Estimation of Driver's Insight for Safe Passing based on Pedestrian Attributes

In order to reduce traffic accidents between a vehicle and a pedestrian, recognition of a pedestrian who has a possibility of collision with a vehicle should be helpful. However, since a pedestrian may suddenly change his/her direction and cross the road, it is difficult to predict his/her behavior directly. Here, we focus on the fact that experienced drivers usually pass by a pedestrian while preparing to step on the brake at any moment when they feel danger. If driver assistant systems can estimate such experienced driver's decisions, they could early detect the pedestrian in danger of collision. Therefore, we classify the driver's decisions into three types by referring to the accelerator operation of drivers, and propose a method to estimate the type of the driver's decision. The drivers are considered to decide their actions focusing on various behaviors and states of a pedestrian, namely pedestrian's attributes. Since the driver's decisions change along the timeline, the use of a temporal context is considered to be effective. Thus, in this paper, we propose an estimation method using a recurrent neural network architecture with the pedestrian's attributes as input. We constructed a dataset collected by experienced drivers in control of the vehicle and evaluated the performance, and then confirmed the effectiveness of the use of pedestrian's attributes.

[1]  Rita Cucchiara,et al.  People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees , 2012, ECCV.

[2]  Hiroshi Murase,et al.  Pedestrian detection from sparse point-cloud using 3DCNN , 2018, 2018 International Workshop on Advanced Image Technology (IWAIT).

[3]  Reinhard Klette,et al.  Part-Based RDF for Direction Classification of Pedestrians, and a Benchmark , 2014, ACCV Workshops.

[4]  Hironobu Fujiyoshi,et al.  Driver's decision analysis in terms of pedestrian attributes — A case study in passing by a pedestrian , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[5]  Hironobu Fujiyoshi,et al.  Robust pedestrian attribute recognition for an unbalanced dataset using mini-batch training with rarity rate , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[6]  Kaiqi Huang,et al.  Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[7]  Hironobu Fujiyoshi,et al.  Misclassification tolerable learning for robust pedestrian orientation classification , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[8]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[9]  Pietro Perona,et al.  Pedestrian Detection: An Evaluation of the State of the Art , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Hironobu Fujiyoshi,et al.  Recognition of Texting-While-Walking by Joint Features Based on Arm and Head Poses , 2016, ACCV Workshops.

[11]  Dariu Gavrila,et al.  Joint probabilistic pedestrian head and body orientation estimation , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[12]  Min Sun,et al.  Anticipating Accidents in Dashcam Videos , 2016, ACCV.

[13]  Klaus C. J. Dietmayer,et al.  Early detection of the Pedestrian's intention to cross the street , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[14]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[15]  Shuicheng Yan,et al.  Scale-Aware Fast R-CNN for Pedestrian Detection , 2015, IEEE Transactions on Multimedia.

[16]  C. G. Keller,et al.  Will the Pedestrian Cross? A Study on Pedestrian Path Prediction , 2014, IEEE Transactions on Intelligent Transportation Systems.

[17]  Hirokatsu Kataoka,et al.  Predicting driving behavior using inverse reinforcement learning with multiple reward functions towards environmental diversity , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).