CHILD AND ADULT CLASSIFICATION USING BIOMETRIC FEATURES BASED ON VIDEO ANALYTICS

Outdoor pedestrian detection is one of most important, primary and challenging preprocessing step for any automated visual surveillance activity ranging from event to activity detection. Currently used algorithms are resolution, scale and clothing dependent, their performance decreases as resolution of camera decreases and the size of pedestrian decreases to small scale (30-80 pixels). Moreover, regions like Middle East where loose clothes are mostly used the performance of these systems get worse. The reason behind the failure of these systems is that most of them target the contour information of pedestrian and as the scale decreases or cloth varies the contour information becomes ambiguous. Noise accumulation, wide area view, low resolution, outdoor environment artifacts, low frame rate further add to the complexity of pedestrian detection. The paper proposes a pedestrian detection algorithm that detects the pedestrian of small scale from the low frame rate (5 frames per second) video captured by low resolution CCTV camera (352x288) resolution. The algorithm is clothing and illumination invariant and proposes two main contributions: first, motion cues and edge lets based contour detection (ECD) are used to target temporal and low level pixel details, handling clothing variation and providing a heuristic window for pedestrian detection and second, the heuristic window is searched for presence of pedestrian using linear support vector machine (SVM)classifier trained over hybrid of histogram of oriented gradients (HOG) and statistical shape based feature vector.

This work presents a novel method for detecting and tracking pedestrians from video images taken by a fixed camera. A pedestrian may be totally or partially occluded in a scene for some period of time. The proposed approach uses the appearance model for the identification of pedestrians and the weighted temporal texture features. We compared the proposed method with other related methods using color and shape features, and analyzed the features' stability. Experimental results with various real video data revealed that real time pedestrian detection and tracking is possible with increased stability over 5-15% even under occasional occlusions in video surveillance applications.

Automatic visual scene understanding is one of the ultimate goals in computer vision and has been in the field’s focus since its early beginning. Despite continuous effort over several years, applications such as autonomous driving and robotics are still unsolved and subject to active research. In recent years, improved probabilistic methods became a popular tool for current state-of-the-art computer vision algorithms. Additionally, high resolution digital imaging devices and increased computational power became available. By leveraging these methodical and technical advancements current methods obtain encouraging results in well defined environments for robust object class detection, tracking and pixel-wise semantic scene labeling and give rise to renewed hope for further progress in scene understanding for real environments. This thesis improves state-of-the-art scene understanding with monocular cameras and aims for applications on mobile platforms such as service robots or driver assistance for automotive safety. It develops and improves approaches for object class detection and semantic scene labeling and integrates those into models for global scene reasoning which exploit context at different levels. To enhance object class detection, we perform a thorough evaluation for people and pedestrian detection with the popular sliding window framework. In particular, we address pedestrian detection from a moving camera and provide new benchmark datasets for this task. As frequently used single-window metrics can fail to predict algorithm performance, we argue for application-driven image-based evaluation metrics, which allow a better system assessment. We propose and analyze features and their combination based on visual and motion cues. Detection performance is evaluated systematically for different feature-classifiers combinations which is crucial to yield best results. Our results indicate that cue combination with complementary features allow improved performance. Despite camera ego-motion, we obtain significantly better detection results for motion-enhanced pedestrian detectors. Realistic onboard applications demand real-time processing with frame rates of 10 Hz and higher. In this thesis we propose to exploit parallelism in order to achieve the required runtime performance for sliding window object detection. In a case study we employ commodity graphics hardware for the popular histograms of oriented gradients (HOG) detection approach and achieve a significant speed-up compared to a baseline CPU implementation. Furthermore, we propose an integrated dynamic conditional random field model for joint semantic scene labeling and object detection in highly dynamic scenes. Our model improves semantic context modeling and fuses low-level filter bank responses with more global object detections. Recognition performance is increased for object as well as scene classes. Integration over time needs to account for different dynamics of objects and scene classes but yields more robust results. Finally, we propose a probabilistic 3D scene model that encompasses multi-class object detection, object tracking, scene labeling, and 3D geometric relations. This integrated 3D model is able to represent complex interactions like inter-object occlusion, physical exclusion between objects, and geometric context. Inference in this model allows to recover 3D scene context and perform 3D multi-object tracking from a mobile observer, for objects of multiple categories, using only monocular video as input. Our results indicate that our joint scene tracklet model for the evidence collected over multiple frames substantially improves performance. All experiments throughout this thesis are performed on challenging real world data. We contribute several datasets that were recorded from moving cars in urban and sub-urban environments. Highly dynamic scenes are obtained while driving in normal traffic on rural roads. Our experiments support that joint models, which integrate semantic scene labeling, object detection and tracking, are well suited to improve the individual stand-alone tasks’ performance.

Pedestrian detector performance is damaged because occlusion often leads to missed detection. In order to improve the detector's ability to detect pedestrian, a single-stage detector based on feature-guided attention mechanism is proposed. Firstly, a feature attention module is designed, which preserves the association between the feature channels while retaining spatial information, and guides the model to focus on visible region. Secondly, the attention module is used to fuse shallow and deep features, then high-level semantic features of pedestrians are extracted. Finally, pedestrian detection is treated as a high-level semantic feature detection problem. Pedestrian location and scale are obtained through heat map prediction, then the final prediction bounding box is generated. This way, the proposed method avoids the extra parameter settings of the traditional anchor-based method. Experiments show that the proposed method is superior to other comparison algorithms for the accuracy of occlusion target detection on CityPersons and Caltech pedestrian database. At the same time, the proposed method achieves a faster detection speed and a better balance between detection accuracy and speed.

his paper discuss the problem of pedestrian detection and tracking in HD video, the resolution of which is 1080*1920 pixels, using background difference for pedestrian detection and Mean-Shift for pedestrian tracking. And we realized it in our system using some acceleration methods, the experimental result of our system showed it could get the same result as the video with the resolution of 400*600 pixels at the same speed using our method. The Acceleration rate can get as high as 10.

Computer Vision Plays a vital role in traffic management and surveillance systems and has been an active research area in the past years. In systems like these, the detection of vehicles and also classification of the vehicle plays a major role. This Paper presents a real time system for Vehicle Detection and Classification with Haar cascade Classifier along with Mixture Of Guassians (MoG) for Background Substitution. The datasets are traffic videos of urban environment taken from various cities around the world which were used to train the classifier hence generating a robust classifier. The proposed approach is computationally less expensive with faster processing speed. The experiments on-road prove it to be a robust and real time algorithm which is highly competitive with the existing architecture.

Pedestrian detection is an active area of research with challenge in computer vision.This study conducts a detailed survey on state-of-the-art pedestrian detection methods from 2005 to 2011,focusing on the two most important problems:feature extraction,the classification and localization.We divided these methods into different categories;pedestrian features are divided into three subcategories:low-level feature,learning-based feature and hybrid feature.On the other hand,classification and localization is also divided into two sub-categories:sliding window and beyond sliding window.According to the taxonomy,the pros and cons of different approaches are discussed.Finally,some experiences of how to construct a robust pedestrian detector are presented and future research trends are proposed.

Many classes of objects can now be successfully detected with statistical machine learning techniques. Faces, cars and pedestrians, have all been detected with low error rates by learning their appearance in a highly generic manner from extensive training sets. These recent advances have enabled the use of reliable object detection components in real systems, such as automatic face focusing functions on digital cameras. One key drawback of these methods, and the issue addressed here, is the prohibitive requirement that training sets contain thousands of manually annotated examples. We present three methods which make headway toward reducing labeling requirements and in turn, toward a tractable solution to the general detection problem. First, we propose a new learning strategy for object detection. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform based on the signal of interest. We train a detector with a standard AdaBoost procedure by using combinations of pose-indexed features and pose estimators. This allows the learning process to select and combine various estimates of the pose with features able to compensate for variations in pose without the need to label data for training or explore the pose space in testing. We validate our framework on three types of data: hand video sequences, aerial images of cars, as well as face images. We compare our method to a standard Boosting framework, with access to the same ground truth, and show a reduction in the false alarm rate of up to an order of magnitude. Where possible, we compare our method to the state-of-the art, which requires pose annotations of the training data, and demonstrate comparable performance. Second, we propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists in iteratively improving an appearance-based model built with a Boosting procedure, and the reconstruction of trajectories corresponding to the motion of multiple targets. We demonstrate the efficiency of our procedure by learning a pedestrian detector from videos and a cell detector from microscopy image sequences. In both cases, our method is demonstrated to reduce the labeling requirement by one to two orders of magnitude. We show that in some instances, our method trained with sparse labels on a video sequence is able to outperform a standard learning procedure trained with the fully labeled sequence. Third, we propose a new active learning procedure which exploits the spatial structure of image data and queries entire scenes or frames of a video rather than individual examples. We extend the Query by Committee approach allowing it to characterize the most informative scenes that are to be selected for labeling. We show that an aggressive procedure which exhibits zero tolerance to target localization error performs as well as more sophisticated strategies taking into account the trade-off between missed detections and localization error. Finally, we combine this method with our two proposed approaches above and demonstrate that the resulting algorithm can properly perform car detection from a small set of annotated image as well as pedestrian detection from a handful of labeled video frames.

This paper proposes a new approach for a vehicle based pedestrian detection and classification system. The pedestrian detection is performed based on the 3D data by generating a density map. Pedestrian classification uses a pattern matching approach and exploits both 2D image information and 3D dense stereo information. Because 3D information accuracy does not allow the direct classification of the 3D shape, a combined 3D-2D method is proposed. The 3D data is used for effective generation of pedestrian hypotheses, scale and depth estimation, and 2D models selection. From the 3D hypothesis, the corresponding 2D image window is selected and the 2D hypothesis is generated. The 2D hypothesis consists in the objects external edges obtained by an edge extraction and depth based filtering process. The scaled models are matched against the selected hypothesis using an elastic high speed matching based on the Chamfer distance. The method has been tested on synthetic and real world scenarios.

Recently, European Union advocates the smart Solid-State Lighting (SSL). The key factors are a smart-control scheme and an interaction with other networks, such as communication networks and traffic monitoring sensor networks. Public lighting represents a significant share of city total electricity costs, accounting for up to 60% of the budget. The adoption and deployment of new technologies, such as SSL that is based on Light-Emitting Diodes (LED), offer great opportunities to improve efficiencies and reduce costs. When combined with smart light management systems, SSL can save up the electricity used for lighting and significantly reduce energy and maintenance costs compared to current lighting installations. Moreover, streetlights are the infrastructures erecting beside or in the middle of the streets, so they seem to be the ideal observers of the traffic situations. Even though, other functional sensors, e.g., for measuring temperatures, CO2 and even particulate matter 2.5 (PM2.5), could be integrated in the smart-streetlights. Nowadays there are no sensors embedded in commercial available streetlights, except for the infrared motion sensor used only for pedestrian detection since their range is limited to about 10 meters, as well as there are limited networking capabilities, both in data-rate and functionalities, e.g. it is possible the dimming of only the entire file of streetlights. Hence, the idea to develop aWireless Sensor Front-End (WSFE), which is capable of working as motion sensor, namely a Doppler radar sensor, to monitor the road traffic as well as transceiver to communicate with the other network nodes. Such kind of WSFE could enable many streetlights futures, for example the lighting can be adapted to the traffic conditions and the presence of pedestrians on the sideways. Meanwhile, the communication function can build up a wireless network that can be used to manage the streetlight infrastructure and to collect information on traffic conditions, sensor reading, network status and so on. This thesis proposes a 24GHz 4-channel Phased-Array (Ph-A) front-end for smart-streetlight applications. The design exploits a 90nm Complementary Metal-Oxide-Semiconductor (CMOS) technology to benefit of the low-cost offered by CMOS technology. The architecture of the selected front-end allows the implementation of transceivers as well as Doppler radar sensors. Furthermore, the Ph-A technology is applied to the Doppler radar sensor in order to realizemulti-lane road scanning and pedestrian detection. The intercommunication between streetlights is based on a time-sharing mechanism and uses the same FE reconfigured as transceiver.[...]

Pedestrian detection and tracking constitutes a key element of many intelligent video systems in different application areas, in particular for video surveillance, driving assistance, advanced manufacturing automation, and video indexing and retrieval tasks. Each particular application domain poses significant and, sometimes, different challenges to this task (e.g., applications with static or dynamic cluttered backgrounds, recognition in poor lighting conditions, and occlusion management). For this reason, a considerable amount of literature has been produced in the past to cope with a majority of the given issues. This entry presents the reader with an overview of recent detection and tracking approaches by focusing on their role in computer vision applications, analyzing the associated main challenges, and how they are currently addressed.

Lately electronic tagging policy for the sexual offenders was introduced in order to reduce and prevent sexual offences. However, most sexual offences against children happening these days are committed by the tagged offenders whose identities have been released. So, for the crime prevention, we need measures with which we could minimize the suffers more promptly and actively. This paper suggests a new system to relieve the sexual abuse related anxiety of the children and solve the problems that electronic bracelet has. Existing bracelets are only worn by serious criminals, and it's only for risk management and positioning, there is no way to protect the children who are the potential victims of sexual abuse and there actually happened some cases. So we suggest also letting the students(children) wear the LBS(Location Based Service) and USN(Ubiquitous Sensor Network) technology based electronic bracelets to monitor and figure out dangerous situations intelligently, so that we could prevent sexual offences against children beforehand, and while a crime is happening, we could judge the situation of the crime intelligently and take swift action to minimize the suffer. And by checking students' attendance and position, guardians could know where their children are in real time and could protect the children from not only sexual offences but also violent crimes against children like kidnapping. The overall system is like follows : RFID Tag for children monitors the approach of offenders. While an offender's RFID tag is approaching, it will transmit the situation and position as the first warning message to the control center and the guardians. When the offender is going far away, it turns to monitoring mode, and if the tag of the child or the offender is taken off or the child and offender stay at one position for 3~5 minutes or longer, then it will consider this as a dangerous situation, then transmit the emergency situations and position as the second warning message to the control center and the guardians, and ask for the dispatch of police to prevent the crime at the initial stage. The RFID module of criminals' electronic bracelets is RFID TAG, and the RFID module for the children is RFID receiver(reader), so wherever the offenders are, if an offender is at a place within 20m from a child, RFID module for children will transmit the situation every certain periods to the control center by the automatic response of the receiver. As for the positioning module, outdoors GPS or mobile communications module(CELL module)is used and UWB, WI-FI based module is used indoors. The sensor is set under the purpose of making it possible to measure the position coordinates even indoors, so that one could send his real time situation and position to the server of central control center. By using the RFID electronic roll book system of educational institutions and safety system installed at home, children's position and situation can be checked. When the child leaves for school, attendance can be checked through the electronic roll book, and when school is over the information is sent to the guardians. And using RFID access control turnstiles installed at the apartment or entrance of the house, the arrival of the children could be checked and the information is transmitted to the guardians. If the student is absent or didn't arrive at home, the information of the child is sent to the central control center from the electronic roll book or access control turnstiles, and look for the position of the child's electronic bracelet using GPS or mobile communications module, then send the information to the guardians and teacher so that they could report to the police immediately if necessary. Central management and control system is built under the purpose of monitoring dangerous situations and guardians' checking. It saves the warning and pattern data to figure out the areas with dangerous situation, and could help introduce crime prevention systems like CCTV with the highest priority. And by DB establishment personal data could be saved, the frequency of first and second warnings made, the terminal ID of the specific child and offender, warning made position, situation (like approaching, taken off of the electronic bracelet, same position for a certain time) and so on could be recorded, and the data is going to be used for preventing crimes. Even though we've already introduced electronic tagging to prevent recurrence of child sexual offences, but the crimes continuously occur. So I suggest this system to prevent crimes beforehand concerning the children's safety. If we make electronic bracelets easy to use and carry, and set the price reasonably so that many children can use, then lots of criminals could be prevented and we can protect the children easily. By preventing criminals before happening, it is going to be a helpful system for our safe life.

Human face recognition is distinguished by a method of identifying facts or confirmation that tests personality. The technique essentially relies on two stages, one is face identification, and another is face recognition. Facial recognition applies to a PC device with a few implementations in which human faces can be identified in pictures. Usually, facial identification is achieved by using “right” data from full-frontal facial photographs. Although there are a variety of situations in which full frontal faces are not visible, blemished faces captured by CCTV cameras are an excellent demonstration. Subsequently, the use of fractional facial data as tests is still, to a large extent, an unexplored field of research on the PC-based face recognition problem. In this research, through using incomplete facial evidence to concentrate on face recognition. By implementing critical analysis to evaluate the presentation of AI using the Haar Cascade Classifier is proposed and used to build our framework. There are three phases of the proposed face detection method such as the face data gathering (FDG) process, train the stored image (TSI) phase, face recognition using the local (FRUL) binary patterns histograms (LBPH) algorithm, and this classifier computation was tested by splitting it into four phases. In this analysis, Haar feature selection is applied to complete the detection phase, and also to generate an integral image, Adaboost preparing, Cascading Classifiers. To complete this venture's human protection facial recognition framework with face detection, local binary patterns histograms (LBPH) is used to estimate the model. In LBPH, a few parameters are used and a dataset is obtained by implementing an algorithm. By adding the LBPH operation and extracting the histograms, I got the Final computational part. “Image Processing Based Human Face Recognition Using Haar Cascade Classifier” Image Processing-Based Human Face Recognition Using Haar Cascade Classifier.KeywordsImage processingFace recognitionHuman faceCascade classifier

In order to improve the accuracy rate of person re-identification, a pedestrian attribute hierarchy recognition neural network is proposed based on attention model. Compared with the existing algorithms, the model has the following three advantages. Firstly, the attention model is used in this paper to identify the pedestrian attributes, and to extract of pedestrian attribute information and degree of significance. Secondly, the attention model in used in this paper to classify the attributes according to the significance of the pedestrian attributes and the amount of informationcontained. Thirdly, this paper analyzes the correlation between attributes, and adjusts the next level identification strategy according to the recognition results of the upper level. It can improve the recognition accuracy of small target attributes, and the accuracy of pedestrian recognition is improved. The experimental results show that the proposed model can effectively improve the first accuracy rate (rank-1) of person re-identification compared with the existing methods. On the Market1501 dataset, the first accuracy rate is 93.1%, and the first accuracy rate is 81.7% on the DukeMTMC dataset.

Illumination, for pedestrian detection at nighttime is weak, and detection is easily affected through variations in illumination. Thus, a bicharacteristic method of pedestrian detection at nighttime based on hierarchical tree cascade classification is presented according to “coarse-to-fine” principle. The proposed method consists of two stages of cascade classifiers. Coarse cascade classifiers are constructed in complete binary tree architecture. These classifiers use Haar-like features for the rapid identification of candidate pedestrian areas. By contrast, fine cascade classifiers have a parallel structure. Edgelet features are used for detection along three parts: the head-shoulder, trunk, and leg parts of candidate pedestrian areas. Bayesian decision-making is adopted to achieve pedestrian target detection and a comprehensive analysis of the detection results from these three parts. Experiments show that the proposed method has high accuracy, ideal real-time performance, and strong reliability...