Xingzhe Xie

Human Mobility Monitoring in Very Low Resolution Visual Sensor Network

This paper proposes an automated system for monitoring mobility patterns using a network of very low resolution visual sensors (30 × 30 pixels). The use of very low resolution sensors reduces privacy concern, cost, computation requirement and power consumption. The core of our proposed system is a robust people tracker that uses low resolution videos provided by the visual sensor network. The distributed processing architecture of our tracking system allows all image processing tasks to be done on the digital signal controller in each visual sensor. In this paper, we experimentally show that reliable tracking of people is possible using very low resolution imagery. We also compare the performance of our tracker against a state-of-the-art tracking method and show that our method outperforms. Moreover, the mobility statistics of tracks such as total distance traveled and average speed derived from trajectories are compared with those derived from ground truth given by Ultra-Wide Band sensors. The results of this comparison show that the trajectories from our system are accurate enough to obtain useful mobility statistics.

Detecting Road Intersections from GPS Traces Using Longest Common Subsequence Algorithm

Intersections are important components of road networks, which are critical to both route planning and path optimization. Most existing methods define the intersections as locations where the road users change their moving directions and identify the intersections from GPS traces through analyzing the road users’ turning behaviors. However, these methods suffer from finding an appropriate threshold for the moving direction change, leading to true intersections being undetected or spurious intersections being falsely detected. In this paper, the intersections are defined as locations that connect three or more road segments in different directions. We propose to detect the intersections under this definition by finding the common sub-tracks of the GPS traces. We first detect the Longest Common Subsequences (LCSS) between each pair of GPS traces using the dynamic programming approach. Second, we partition the longest nonconsecutive subsequences into consecutive sub-tracks. The starting and ending points of the common sub-tracks are collected as connecting points. At last, intersections are detected from the connecting points through Kernel Density Estimation (KDE). Experimental results show that our proposed method outperforms the turning point-based methods in terms of the F-score.

Inferring Directed Road Networks from GPS Traces by Track Alignment

This paper proposes a method to infer road networks from GPS traces. These networks include intersections between roads, the connectivity between the intersections and the possible traffic directions between directly-connected intersections. These intersections are localized by detecting and clustering turning points, which are locations where the moving direction changes on GPS traces. We infer the structure of road networks by segmenting all of the GPS traces to identify these intersections. We can then form both a connectivity matrix of the intersections and a small representative GPS track for each road segment. The road segment between each pair of directly-connected intersections is represented using a series of geographical locations, which are averaged from all of the tracks on this road segment by aligning them using the dynamic time warping (DTW) algorithm. Our contribution is two-fold. First, we detect potential intersections by clustering the turning points on the GPS traces. Second, we infer the geometry of the road segments between intersections by aligning GPS tracks point by point using a “stretch and then compress” strategy based on the DTW algorithm. This approach not only allows road estimation by averaging the aligned tracks, but also a deeper statistical analysis based on the individual track’s time alignment, for example the variance of speed along a road segment.

PhD Forum: Analyzing Behaviors Patterns of the Elderly from Low-precision Trajectories

Behavior analysis plays an important role in the field of Smart Homes (SH). In this work, we present to analyze the behavior patterns of the elderly person using statistical features extracted from the tracking results of a very low-resolution camera system. Firstly, the low-precision tracking results are prepossessed to remove the bad tracks, which do not fit the walking speed of human beings. The good tracks are classified into walking tracks and staying tracks according to the position variance of their tracking points. Secondly, the statistical features, such as the time of getting up and going to bed, the walking distance over a day, and the number of tracks detected at specific area, are extracted as the description of the behaviors at each day. At last, these features are clustered into different behaviors patterns using a Random Sample Consensus (RANSAC)-principle method. The initial results demonstrates that our method is able to detect the behavior patterns.

Average Track Estimation of Moving Objects Using RANSAC and DTW

This paper proposes a method for clustering and averaging the tracks of people obtained in a multi-camera network using Dynamic Time Warping (DTW) and Random Sampling (RANSAC). The method allows analyzing trajectories of factory workers in order to estimate average work cycles, variances on the work cycle and outlier trajectories. The main application is to provide information on problematic parts of work cycles, and on how to optimize the work cycles. The main novelty of the methods is track clustering based on a combination of DTW and RANSAC, with time alignment of tracks as byproduct. The experimental results show that our algorithm outperforms other methods on averaging the tracks, specifically that the spacial structure is kept even part of tracks differentiates from each other. Also it allows a deeper statistical analysis using the time alignment, i.e. time variability analysis of the arrival time for a specific location.

A Review of Urban Air Pollution Monitoring and Exposure Assessment Methods

The impact of urban air pollution on the environments and human health has drawn increasing concerns from researchers, policymakers and citizens. To reduce the negative health impact, it is of great importance to measure the air pollution at high spatial resolution in a timely manner. Traditionally, air pollution is measured using dedicated instruments at fixed monitoring stations, which are placed sparsely in urban areas. With the development of low-cost micro-scale sensing technology in the last decade, portable sensing devices installed on mobile campaigns have been increasingly used for air pollution monitoring, especially for traffic-related pollution monitoring. In the past, some reviews have been done about air pollution exposure models using monitoring data obtained from fixed stations, but no review about mobile sensing for air pollution has been undertaken. This article is a comprehensive review of the recent development in air pollution monitoring, including both the pollution data acquisition and the pollution assessment methods. Unlike the existing reviews on air pollution assessment, this paper not only introduces the models that researchers applied on the data collected from stationary stations, but also presents the efforts of applying these models on the mobile sensing data and discusses the future research of fusing the stationary and mobile sensing data.

Obstacle Detection for Patrol Robot Using Bumblebee2 Stereo Vision System

This paper employs Bumblebee2 stereo vision system to detect the obstacles for patrol robot in substation environment. Firstly, with the selected points in the disparity image, the ground plane is calculated by the RANSAC (Random Sample Consensus) algorithm. And then, the local occupancy grid map is built for patrol robot, and the obstacles are detected through connected component analysis method. The actual test in substation environment verified the reliability of the system.

Road Intersection Detection through Finding Common Sub-Tracks between Pairwise GNSS Traces

This paper proposes a novel approach to detect road intersections from GNSS traces. Different from the existing methods of detecting intersections directly from the road users’ turning behaviors, the proposed method detects intersections indirectly from common sub-tracks shared by different traces. We first compute the local distance matrix for each pair of traces. Second, we apply image processing techniques to find all “sub-paths” in the matrix, which represents good alignment between local common sub-tracks. Lastly, we identify the intersections from the endpoints of the common sub-tracks through Kernel Density Estimation (KDE). Experimental results show that the proposed method outperforms the traditional turning point-based methods in terms of the F-score, and our previous connecting point-based method in terms of computational efficiency.

Abnormal work cycle detection based on dissimilarity measurement of trajectories

This paper proposes a method for detecting the abnormalities of the executed work cycles for the factory workers using their tracks obtained in a multi-camera network. The method allows analyzing both spatial and temporal dissimilarity between the pairwise tracks. The main novelty of the methods is calculating spatial dissimilarity between pair-wise tracks by aligning them using Dynamic Time Warping (DTW) based on coordinate distance, and specially the velocity and dwell time dissimilarity using a different track alignment based on velocity difference. These dissimilarity measurements are used to cluster the executed work cycles and detect abnormalities. The experimental results show that our algorithm outperforms other methods on clustering the tracks because of the use of temporal dissimilarity.