camera and also maintain a security based system by multiple camera to track person in indoor environment, to identify by my proposal system which consist of multiple camera to monitor a person. Present study mainly aims to provide security and detect the moving object in real time video sequences and live video streaming. Based on a robust algorithm for human body detection and tracking in videos created with support of multiple cameras.

Robust event detection scheme for complex scenes in video surveillance

Event detection for video surveillance is a difficult task due to many challenges: cluttered background, illumination variations, scale variations, occlusions among people, etc. We propose an effective and efficient event detection scheme in such complex situations. Moving shadows due to illumination are tackled with a segmentation method with shadow detection, and scale variations are taken care of using the CamShift guided particle filter tracking algorithm. For event modeling, hidden Markov models are employed. The proposed scheme also reduces the overall computational cost by combing two human detection algorithms and using tracking information to aid human detection. Experimental results on TRECVid event detection evaluation demonstrate the efficacy of the proposed scheme. It is robust, especially to moving shadows and scale variations. Employing the scheme, we achieved the best run results for two events in the TRECVid benchmarking evaluation.

Fast Human Detection Using Motion Detection and Histogram of Oriented Gradients

This paper presents a real-time Human detection algorithm based on HOG (Histograms of Oriented Gradients) features and SVM (Support Vector Machine) architecture. Motion detection is used to extract moving regions, which can be scanned by sliding windows; detecting moving region can subtract unnecessary sliding windows of static background regions under the surveillance conditions, then detection efficiency can be improved. Every sliding window is regarded as an individual image region and HOG features are calculated as classified eigenvectors. At last, the detected video objects can be categorized into pre-defined groups of humans and other objects by using SVM classifier. Experimental results from real-time video are provided which demonstrate the effectiveness of the method.

A Personnel Detection Algorithm for an Intermodal Maritime Application of ITS Technology for Security at Port Facilities

With an overwhelming number of containers entering the United States on a daily basis, ports of entry are causing major concerns for homeland security. The disruption to commerce to inspect all containers would be prohibitive. Currently, fences and port security patrols protect these container storage yards. To improve security system performance, the authors propose a low cost fully distributed Intelligent Transportation System based implementation. Based on prior work accomplished in the design and fielding of a similar system in the United States, current technologies can be assembled, mixed and matched, and scaled to provide a comprehensive security system. We also propose the incorporation of a human detection algorithm to enhance standard security measures. The human detector is based on the histogram of oriented gradients detec- tion approach and the Haar-like feature detection approach. According to the conducted experimental results, merging the two detectors, results in a human detector with a high detection rate and lower false posi- tive rate. This system allows authorized operators on any console to control any device within the facility and monitor restricted areas at any given time.

Efficient HOG human detection

While Histograms of Oriented Gradients (HOG) plus Support Vector Machine (SVM) (HOG+SVM) is the most successful human detection algorithm, it is time-consuming. This paper proposes two ways to deal with this problem. One way is to reuse the features in blocks to construct the HOG features for intersecting detection windows. Another way is to utilize sub-cell based interpolation to efficiently compute the HOG features for each block. The combination of the two ways results in significant increase in detecting humans—more than five times better. To evaluate the proposed method, we have established a top-view human database. Experimental results on the top-view database and the well-known INRIA data set have demonstrated the effectiveness and efficiency of the proposed method.

A Novel Human Pose Detection from Videos Algorithm Based on Motion Capture Data

This video image of static background frame and deduction, the pixel, pixels for sports change monitoring and static pixels. By combining the feature of deformation of human body positioning movement of template, the human body pose detection algorithm put in spatio-temporal detection to human pose recognition using feature matching, accelerate matching speed probability. This method in the testing result is superior to other pose recognition algorithm, and also has the ability to quickly identify.