视频监控中运动物体的检测与跟踪

针对固定摄像头下的交通监控场景,首先给出一种基于分块原理的背景重建算法,克服了平均法重建的背景图像模糊的缺点。然后用减背景方法检测运动物体,并利用数学形态学方法对得到原始前景点作处理,填补了运动物体内部的空洞,减少了噪声点,改善了检测性能。为适应背景的变化,对背景进行自适应更新,并且通过对Meanshift算法的改进提高了跟踪的准确性。实验结果表明,算法在有效检测到运动物体的同时能够快速准确地跟踪运动物体。     

Development of head detection and tracking systems for visual surveillance

This paper proposes a technique for the detection of head nod and shake gestures based on eye tracking and head motion decision. The eye tracking step is divided into face detection and eye location. Here, we apply a motion segmentation algorithm that examines differences in moving people’s faces. This system utilizes a Hidden Markov Model-based head detection module that carries out complete detection in the input images, followed by the eye tracking module that refines the search based on a candidate list provided by the preprocessing module. The novelty of this paper is derived from differences in real-time input images, preprocessing to remove noises (morphological operators and so on), detecting edge lines and restoration, finding the face area, and cutting the head candidate. Moreover, we adopt a K-means algorithm for finding the head region. Real-time eye tracking extracts the location of eyes from the detected face region and is performed at close to a pair of eyes. After eye tracking, the coordinates of the detected eyes are transformed into a normalized vector of x-coordinate and y-coordinate. Head nod and shake detector uses three hidden Markov models (HMMs). HMM representation of the head detection can estimate the underlying HMM states from a sequence of face images. Head nod and shake can be detected by three HMMs that are adapted by a directional vector. The directional vector represents the direction of the head movement. The vector is HMMs for determining neutral as well as head nod and shake. These techniques are implemented on images, and notable success is notified.     

Adaptive compressive sensing for target tracking within wireless visual sensor networks-based surveillance applications

Wireless Visual Sensor Networks (WVSNs) have gained significant importance in the last few years and have emerged in several distinctive applications. The main aim is to design low power WVSN surveillance application using adaptive Compressive Sensing (CS) which is expected to overcome the WVSN resource constraints such as memory limitation, communication bandwidth and battery constraints. In this paper, an adaptive block CS technique is proposed and implemented to represent the high volume of captured images in a way for energy efficient wireless transmission and minimum storage. Furthermore, to achieve energy-efficient target detection and tracking with high detection reliability and robust tracking, to maximize the lifetime of sensor nodes as they can be left for months without any human interactions. Adaptive CS is expected to dynamically achieve higher compression rates depending on the sparsity nature of different datasets, while only compressing relative blocks in the image that contain the target to be tracked instead of compressing the whole image. Hence, saving power and increasing compression rates. Least mean square adaptive filter is used to predicts target’s next location to investigate the effect of CS on the tracking performance. The tracking is achieved in both indoor and outdoor environments for single/multi targets. Results have shown that with adaptive block CS up to 20 % measurements of data are required to be transmitted while preserving the required performance for target detection and tracking.     

Multi-human tracking using part-based appearance modelling and grouping-based tracklet association for visual surveillance applications

Multimedia Tools and Applications - Although much progress has been made in multi-object tracking in recent decades due to its variety of applications including visual surveillance, traffic...     

Action categorization by structural probabilistic latent semantic analysis

Temporal dependency is a very important cue for modeling human actions. However, approaches using latent topics models, e.g., probabilistic latent semantic analysis (pLSA), employ the bag of words assumption therefore word dependencies are usually ignored. In this work, we propose a new approach structural pLSA (SpLSA) to model explicitly word orders by introducing latent variables. More specifically, we develop an action categorization approach that learns action representations as the distribution of latent topics in an unsupervised way, where each action frame is characterized by a codebook representation of local shape context. The effectiveness of this approach is evaluated using both the WEIZMANN dataset and the MIT dataset. Results show that the proposed approach outperforms the standard pLSA. Additionally, our approach is compared favorably with six existing models including GMM, logistic regression, HMM, SVM, CRF, and HCRF given the same feature representation. These comparative results show that our approach achieves higher categorization accuracy than the five existing models and is comparable to the state-of-the-art hidden conditional random field based model using the same feature set.     

Quantitative cross impact analysis with latent semantic indexing

Cross impact analysis (CIA) consists of a set of related methodologies that predict the occurrence probability of a specific event and that also predict the conditional probability of a first event given a second event. The conditional probability can be interpreted as the impact of the second event on the first. Most of the CIA methodologies are qualitative that means the occurrence and conditional probabilities are calculated based on estimations of human experts. In recent years, an increased number of quantitative methodologies can be seen that use a large number of data from databases and the internet. Nearly 80% of all data available in the internet are textual information and thus, knowledge structure based approaches on textual information for calculating the conditional probabilities are proposed in literature. In contrast to related methodologies, this work proposes a new quantitative CIA methodology to predict the conditional probability based on the semantic structure of given textual information. Latent semantic indexing is used to identify the hidden semantic patterns standing behind an event and to calculate the impact of the patterns on other semantic textual patterns representing a different event. This enables to calculate the conditional probabilities semantically. A case study shows that this semantic approach can be used to predict the conditional probability of a technology on a different technology.     

Spatial and semantic convolutional features for robust visual object tracking

Multimedia Tools and Applications - Robust and accurate visual tracking is a challenging problem in computer vision. In this paper, we exploit spatial and semantic convolutional features extracted...     

Prior-based probabilistic latent semantic analysis for multimedia retrieval

Multimedia Tools and Applications - Topic models have shown to be one of the most effective tools in Content-Based Multimedia Retrieval (CBMR). However, the high computational learning cost...     

Motion anomaly detection and trajectory analysis in visual surveillance

Motion anomaly detection through video analysis is important for delivering autonomous situation awareness in public places. Surveillance scene segmentation and representation is the preliminary step to implementation anomaly detection. Surveillance scene can be represented using Region Association Graph (RAG), where nodes represent regions and edges denote connectivity among the regions. Existing RAG-based analysis algorithms assume simple anomalies such as moving objects visit statistically unimportant or abandoned regions. However, complex anomalies such as an object encircles within a particular region (Type-I) or within a set of regions (Type-II). In this paper, we extract statistical features from a given set of object trajectories and train multi-class support vector machines (SVM) to deal with each type of anomaly. In the testing phase, a given test trajectory is categorized as normal or anomalous with respect to the trained models. Performance evaluation of the proposed algorithm has been carried out on public as well as our own datasets. We have recorded sensitivity as high as 86% and fall-out rate as low as 9% in experimental evaluation of the proposed technique. We have carried out comparative analysis with state-of-the-art techniques to benchmark the method. It has been observed that the proposed model is consistent and highly accurate across challenging datasets.     

一种用于智能监控的目标检测和跟踪方法

在对现有目标检测、跟踪算法进行分析对比的基础上,设计并实现了一种简单有效的目标检测和跟踪方案。首先提出了一种基于像素灰度归类和单模态高斯模型的背景重构算法,能够利用多帧包含前景目标的场景图像重构准确的背景模型。进而以此为基础采用背景减法进行各帧中目标的检测,并选取形心作为匹配特征实现了场景中多个目标的有效跟踪。实验表明,该方法实现简单,无须事先提供背景图像即可实现目标的准确检测和跟踪,其性能明显优于传统基于时间平均背景模型的方法。     

Moving object detection using region tracking

For many vision-based systems, it is important to detect a moving object automatically. The region-based motion estimation method is popular for automatic moving object detection. The region-based method has several advantages in that it is robust to noise and variations in illumination. However, there is a critical problem in that there exists an occlusion problem which is caused by the movement of the object. The occlusion problem results in an incorrect motion estimation and faulty detection of moving objects. When there are occlusion regions, the motion vector is not correctly estimated. That is, a stationary background in the occluded region can be classified as a moving object.In order to overcome this occlusion problem, a new occlusion detection algorithm is proposed. The proposed occlusion detection algorithm is motivated by the assumption that the distribution of the error histogram of the occlusion region is different from that of the nonocclusion region. The proposed algorithm uses the mean and variance values to decide whether an occlusion has occurred in the region. Therefore, the proposed occlusion detection and motion estimation scheme detects the moving regions and estimates the new motion vector, while avoiding misdetection caused by the occlusion problem. The experimental results for several video sequences demonstrate the robustness of the proposed approach to the occlusion problem.This work was presented in part at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24–26, 2003     

Online belief propagation algorithm for probabilistic latent semantic analysis

Probabilistic latent semantic analysis (PLSA) is a topic model for text documents, which has been widely used in text mining, computer vision, computational biology and so on. For batch PLSA inference algorithms, the required memory size grows linearly with the data size, and handling massive data streams is very difficult. To process big data streams, we propose an online belief propagation (OBP) algorithm based on the improved factor graph representation for PLSA. The factor graph of PLSA facilitates the classic belief propagation (BP) algorithm. Furthermore, OBP splits the data stream into a set of small segments, and uses the estimated parameters of previous segments to calculate the gradient descent of the current segment. Because OBP removes each segment from memory after processing, it is memory-efficient for big data streams. We examine the performance of OBP on four document data sets, and demonstrate that OBP is competitive in both speed and accuracy for online expectation maximization (OEM) in PLSA, and can also give a more accurate topic evolution. Experiments on massive data streams from Baidu further confirm the effectiveness of the OBP algorithm.     

基于隐含语义分析的音乐检索

为提高音乐检索效率,使检索结果与搜索目的更接近,提出了基于隐含语义分析的音乐检索方法.将曲谱表示为标准音符和音转的交替串,基于每个交替串使用频率高于包含它的多交替串排列的事实,设计了音乐词汇统计算法.为使各分句能整齐地转化为相同维数的向量,使用最长的分句长度作为标准维数,基于增加频率和的原则进行单词的重新分割.实验结果表明,基于隐含语义分析的检索能获得令人满意的检索结果.     

Automatic text summarization using latent semantic analysis

In the paper, the most state-of-the-art methods of automatic text summarization, which build summaries in the form of generic extracts, are considered. The original text is represented in the form of a numerical matrix. Matrix columns correspond to text sentences, and each sentence is represented in the form of a vector in the term space. Further, latent semantic analysis is applied to the matrix obtained to construct sentences representation in the topic space. The dimensionality of the topic space is much less than the dimensionality of the initial term space. The choice of the most important sentences is carried out on the basis of sentences representation in the topic space. The number of important sentences is defined by the length of the demanded summary. This paper also presents a new generic text summarization method that uses nonnegative matrix factorization to estimate sentence relevance. Proposed sentence relevance estimation is based on normalization of topic space and further weighting of each topic using sentences representation in topic space. The proposed method shows better summarization quality and performance than state-of-the-art methods on the DUC 2001 and DUC 2002 standard data sets.     

Space-variant motion detection for active visual target tracking

A biologically inspired approach to active visual target tracking is presented. The approach makes use of three strategies found in biological systems: space-variant sensing, a spatio-temporal-frequency-based model of motion detection and the alignment of sensory-motor maps. Space-variant imaging is used to create a 1D array of elementary motion detectors (EMDs) that are tuned in such a way as to make it possible to detect motion over a wide range of velocities while still being able to detect motion precisely. The array is incorporated into an active visual tracking system. A method of analysis and design for such a tracking system is proposed. It makes use of a sensory-motor map which consists of a phase-plane plot of the continuous-time dynamics of the tracking system overlaid onto a map of the detection capabilities of the array of EMDs. This sensory-motor map is used to design a simple 1D tracking system and several simulations show how the method can be used to control tracking performance using such metrics as overshoot and settling time. A complete 1D active vision system is implemented and a set of simple target tracking experiments are performed to demonstrate the effectiveness of the approach.     

用于UAV视觉导航的跑道检测与跟踪

跑道检测与跟踪是UAV视觉导航研究的重点内容.针对UAV着陆过程中跑道变化情况,提出一种新的方法,利用单目视觉信息,基于距离跑道的远近不同采用不同的策略实现跑道检测与跟踪,帮助UAV自主降落在安全区域.当距离较远时,利用地平线检测和模板匹配的方法对跑道进行定位;结合模板更新策略实现跑道跟踪;当距离较近时,在融合远距离跑道方位信息的基础上利用改进型Canny算子和Hough变换对跑道边缘进行更精确的描述.实验结果表明,利用该方法可以有效地对跑道进行检测和跟踪,并且具有较快的处理速度.     

Bayesian tracking fusion framework with online classifier ensemble for immersive visual applications

During the last decade, the development of the immersive virtual reality (VR) has achieved a great progress in different application areas. For more advanced large-scale immersive VR environments or systems, one of the most challenge is to accurately track the position of the user’s body part such as head when he/she is immersived in the environment to feel the changes among the synthetic stereoscopic image sequences. Unfortunately, accurate tracking is not easy in the virtual reality scenarios due to the variety types of existing intrinsic and extrinsic changes when tracking is on-the-fly. Especially for the single tracker, a long time accurate tracking is usually not possible because of the model adaption problem in different environments. Recent trend of research in tracking is to incorporate multiple trackers into a compositive learning framework and utilize the advantages of different trackers for more effective tracking. Therefore, in this paper, we propose a novel Bayesian tracking fusion framework with online classifier ensemble strategy. The proposed tracking formulates a fusion framework for online learning of multiple trackers by modeling a cumulative loss minimization process. With an optimal pair-wise sampling scheme for the SVM classifier, the proposed fusion framework can achieve more accurate tracking performance when compared with the other state-of-art trackers. In addition, the experiments on the standard benchmark database also verify that the proposed tracking is able to handle the challenges in many immersive VR applications and environments.