Objective: Pedestrian safety is considered as one of the greatest concerns, especially for developing countries. In the year of 2015, about 48% pedestrian accidents with 56% fatalities occurred at mid-blocks in Beijin...Objective: Pedestrian safety is considered as one of the greatest concerns, especially for developing countries. In the year of 2015, about 48% pedestrian accidents with 56% fatalities occurred at mid-blocks in Beijing. Since the high frequency and fatality risk, this study focused on pedestrian accidents taking place at mid-blocks and aimed at identifying significant factors. Methods: Based on total 10,948 crash records, a binary logit model was established to explore the impact of various factors on the probability of pedestrian’s death. Furthermore, first-degree interaction effects were introduced into the basic model. The Hosmer-Lemeshow goodness-of-fit test was used to assess the model performance. Odds ratio was calculated for categorical variables to compare significant accident conditions with the conference level. Variables within consideration in this study included weather, area type, road type, speed limit, pedestrian location, lighting condition, vehicle type, pedestrian gender and pedestrian age. Results: The calibration results of the model show that the increased fatality chances of an accident at mid-blocks are associated with normal weather, rural area, two-way divided road, crossing elsewhere in carriageway, darkness (especially for no street lighting), light vehicle, large vehicle and male pedestrian. With road speed limit increasing by 10 km/h, the probability of death accordingly increases by 46%. Older victims have higher chances of being killed in a crash. Moreover, three interaction effects are found significant: rural area and two-way divided, rural area and crossing elsewhere as well as speed limit and pedestrian age. Conclusions: This study has analyzed police accident data and identified factors significant to the death probability of pedestrians in accidents occurred at mid-blocks. Recommendations and improving measures were proposed correspondingly. Behaviors of different road users at mid-blocks should be taken into account in the future research.展开更多
Pedestrians usually cross the road at mid-block locations in India because of the ease and convenience to reach their destination as compared to intersection locations. It is important to evaluate the pedestrian gap a...Pedestrians usually cross the road at mid-block locations in India because of the ease and convenience to reach their destination as compared to intersection locations. It is important to evaluate the pedestrian gap acceptance behavior at mid-block locations because of inadequate vehicular gaps un- der mixed traffic condition, which translates into the pedestrian road crossing behavior. The present study examines the pedestrian gap acceptance behaviour by employing an artificial neural network （ANN） model for understanding the decision making process of pedestrians, i. e. , acceptance or rejec- tion of vehicular gaps at a mid-block location. From the results it has been found that the pedestrian rolling gap, frequency of attempt, vehicular gap size, pedestrian speed change condition and vehicle speed have major role in pedestrian gap acceptance. These results can lead to a better design of pedestrian crossing facilities where adequate gaps are not available in vehicular flow at mid-block crosswalk locations.展开更多
The pedestrian crossing speed is one of the important factors in pedestrian crossing facility design.Research studies have shown that the pedestrian crossing speed is influenced by availability of green time at signal...The pedestrian crossing speed is one of the important factors in pedestrian crossing facility design.Research studies have shown that the pedestrian crossing speed is influenced by availability of green time at signalized crosswalks and pedestrian characteristics such as gender and age.However,the effects of vehicular time gap and additional pedestrian behavioural characteristics on pedestrian crossing speed patterns have not been examined at unprotected(un-signalized)mid-block crosswalks.The present study examines the pedestrian crossing speed change patterns considering the effect of vehicular time gap and pedestrian behavioural characteristics such as rolling behaviour,path change,etc.,at selected unprotected mid-block crosswalk locations under mixed traffic conditions in India.Video graphic survey has been conducted at eight selected unprotected mid-block crosswalk locations in Mumbai City for two to three hours duration during normal weather conditions.The data was mined using AVS video editor software,and the extracted data includes pedestrian speed,pedestrian characteristics(gender and age),pedestrian behaviour(rolling behaviour,path change,etc.),vehicle characteristics(type and speed of the vehicle)and traffic characteristics.Pedestrian crossing speed change patterns(whether pedestrian is changing speed or not while crossing a road)was considered as a binary variable and a logistic regression model was developed with vehicular gaps and other pedestrian behavioural characteristics as independent variables.The results revealed that there is a reduction in pedestrian crossing speed change behaviour with an increase in vehicular gap size at unprotected mid-block crosswalks.The younger pedestrians have more probability of exhibiting crossing speed change patterns as compared to the elderly pedestrians at mid-block crosswalks.Further,it is identified that there is an increase in pedestrian crossing speed with increase in vehicle speed as well as heavy vehicle type.Pedestrian behavioural characteristics also have a significant influence on crossing speed.The study findings would provide useful information to designers and policy makers for design of pedestrian crossing facility under mixed traffic conditions.展开更多
针对现有的基于对抗学习的领域适应算法未能充分挖掘样本的可转移特征导致泛化能力较差和分类精确度较低的问题,提出基于特征和类别对齐的领域适应(FCDA)算法.首先,针对最大均值差异(MMD)度量准则存在的不足进行改进,得到一种新的MID(ma...针对现有的基于对抗学习的领域适应算法未能充分挖掘样本的可转移特征导致泛化能力较差和分类精确度较低的问题,提出基于特征和类别对齐的领域适应(FCDA)算法.首先,针对最大均值差异(MMD)度量准则存在的不足进行改进,得到一种新的MID(maximizes the intra-domain density)度量函数,分别度量具有相同标签的源域样本特征间的分布散度和相同标签的目标域样本特征间的分布散度,实现最大化域内同类样本的类密度,从而降低类的错分率;其次,为了能更深层次地学习目标样本的抽象的、可转移的特征,从而减小域间差异,在特征提取网络后加入残差校正块,深化基础网络,提高其特征的可迁移性;最后,将获取的特征经过联合判别网络,通过对抗损失函数同时实现在类级和域级的对齐.所提出的算法在数据集Office-31上平均准确率为88.6%,在数据集Office-Home上平均准确率为67.7%,并与其他算法相比,验证了所提算法具备良好的泛化能力,可以实现较高的分类性能.展开更多
文摘Objective: Pedestrian safety is considered as one of the greatest concerns, especially for developing countries. In the year of 2015, about 48% pedestrian accidents with 56% fatalities occurred at mid-blocks in Beijing. Since the high frequency and fatality risk, this study focused on pedestrian accidents taking place at mid-blocks and aimed at identifying significant factors. Methods: Based on total 10,948 crash records, a binary logit model was established to explore the impact of various factors on the probability of pedestrian’s death. Furthermore, first-degree interaction effects were introduced into the basic model. The Hosmer-Lemeshow goodness-of-fit test was used to assess the model performance. Odds ratio was calculated for categorical variables to compare significant accident conditions with the conference level. Variables within consideration in this study included weather, area type, road type, speed limit, pedestrian location, lighting condition, vehicle type, pedestrian gender and pedestrian age. Results: The calibration results of the model show that the increased fatality chances of an accident at mid-blocks are associated with normal weather, rural area, two-way divided road, crossing elsewhere in carriageway, darkness (especially for no street lighting), light vehicle, large vehicle and male pedestrian. With road speed limit increasing by 10 km/h, the probability of death accordingly increases by 46%. Older victims have higher chances of being killed in a crash. Moreover, three interaction effects are found significant: rural area and two-way divided, rural area and crossing elsewhere as well as speed limit and pedestrian age. Conclusions: This study has analyzed police accident data and identified factors significant to the death probability of pedestrians in accidents occurred at mid-blocks. Recommendations and improving measures were proposed correspondingly. Behaviors of different road users at mid-blocks should be taken into account in the future research.
文摘Pedestrians usually cross the road at mid-block locations in India because of the ease and convenience to reach their destination as compared to intersection locations. It is important to evaluate the pedestrian gap acceptance behavior at mid-block locations because of inadequate vehicular gaps un- der mixed traffic condition, which translates into the pedestrian road crossing behavior. The present study examines the pedestrian gap acceptance behaviour by employing an artificial neural network （ANN） model for understanding the decision making process of pedestrians, i. e. , acceptance or rejec- tion of vehicular gaps at a mid-block location. From the results it has been found that the pedestrian rolling gap, frequency of attempt, vehicular gap size, pedestrian speed change condition and vehicle speed have major role in pedestrian gap acceptance. These results can lead to a better design of pedestrian crossing facilities where adequate gaps are not available in vehicular flow at mid-block crosswalk locations.
文摘The pedestrian crossing speed is one of the important factors in pedestrian crossing facility design.Research studies have shown that the pedestrian crossing speed is influenced by availability of green time at signalized crosswalks and pedestrian characteristics such as gender and age.However,the effects of vehicular time gap and additional pedestrian behavioural characteristics on pedestrian crossing speed patterns have not been examined at unprotected(un-signalized)mid-block crosswalks.The present study examines the pedestrian crossing speed change patterns considering the effect of vehicular time gap and pedestrian behavioural characteristics such as rolling behaviour,path change,etc.,at selected unprotected mid-block crosswalk locations under mixed traffic conditions in India.Video graphic survey has been conducted at eight selected unprotected mid-block crosswalk locations in Mumbai City for two to three hours duration during normal weather conditions.The data was mined using AVS video editor software,and the extracted data includes pedestrian speed,pedestrian characteristics(gender and age),pedestrian behaviour(rolling behaviour,path change,etc.),vehicle characteristics(type and speed of the vehicle)and traffic characteristics.Pedestrian crossing speed change patterns(whether pedestrian is changing speed or not while crossing a road)was considered as a binary variable and a logistic regression model was developed with vehicular gaps and other pedestrian behavioural characteristics as independent variables.The results revealed that there is a reduction in pedestrian crossing speed change behaviour with an increase in vehicular gap size at unprotected mid-block crosswalks.The younger pedestrians have more probability of exhibiting crossing speed change patterns as compared to the elderly pedestrians at mid-block crosswalks.Further,it is identified that there is an increase in pedestrian crossing speed with increase in vehicle speed as well as heavy vehicle type.Pedestrian behavioural characteristics also have a significant influence on crossing speed.The study findings would provide useful information to designers and policy makers for design of pedestrian crossing facility under mixed traffic conditions.
文摘针对现有的基于对抗学习的领域适应算法未能充分挖掘样本的可转移特征导致泛化能力较差和分类精确度较低的问题,提出基于特征和类别对齐的领域适应(FCDA)算法.首先,针对最大均值差异(MMD)度量准则存在的不足进行改进,得到一种新的MID(maximizes the intra-domain density)度量函数,分别度量具有相同标签的源域样本特征间的分布散度和相同标签的目标域样本特征间的分布散度,实现最大化域内同类样本的类密度,从而降低类的错分率;其次,为了能更深层次地学习目标样本的抽象的、可转移的特征,从而减小域间差异,在特征提取网络后加入残差校正块,深化基础网络,提高其特征的可迁移性;最后,将获取的特征经过联合判别网络,通过对抗损失函数同时实现在类级和域级的对齐.所提出的算法在数据集Office-31上平均准确率为88.6%,在数据集Office-Home上平均准确率为67.7%,并与其他算法相比,验证了所提算法具备良好的泛化能力,可以实现较高的分类性能.
