摘要 :
Pedestrian and bicyclist travel behaviors are important for planning, designing and management of
non-motorized transportation facilities. Traffic parameters such as walking speed and acceleration are
important variables for analy...
展开
Pedestrian and bicyclist travel behaviors are important for planning, designing and management of
non-motorized transportation facilities. Traffic parameters such as walking speed and acceleration are
important variables for analyzing pedestrian and bicyclist travel behaviors. Manually counting such data
is labor intensive and expensive. To better use the existing surveillance infrastructure, we propose a
computer vision based approach using ordinary video cameras for extraction of pedestrian parameters.
Moving objects are extracted by Gaussian Mixture Model, and tracked by Kalman Filter. To identify
pedestrians and bicycles, Back Propagation Neural Network is employed. Direct Linear Transformation
based camera calibrating algorithm is utilized to transform the coordinate in image to real world, which is
the basis of statistical analyses. The presented approach is implemented in pedestrian and bicyclist
tracking and classification (PBTC) system. Real world videos were used to test the performance of this
system, and the results show that about 85% of pedestrians were successfully detected and several traffic
parameters were extracted. Although the system is still in experimental stage and needs to be further
improved, it has proven its potential usage in traffic engineering practice and research as automated
pedestrian data collection tool.
收起
摘要 :
Pedestrian and bicyclist travel behaviors are important for planning, designing and management of
non-motorized transportation facilities. Traffic parameters such as walking speed and acceleration are
important variables for ana...
展开
Pedestrian and bicyclist travel behaviors are important for planning, designing and management of
non-motorized transportation facilities. Traffic parameters such as walking speed and acceleration are
important variables for analyzing pedestrian and bicyclist travel behaviors. Manually counting such data
is labor intensive and expensive. To better use the existing surveillance infrastructure, we propose a
computer vision based approach using ordinary video cameras for extraction of pedestrian parameters.
Moving objects are extracted by Gaussian Mixture Model, and tracked by Kalman Filter. To identify
pedestrians and bicycles, Back Propagation Neural Network is employed. Direct Linear Transformation
based camera calibrating algorithm is utilized to transform the coordinate in image to real world, which is
the basis of statistical analyses. The presented approach is implemented in pedestrian and bicyclist
tracking and classification (PBTC) system. Real world videos were used to test the performance of this
system, and the results show that about 85% of pedestrians were successfully detected and several traffic
parameters were extracted. Although the system is still in experimental stage and needs to be further
improved, it has proven its potential usage in traffic engineering practice and research as automated
pedestrian data collection tool.
收起
摘要 :
Currently, computational fluid dynamics (CFD) simulation of intermittently separating 3D flows remain too expensive for general use at practical Reynolds numbers. Low-order methods including inviscid and phenomeno-logical models a...
展开
Currently, computational fluid dynamics (CFD) simulation of intermittently separating 3D flows remain too expensive for general use at practical Reynolds numbers. Low-order methods including inviscid and phenomeno-logical models are current used to model these flows in the study of dynamic responses, however there have not been comprehensive assessments and comparison of their accuracy when applied to such settings. We present a review and comparison between various low-order simulation regimes for intermittently separated flows on flexible lifting surfaces. The dynamic fluid-structure coupling response is demonstrated with test cases involving limit-cycle oscillation (LCO) simulations on low-aspect-ratio -wings. We notice that long-range spanwise interactions on lifting surfaces has an as important, if not more significant, effect on the LCO result than the choice of aerodynamic model. We also propose a post-processing technique to recover these long-range spanwise interactions without modifying the basic 2D solution process.
收起
摘要 :
Requirement volatility is a common and inevitable project risk which has severe consequences on software projects. When requirement change occurs, a project manager wants to analyze its impact so as to better cope with it. As the ...
展开
Requirement volatility is a common and inevitable project risk which has severe consequences on software projects. When requirement change occurs, a project manager wants to analyze its impact so as to better cope with it. As the modification to one requirement can cause changes in its dependent requirements and its dependency relationship, the impact analysis can be very complex. This paper proposes a simulation approach DepRVSim (Requirement Volatility Simulation considering Dependency relationship) to assessing this sort of impact. We abstract the general patterns of the influence mechanism, which may trigger modification in its dependency relationship and bring changes in other requirements through dependency. DepRVSim can generate such information as the probability distribution of effort deviation and schedule deviation. As a proof-of-concept, the applicability of DepRVSim is demonstrated with an illustrative case study of a real software project. Results indicate that DepRVSim is able to provide experimental evidence for decision making when requirement changes.
收起
摘要 :
Requirement volatility is a common and inevitable project risk which has severe consequences on software projects. When requirement change occurs, a project manager wants to analyze its impact so as to better cope with it. As the ...
展开
Requirement volatility is a common and inevitable project risk which has severe consequences on software projects. When requirement change occurs, a project manager wants to analyze its impact so as to better cope with it. As the modification to one requirement can cause changes in its dependent requirements and its dependency relationship, the impact analysis can be very complex. This paper proposes a simulation approach DepRVSim (Requirement Volatility Simulation considering Dependency relationship) to assessing this sort of impact. We abstract the general patterns of the influence mechanism, which may trigger modification in its dependency relationship and bring changes in other requirements through dependency. DepRVSim can generate such information as the probability distribution of effort deviation and schedule deviation. As a proof-of-concept, the applicability of DepRVSim is demonstrated with an illustrative case study of a real software project. Results indicate that DepRVSim is able to provide experimental evidence for decision making when requirement changes.
收起
摘要 :
Many railway accidents happen under shunting mode. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver to avoid danger. However, hum...
展开
Many railway accidents happen under shunting mode. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver to avoid danger. However, human error and fatigue will reduce the safety of shunting operation. To address this issue, a novel object detection framework for a train automatic detecting objects ahead in shunting mode, called Feature Fusion detection neural network (FFDet). It consists of two connected modules, i.e., the refine detection module and the object detection module. The refine detection module coarsely the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results show that FFDet demonstrates good performance in detecting objects and can meet the needs of practical application in shunting mode.
收起
摘要 :
Many railway accidents happen under shunting mode. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver to avoid danger. However, hum...
展开
Many railway accidents happen under shunting mode. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver to avoid danger. However, human error and fatigue will reduce the safety of shunting operation. To address this issue, a novel object detection framework for a train automatic detecting objects ahead in shunting mode, called Feature Fusion detection neural network (FFDet). It consists of two connected modules, i.e., the refine detection module and the object detection module. The refine detection module coarsely the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results show that FFDet demonstrates good performance in detecting objects and can meet the needs of practical application in shunting mode.
收起
摘要 :
Pedestrians are the most essential and important component of traffic systems. The pedestrian injury and fatality rates are at a high level due to the severe traffic crashes. Therefore, effective strategies should be implemented t...
展开
Pedestrians are the most essential and important component of traffic systems. The pedestrian injury and fatality rates are at a high level due to the severe traffic crashes. Therefore, effective strategies should be implemented to enhance pedestrian safety. However, there is a lack of feasible methods to collect pedestrian data for pedestrian safety study. And the effectiveness of the existing methods may decrease along with the increasing complexity of the traffic system. To ensure pedestrian safety even in crowded scenes, a head-based pedestrian detection and counting method is proposed in this paper to capture the data of pedestrians. From the test results, several important attributes such as crowd density, location, and speed can be obtained. Instead of collecting the full bodies of pedestrians, human heads are used in our study to avoid the occlusion problem happened in crowded scenes. After setting the detection region, head detection is started by applying mixed color algorithm to locate candidate head area and then using Canny algorithm and Hough transform to extract target contour and locate head precisely. Finally, the minimum distance method is utilized to match and count the effective heads. The detection results compared with manual count indicate its extremely accurate performance. This method demonstrates the proposed approach which is useful and effective for crowded pedestrian detection and counting, and can be applied in real-world traffic system to detect pedestrians and prevent pedestrian accidents.
收起
摘要 :
Pedestrians are the most essential and important component of traffic systems. The pedestrian injury and fatality rates are at a high level due to the severe traffic crashes. Therefore, effective strategies should be implemented t...
展开
Pedestrians are the most essential and important component of traffic systems. The pedestrian injury and fatality rates are at a high level due to the severe traffic crashes. Therefore, effective strategies should be implemented to enhance pedestrian safety. However, there is a lack of feasible methods to collect pedestrian data for pedestrian safety study. And the effectiveness of the existing methods may decrease along with the increasing complexity of the traffic system. To ensure pedestrian safety even in crowded scenes, a head-based pedestrian detection and counting method is proposed in this paper to capture the data of pedestrians. From the test results, several important attributes such as crowd density, location, and speed can be obtained. Instead of collecting the full bodies of pedestrians, human heads are used in our study to avoid the occlusion problem happened in crowded scenes. After setting the detection region, head detection is started by applying mixed color algorithm to locate candidate head area and then using Canny algorithm and Hough transform to extract target contour and locate head precisely. Finally, the minimum distance method is utilized to match and count the effective heads. The detection results compared with manual count indicate its extremely accurate performance. This method demonstrates the proposed approach which is useful and effective for crowded pedestrian detection and counting, and can be applied in real-world traffic system to detect pedestrians and prevent pedestrian accidents.
收起
摘要 :
Currently, Mobile Edge Computing (MEC) is widely used in different smart application scenarios such as smart health, smart traffic and smart home. However, smart end devices are usually constrained in battery and computing power, ...
展开
Currently, Mobile Edge Computing (MEC) is widely used in different smart application scenarios such as smart health, smart traffic and smart home. However, smart end devices are usually constrained in battery and computing power, and hence how to optimize the energy consumption of end devices with intelligent task offloading and scheduling strategies under constraints such as deadlines is a critical yet challenging topic. Meanwhile, most existing studies do not consider the mobility of end devices during task execution but in reality end devices may need to be constantly moving in a MEC environment. In this paper, motivated by a patient health monitoring scenario, we propose a Mobility-Aware Workflow Offloading and Scheduling Strategy (MAWOSS) for MEC which provides a holistic approach that covers the workflow task offloading strategy, the workflow task scheduling algorithm and the workflow task migration strategy. Comprehensive experimental results show that compared with others, MAWOSS is able to achieve the optimal fitness with lower energy consumption and smaller workflow makespan under the deadlines.
收起