Human Detection Method Research Articles

Virtual Fitting Space for Dress Trials

People buy clothes in stores which may take a lot of time for them to try their fitting and in online shopping there is no possibility where people can try-on the clothes which they want to buy. Our intention is that by creating a virtual fitting room environment we can improvise approachability of trying clothes on and need not have to waste time we need to have the correct measurement of the user and the dress model with correct rotation, measurement, location. Even people are interested more in online shopping and do buy a lot of things, but buying clothes online is still considered as ineffective way because people don’t have enough knowledge about dress fittings in online shopping and it is not even possible to try- on the clothes. In order to improvise this drawback we can use the virtual fitting room which would provide the online customers with a wide range of options and a great delight to the vendors online. This concept of e-clothing helps you decide whether the dress fits you or suits you in an easy and efficient manner. Our analysis about customers provides a great fitting of dress to the person as per their requirement. To identify a human we use skeleton detection and to find the outline of human we use human contour detection method. Different positions of human body are detected using Haar cascade classification method and warping process is used to resize the outfit according to the size of the human body.

KS-FALL: Indoor Human Fall Detection Method Under 5GHz Wireless Signals

In modern society, it has become the main threat to the elderly fall’s health or even death in the elderly. The real-time and reliable fall detection system can save the fall and hurt the elderly in time. In this paper, a human fall detection method KS-FALL based on Channel State Information and in 5G environment is proposed. KS-FALL uses Atheros commercial NIC equipment to map the amplitude information in the wireless signal to the human body’s fall action, and does not require the user to wear any equipment. Compared with the traditional 2.4 GHz signal, the 5 GHz signal provides richer sub-carrier frequency domain information, which better reflects the relationship between human motion and wireless signals, thereby more effectively distinguishing and recognizing walking, squatting, falling, etc. action, filter the environmental interference through powerful denoising method, use K-means to cluster different action data, combine SVM classifier to construct fine-grained offline fingerprint database, and use SoftMax regression model to correct SVM classification in real-time detection stage. And real-time test in two different scenarios, and the detection accuracy of the fall reached 92.3%, realizing the device-free, non-invasive, high-precision human fall detection.

Human tracking from single RGB-D camera using online learning

Human detection and tracking is an essential component in several robotics applications, especially in indoor built environments where humans and robots are expected to coexist or collaborate. Due to their low cost and capability to capture both color and depth data, RGB-D cameras have shown significant promise in human detection and tracking for robotic applications. In this paper, a new human tracking method is proposed to detect and track a specific individual from a single RGB-D sensor using online learning classifiers with no ground plane assumption. Given a previous target human position, a candidate sampling method is designed to find potential positive samples while negative samples are obtained by a random sampling process. The kernelized Support Vector Machine (SVM) is employed as the online classifier to recognize the target human and updated using both the positive and negative examples. The experimental results on six RGB-D videos of a public dataset demonstrate that the proposed method achieves higher success rates compared to a 2D tracker and a 3D human detection method at a frame rate of 3.8 fps, and is capable of efficiently retrieving the target human following intermittent occlusion.

A new 3D descriptor for human classification: application for human detection in a multi-kinect system

In this paper we present a new 3D descriptor for human classification and a human detection method based on this descriptor. The proposed 3D descriptor allows classification of an object represented by a point cloud, as human or non-human. It is derived from the well-known Histogram of Oriented Gradient by employing surface normals instead of gradients. The process consists in an appropriate subdivision of the object point cloud into blocks. These blocks provide the spatial distribution modeling of the surface normal orientation into the different parts of the object. This distribution modelling is expressed as a histogram. In addition we have set up a multi-kinect acquisition system that provides us with Complete Point Clouds (CPC) (i.e. 360° view). Such CPCs enable a suitable processing, particularly in case of occlusions. Moreover they allow for the determination of the human frontal orientation. Based on the proposed 3D descriptor, we have developed a human detection method that is applied on CPCs. First, we evaluated the 3D descriptor over a set of CPC candidates by using the Support Vector Machine (SVM) classifier. The learning process was conducted with the original CPC database that we have built. The results are very promising. The descriptor can discriminate human from non-human candidates and provides the frontal direction of humans with high precision. In addition we demonstrated that using the CPCs improves significantly the classification results in comparison with Single Point Clouds (i.e. points clouds acquired with only one kinect). Second, we compared our detection method with two others, namely the HOG detector on RGB images and a 3D HOG-based detection method that is applied on RGB-depth data. The obtained results on different situations show that the proposed human detection method provides excellent performances that outperform the other two detection methods.

Complex network based models of ECoG signals for detection of induced epileptic seizures in rats.

The automatic detection of seizures bears a considerable significance in epileptic diagnosis as it can efficiently lead to a considerable reduction of the workload of the medical staff. The present study aims at automatic detecting epileptic seizures in epileptic rats. To this end, seizures were induced in rats implementing the pentylenetetrazole model, with the electrocorticogram (ECoG) signals during, before and after the seizure periods being recorded. For this purpose, five algorithms for transforming time series into complex networks based on visibility graph (VG) algorithm were used. In this study, VG based methods were used for the first time to analyze ECoG signals in rats. Afterward, Standard measures in network science (graph properties) were made to examine the topological structure of these networks produced on the basis of ECoG signals. Then these measures were given to a classifier as input features so that the ECoG signals could be classified into seizure periods and seizure-free periods. Artificial Neural Network, considered a popular classifier, was used in this work. The experimental results showed that the method managed to detect epileptic seizure in rats with a high accuracy of 92.13%. Our proposed method was also applied to the recorded EEG signals from Bonn database to show the efficiency of the proposed method for human seizure detection.

A High-Computational Efficiency Human Detection and Flow Estimation Method Based on TOF Measurements.

State-of-the-art human detection methods focus on deep network architectures to achieve higher recognition performance, at the expense of huge computation. However, computational efficiency and real-time performance are also important evaluation indicators. This paper presents a fast real-time human detection and flow estimation method using depth images captured by a top-view TOF camera. The proposed algorithm mainly consists of head detection based on local pooling and searching, classification refinement based on human morphological features, and tracking assignment filter based on dynamic multi-dimensional feature. A depth image dataset record with more than 10k entries and departure events with detailed human location annotations is established. Taking full advantage of the distance information implied in the depth image, we achieve high-accuracy human detection and people counting with accuracy of 97.73% and significantly reduce the running time. Experiments demonstrate that our algorithm can run at 23.10 ms per frame on a CPU platform. In addition, the proposed robust approach is effective in complex situations such as fast walking, occlusion, crowded scenes, etc.

Human Lesion Detection Method Based on Image Information and Brain Signal

The brain is the largest and most complex structure in the central nervous system. It dominates all activities in the body, and the lesions in the human body are also reflected in the brain signal. In this paper, the image method is used to assist the brain signal to detect the human lesion. Due to the particularity of medical images, there is no common segmentation method for any medical image, and there is no objective standard to judge whether the segmentation is effective. Medical image segmentation technology is still a bottleneck restricting the development and the application of other related technologies in medical image processing. Based on the above reasons, this paper proposes an improved region growing algorithm based on the fuzzy theory and region growing algorithm. The algorithm is used to segment the medical images of the liver and chest X-ray of different human organs. The improved algorithm uses a threshold segmentation algorithm to assist in the automatic selection of seed points and improves the region growing rules, then morphological post-processing is used to improve the segmentation effect. The experimental results show that the improved region growing algorithm has better segmentation effect under two different organs, which proves that the algorithm has certain applicability, and its accuracy and segmentation quality are better than the traditional region growing algorithm. This algorithm combines the advantages of the threshold method and traditional region growing method. It is feasible in algorithm and has certain application value.

Обзор и классификация опубликованных методов детектирования человека

Обзор и классификация опубликованных методов детектирования человека

Human Action Recognition Using Spatio-Temporal Pyramid Model Based Background Subtraction on Depth Maps

In this paper, a background subtraction in region method is proposed to recognize actions and interactions in the video. Firstly, the video is taken and converted into frames. Preprocessing techniques are applied to sampled images for noise reduction. Next, a background subtraction method is used to extract the foreground objects in region units. The combination of the background model, color of the object and movement information are employed to get the region object likelihood. Then, an Improved Adaptive region decision function determines the object regions. Moreover, the human detection method produces a bounding box surrounding a person. Histogram Oriented Gradient (HOG) is used for feature extraction and representation. Finally, Multi class support vector machine (SVM) is the classifier used for classification. Introduction

Preference of specimen collection methods for human papillomavirus detection for cervical cancer screening: a cross-sectional study of high-risk women in Mombasa, Kenya

Preference of specimen collection methods for human papillomavirus detection for cervical cancer screening: a cross-sectional study of high-risk women in Mombasa, Kenya

An intelligent video analytics model for abnormal event detection in online surveillance video

One of the primary tools for monitoring human movement and to prevent unwanted or unintended activities is surveillance camera. Nowadays, security management professional rely heavily on video surveillance to challenge crime and avert negative incidents that impact human society. Large numbers of surveillance camera installations have been increasing dramatically in the private and public sectors to monitor public activities. Video surveillance is one of the most effective methods to guarantee security. Fitting a surveillance camera simply transfers the captured video to security personnel. But the abnormal activities can be identified only by integrating an intelligent system to analyze the videos. Hence, this paper is motivated to design and implement an Intelligent Video Analytics Model (IVAM) also known as Human Object Detection (HOD) method for analyzing and detecting video-based abundant objects and abnormal human activities. IVAM can be deployed along with surveillance cameras in any public places like airport, hospital, shopping malls and railway station to automatically identify any abnormal event. IVAM is experimented with MATLAB software and the results are verified. The performance of IVAM is evaluated by comparing the obtained results with the existing approaches and it is proved that IVAM performs better compared to other contemporary methods in terms of accurately detecting the anomalies with less error rate and high classification accuracy.

Preference of specimen collection methods for human papillomavirus detection for cervical cancer screening: a cross-sectional study of high-risk women in Mombasa, Kenya

ObjectivesSelf-collection of genital specimens for high-risk types of human papillomavirus (hrHPV) detection may increase cervical cancer screening uptake. We hypothesized that women would prefer self-collection to clinician-collection of genital specimens. To test this hypothesis, and women’s preference between two different self-collection approaches, a total of 199 women were enrolled in a cross-sectional study in Mombasa, Kenya.Materials and methodsParticipants provided self-collected specimens using the Evalyn cytobrush (Rovers) stored in a dry tube and the Viba cytobrush (Rovers) stored in wet Aptima media (Hologic). A clinician also collected cervical specimens for hrHPV testing and for cytology, and performed visual inspection using acetic acid. A post-examination questionnaire assessed preferences for the different methods of specimen collection. To test the difference in proportions for each collection method, we performed an exact binomial probability test, under the null hypothesis that women would prefer each specimen-collection method equally.ResultsMost women preferred clinician-collection over self-collection (68% versus 32%, p < 0.01). For self-collection, dry-self collection with the Evalyn brush was preferred over the wet-selection with the Viba brush (53% versus 27%, p < 0.01). There was no association between preference for self-collection and preference for a particular self-collection cytobrush.ConclusionFurther research to understand and address obstacles to self-collection of genital specimens may be needed to improve the uptake of self-collection for cervical cancer screening, especially in settings with poor access to trained healthcare providers.

Human fall detection using normalized shape aspect ratio

In video surveillance, automatic human fall detection is important to protect vulnerable groups such as the elderly. When the camera layout varies, the shape aspect ratio (SAR) of a human body may change substantially. In order to rectify these changes, in this paper, we propose an automatic human fall detection method using the normalized shape aspect ratio (NSAR). A calibration process and bicubic interpolation are implemented to generate the NSAR table for each camera. Compared with some representative fall detection methods using the SAR, the proposed method integrates the NSAR with the moving speed and direction information to robustly detect human fall, as well as being able to detect falls toward eight different directions for multiple humans. Moreover, while most of the existing fall detection methods were designed only for indoor environment, experimental results demonstrate that this newly proposed method can effectively detect human fall in both indoor and outdoor environments.

Improved Human Detection with a Fusion of Laser Scanner and Vision/Infrared Information for Mobile Applications

This paper presents a method for human detection using a laser scanner with vision or infrared images. Mobile applications require reliable and efficient methods for human detection, especially as a part of driver assistance systems, including pedestrian collision systems. The authors propose an efficient method for multimodal human detection based on a combination of the features and context information. Strictly, the human is detected in the vision/infrared images using a combination of local binary patterns and histogram of oriented gradients features with a neural network in a cascade manner. Next, using coordinates of detected humans from the vision system, the moving trajectory is predicted until the scanner working distance is reached by the individual human. Then the segmentation of data from the laser scanner is further carried out with respect to the predicted trajectory. Finally, human detection in the laser scanner working distance is performed based on modelling of the human legs. The modelling is based on the adaptive breakpoint detection algorithm and proposed improved polylines definition and fitting algorithm. The authors conducted a set of experiments in predefined scenarios, discussed the identified weakness and advantages of the proposed method, and outlined detailed future work, especially for night-time and low-light conditions.

MaaS in Bike-Sharing: Smart Phone GPS Data Based Layout Optimization and Emission Reduction Potential Analysis

As a representation of smart and green city development, bike-sharing system is one of the hottest topic in the fields of transportation, public health, urban planning, and so on. With the development of Mobility as a Service (MaaS), emerging technologies such as mobile data mining give some new solutions for optimizing bike-sharing system and predicting the emission reduction. Here, we propose a bike-sharing layout optimization and emission reduction potential analysis structure under the concept of MaaS. A human travel mode detection method and a geometry-based probability model are proposed to support the particle swarm optimization process. We implement a comparison study to analyze the computational efficiency. Taking Setagaya ward, Tokyo as the study case with about 3 million GPS trajectories, the result shows that with the increase of station number from 30 to 90, the adoption of bike-sharing system can reduce about 3.1-3.8 thousand tonnes of CO2 emission.

FreeSense

Human detection aims to monitor how people are moving in an area of interest. There are many potential applications such as asset security monitoring, emergency management, and elderly care, etc. With the development of wireless sensing technique, Wi-Fi-based human detection method carries great potential due to advantages of pervasive accessibility and coverage flexibility. Previous studies have investigated the detection of human movements via signal variations. However, affected by noises, such as multi-path effect and device difference, existing approaches cannot achieve high accuracy and low false alarm rate at the same time. In this paper, we propose FreeSense, a novel Wi-Fi-based approach for human detection. Different from previous studies that characterize the variation of temporal wireless signals or calculate the deviation of Channel State Information (CSIs) from a normal profile, we will detect human movements by identifying whether there is any phase difference between the amplitude waveforms of multiple receiving antennas. In addition, we also model the sensing coverage for movements of different granularities in open space and propose a method to estimate the coverage range. Extensive experiments demonstrate that FreeSense can achieve an average false positive rate (FP) of 0.53% and an average false negative rate (FN) of 1.40%. The coverage range estimation method can achieve an average accuracy of 1.36 m, sufficient to guide the deployment of devices for human detection indoors.

PCA-Kalman: device-free indoor human behavior detection with commodity Wi-Fi

Human behavior detection has become increasingly significant in various fields of application. In this paper, we propose a device-free indoor human behavior detection method with channel state information (CSI) and principal component analysis (PCA), respectively, in the line of sight environment, non-line-of-sight environment, and through the wall environment experiments. We divide this method into two parts. It begins with an online phase. A fingerprint database is established by collecting the original data packets of CSI in different time periods and using the characteristics of PCA algorithm to reduce the dimension of the original CSI data. Then, some outlier values are removed by Kalman filter algorithm, and we will get more stable data and fully prepared for the docking experiments. At the same time, the PCA algorithm’s estimation results are corrected according to the detected real-time motion speed to reduce the mismatch target. Then, in the offline phase, the classification of data is collected in the real-time environment by using support vector machine (SVM) algorithm. This method not only reduces the time complexity of the algorithm but also improves the detection rate of the human’s behavior and reduces the error. The processed data are matched with the data in the fingerprint database, and finally, the detection of different behaviors performed by humans in an indoor environment is finally achieved according to the matching results. We experimented repeatedly in three different scenarios, with an average 95% of human behavior detection rate in three different environments. In addition, we compare the method proposed in this paper with the existing methods in different aspects, such as the impact of the number of subcarriers, the impact of data packets, and the impact of the test area. The experimental results show that this method is superior to other algorithms in terms of average error and indoor activity recognition accuracy, which can more accurately identify indoor human motion behavior and improve the stability of the system.

Evaluation of two RNA extraction methods for human parechovirus detection on pediatric stool specimens

Human Parechovirus (HPeVs), along with human enteroviruses is associated with gastrointestinal and respiratory infections. The aim of this study was to assess the performance characteristics of two nucleic acid extraction for HPeV-RNA quantitation, the RNAlev Extraction Kit associated with Maxwell automated nucleic acid extractor (Promega, Milan, Italy) and RNAzol manually protocol. A total of 137 fecal specimens previously routinely screened for Rotavirus and Adenovirus were tested for HPeV virus. Methods 1 and 2 detected HPeV-RNA in 11 and 10 samples, respectively, with a 96.2% concordance. In particular, 124/137 (90.5%) were concordantly negative by both methods; 8/137 (5.8%) concordantly positive. For the 8 specimens that were positive by both tests, the population mean (SD) was 320 (601) copies/mg with method 1 and 1216 (2338) copies/mg with method 2. By referring to the 8 specimens that were concordantly positive, the correlation value between the two methods was not statistically significant (r=0.381 and P=0.3599). Bland-Altman analysis showed that differences between the two methods were within ±1000 copies/mg of the averaged results for all of the tested specimens. Method 2, being a semi-automated method, provides benefits over a manual method, in terms of turnaround time, less errors and reliability.

Multiple Human Body Postures Detection using Kinect

&lt;span lang="EN-US"&gt;This paper presents a method to detect multiple human body postures using Kinect sensor. In this study, a combination of shape features and body joint points are used as input features. The Kinect sensor which used infrared camera to produce a depth image is suitable to be used in an environment that has varying lighting conditions. The method for human detection is done by processing the depth image and joint data (skeleton) which able to overcome several problems such as cluttered background, various articulated poses, and change in color and illumination. Then, the body joint coordinates found on the object are used to calculate the body proportion ratio. In the experiment, the average body proportions from three body parts are obtained to verify the suitableness of golden ratio usage in this work. Finally, the measured body proportion is compared with Golden Ratio to determine whether the found object is a real human body or not. This method is tested for various scenarios, where true positive human detection is high for various postures. This method able to detect a human body in low lighting and dark room. The average body proportions obtained from the experiment show that the value is close to the golden ratio value.&lt;/span&gt;

PoseHD: Boosting Human Detectors Using Human Pose Information

As most recently proposed methods for human detection have achieved a sufficiently high recall rate within a reasonable number of proposals, in this paper, we mainly focus on how to improve the precision rate of human detectors. In order to address the two main challenges in precision improvement, i.e., i) hard background instances and ii) redundant partial proposals, we propose the novel PoseHD framework, a top-down pose-based approach on the basis of an arbitrary state-of-the-art human detector. In our proposed PoseHD framework, we first make use of human pose estimation (in a batch manner) and present pose heatmap classification (by a convolutional neural network) to eliminate hard negatives by extracting the more detailed structural information; then, we utilize pose-based proposal clustering and reranking modules, filtering redundant partial proposals by comprehensively considering both holistic and part information. The experimental results on multiple pedestrian benchmark datasets validate that our proposed PoseHD framework can generally improve the overall performance of recent state-of-the-art human detectors (by 2-4% in both mAP and MR metrics). Moreover, our PoseHD framework can be easily extended to object detection with large-scale object part annotations. Finally, in this paper, we present extensive ablative analysis to compare our approach with these traditional bottom-up pose-based models and highlight the importance of our framework design decisions.