A Pedestrian Hazard Assessment Method in Urban Road Scene

Zeng Lingqiu, Ma Jisen, Han Qingwen, Ye Lei

Abstract

  In view of the influence of pedestrians on vehicle driving in traffic scenes and the problem that the assisted driving needs to avoid the danger for pedestrians,  a pedestrian hazard assessment method based on vehicle-mounted monocular cameras is proposed. Based on the characteristic environment of Chinese cities,  this paper divided the driving environment into three scenarios: regular roads,  crosswalks,  auxiliary roads. Different risk assessment methods are used for each type of scenarios. A convolutional neural network is used to detect and identify pedestrians,  auxiliary police,  signal lights and sidewalks on the road in the video. Then,  it detects the key points of the pedestrian and uses the multi-target tracking method to generate the time series of the pedestrian skeleton. Pedestrian behavior and trend are obtained through LSTM(Long-Short Term Memory Neural Network) analysis of posture sequences. Finally,  a pedestrian hazard assessment model is built to realize the pedestrian hazard assessment in multi road scene by synthesizing the video information,  pedestrian information and scene information. The experimental results show that the scene classification makes the assessment results of the hazard model more consistent with the actual pedestrian hazard. The proposed model can effectively evaluate the pedestrian hazard and assist the drivers to drive safely.

 

 

Keywords:  pedestrian safety,   pedestrian behavior analysis,   assisted driving,   multi scenario analysis


Full Text:

PDF


References


GHORI O, MACKOWIAK R, BAUTISTA M, et al. Learning to forecast pedestrian intention from pose dynamics [C]// Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV). Changshu： IEEE, 2018：1277—1284.

SCHNEIDER N, GAVRILA D M. Pedestrian path prediction with recursive Bayesian filters：A comparative study[C]// Proceedings of the Pattern Recognition. Berlin, Heidelberg：Springer Berlin Heidelberg, 2013：174—183.

KELLER C G, GAVRILA D M. Will the pedestrian cross? A study on pedestrian path prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(2)：494—506.

SCHMIDT S, FRBER B. Pedestrians at the kerb - recognising the action intentions of humans [J]. Transportation Research Part F Psychology & Behaviour, 2009, 12(4)：300—310.

FANG Z, L PEZ A M. Is the pedestrian going to cross? Answering by 2D pose estimation [C]// Proceedings of the 2018 IEEE Intelligent Vehicles Symposium(IV). Changshu：IEEE, 2018：1271—1276.

LI Y, LAN C, XING J, et al. Online human action detection using joint classification-regression recurrent neural networks [C]// Proceedings of the Computer Vision - ECCV 2016. Cham：Springer International Publishing, 2016：203—220.

DENG Q, TIAN R, CHEN Y, et al. Skeleton model based behavior recognition for pedestrians and cyclists from vehicle sce ne camera[C]// Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV). Changshu：IEEE, 2018：1293—1298.

HARIYONO J, JO K H. Detection of pedestrian crossing road：A study on pedestrian pose recognition [J]. Neurocomputing, 2017, 234：144—153.

LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO：Common objects in context[C]// Proceedings of he Computer Vision - ECCV 2014. Cham：Springer International Publishing, 2014：740—755.

YU F, XIAN W, CHEN Y, et al. BDD100K：A diverse driving video database with scalable annotation tooling [J/OL]. https：//arxiv.org/ abs/1805.04687, 2018-05-12.

KOTSERUBA Y, RASOULI A, TSOTSOS J. Joint attention in autonomous driving (JAAD) [J/OL]. https：//arxiv.org/abs/1609. 04741v5, 2017-04-27.

VEERAMANI B, RAYMOND J W, CHANDA P. DeepSort：deep convolutional networks for sorting haploid maize seeds [J]. BMC Bioinformatics, 2018, 19(9)：289.

HE K, GKIOXARI G, DOLL R P, et al. Mask R -CNN [J]. IEEETransactions on Pattern Analysis and Machine Intelligence, 2020, 42(2)：386—397.

BRABANDERE B, GANSBEKE W, NEVEN D, et al. End -to -end lane detection through differentiable least -squares fitting [J/OL]. https：//arxiv.org/abs/1902.00293v1, 2019-02-01.


Refbacks

  • There are currently no refbacks.