• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1562-1582
• /
• 2024

The prediction of pedestrian trajectory is conducive to reducing traffic accidents and protecting pedestrian safety, which is crucial to the task of intelligent driving. The existing methods mainly use the past pedestrian trajectory to predict the future deterministic pedestrian trajectory, ignoring pedestrian intention and trajectory diversity. This paper proposes a multi-modal trajectory prediction model that introduces pedestrian intention. Unlike previous work, our model makes multi-modal goal-conditioned trajectory pedestrian prediction based on the past pedestrian trajectory and pedestrian intention. At the same time, we propose a novel Gate Recurrent Unit (GRU) to process intention information dynamically. Compared with traditional GRU, our GRU adds an intention unit and an intention gate, in which the intention unit is used to dynamically process pedestrian intention, and the intention gate is used to control the intensity of intention information. The experimental results on two first-person traffic datasets (JAAD and PIE) show that our model is superior to the most advanced methods (Improved by 30.4% on MSE_0.5s and 9.8% on MSE_1.5s for the PIE dataset; Improved by 15.8% on MSE_0.5s and 13.5% on MSE_1.5s for the JAAD dataset). Our multi-modal trajectory prediction model combines pedestrian intention that varies at each prediction time step and can more comprehensively consider the diversity of pedestrian trajectories. Our method, validated through experiments, proves to be highly effective in pedestrian trajectory prediction tasks, contributing to improving traffic safety and the reliability of intelligent driving systems.

• Journal of Power System Engineering
• /
• v.13 no.2
• /
• pp.56-62
• /
• 2009

The fatalities of pedestrian account for about 40.0% of all fatalities in Korea 2005. Vehicle-Pedestrian accident generates trajectory of pedestrian. In pedestrian involved accident, the most important data to inspect accident is throw distance of pedestrian. The throw distance of pedestrian can be influenced by many variables. But existing studies have been done for simple factors. The variables that influence trajectory of pedestrian can be classified into vehicular factors, pedestrian factors, and road factors. The trajectory of pedestrian, dynamic characteristics of multi-body were analyzed by PC-CRASH, a kinetic analysis program for a traffic accident. PC-CRASH enables an analyst to investigate the effect of many variables. The influence of the offset of impact point was analyzed by Working Model. Based on the results, the variables that influence trajectory of pedestrian were vehicular frontal shape, vehicular impact speed, the offset of impact point, the height of pedestrian, friction coefficients of pedestrian. However the weight of pedestrian did not affect trajectory of pedestrian considerably.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2321-2338
• /
• 2021

Compared with vehicle trajectories, pedestrian trajectories have stronger degrees of freedom and complexity, which poses a higher challenge to trajectory prediction tasks. This paper designs a mode to divide the trajectory of pedestrians at a traffic intersection, which converts the trajectory regression problem into a trajectory classification problem. This paper builds a deep model for pedestrian trajectory prediction at intersections for the task of pedestrian short-term trajectory prediction. The model calculates the spatial correlation and temporal dependence of the trajectory. More importantly, it captures the interactive features among pedestrians through the Attention mechanism. In order to improve the training speed, the model is composed of pure convolutional networks. This design overcomes the single-step calculation mode of the traditional recurrent neural network. The experiment uses Vulnerable Road Users trajectory dataset for related modeling and evaluation work. Compared with the existing models of pedestrian trajectory prediction, the model proposed in this paper has advantages in terms of evaluation indicators, training speed and the number of model parameters.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.6 no.3
• /
• pp.71-76
• /
• 2007

The fatalities of pedestrian account for about 40.0% of all fatalities in Korea 2005. Vehicle-Pedestrian accident generates trajectory of pedestrian. In pedestrian involved accident, the most important data to inspect accident is throw distance of pedestrian. The throw distance of pedestrian can be influenced by many variables. The variables that influence trajectory of pedestrian can be classified into vehicular factors, pedestrian factors, and road factors. Vehicular factors are the frontal shape of vehicle, impact speed of vehicle, the offset of impact point. Many studies have been done about the relation between impact speed and throw distance of pedestrian. But the influence of the offset of impact point was neglected. The influence of the offset of impact point was analyzed by Working Model, and the trajectory of pedestrian, dynamic characteristics of multi-body were analyzed by PC-CRASH, a kinetic analysis program for a traffic accident. Based on the results, the increase of offset reduced the throw distance of pedestrian. However box type vehicle just like bus, the offset of impact point did not influence the throw distance of pedestrian considerably.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.6 no.3
• /
• pp.105-111
• /
• 2007

The type of pedestrian accident can be characterized by vehicular frontal shape and the height of pedestrian. The trajectory of pedestrian after collision by passenger car is different from that by bus due to vehicular frontal shape. The frontal shape of SUV vehicles is dissimilar to passenger car and bus. So, the trajectory and throw distance of pedestrian by SUV vehicles is not the same of passenger car and bus. In this paper, a series of pedestrian kinetic simulation were conducted to inspect the difference in throw distance between SUV vehicle and passenger car and bus by PC-CRASH that is the program for kinetic analysis of articulated body. From the results, if the height of pedestrian is taller than 1.70m, there is no difference in throw distance between SUV vehicle and passenger car, but if the height of pedestrian is about 1.55m throw distance of SUV vehicle is about 4m longer than that of passenger car at each impact speed. The throw distance of pedestrian by Bus is shorter than that of passenger car and SUV at each impact speed.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.4
• /
• pp.256-266
• /
• 2016

Concurrently detected and annotated abnormal events can have a significant impact on surveillance systems. By considering the specific domain of pedestrian trajectories, this paper presents two main contributions. First, as introduced in much of the work on trajectory-based anomaly detection in the literature, only information about pedestrian paths, such as direction and speed, is considered. Differing from previous work, this paper proposes a framework that deals with additional types of trajectory-based anomalies. These abnormal events take places when a person enters prohibited areas. Those restricted regions are constructed by an online learning algorithm that uses surrounding information, including detected pedestrians and background scenes. Second, a simple data-boosting technique is introduced to overcome a lack of training data; such a problem particularly challenges all previous work, owing to the significantly low frequency of abnormal events. This technique only requires normal trajectories and fundamental information about scenes to increase the amount of training data for both normal and abnormal trajectories. With the increased amount of training data, the conventional abnormal trajectory classifier is able to achieve better prediction accuracy without falling into the over-fitting problem caused by complex learning models. Finally, the proposed framework (which annotates tracks that enter prohibited areas) and a conventional abnormal trajectory detector (using the data-boosting technique) are integrated to form a united detector. Such a detector deals with different types of anomalous trajectories in a hierarchical order. The experimental results show that all proposed detectors can effectively detect anomalous trajectories in the test phase.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.13 no.4
• /
• pp.8-18
• /
• 2005

Pedestrians involved in traffic accidents manifest unique trajectory characteristics depending on the collision speed, vehicle configuration, and pedestrian postures. However, the existing analytical models for pedestrian movements do not fully include the rotational characteristics of the pedestrians because they assume a two dimensional parabolic trajectory. This faulty assumption in the development of these models limits their applicability and reliability This study investigated the pedestrians movement at collision by computer simulation. The simulations are carried out by using HADYMO, which is a special simulation software system for dynamic movement analysis. Vehicles and pedestrians are modeled and verified via real crash worthiness experiments. Simulations are performed for various collision speeds, vehicle configuration, and pedestrian postures. Since the simulation uses multi-body dynamics, It can express irregular phenomena of the bodies quite well. The results can be exploited for vehicle design and traffic accident reconstruction.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.2
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.

• Korean Journal of Applied Biomechanics
• /
• v.31 no.1
• /
• pp.37-43
• /
• 2021

Objective: The purpose of this study was to investigate the effect of mobile phone text messaging on the collision avoidance strategy for an approaching and stationary pedestrian. Method: Eighteen healthy young adults participated in this study. Each participant was asked to perform a task to walking with/without mobile phone text messaging and a task to avoid collisions with another pedestrian who was approaching or stationary during walking. Results: When text messaging with avoidance collision, it showed an early onset time, a larger mediolateral COM trajectory, trunk rotation angle and trunk rotation velocity (p<.05). Also, compared to an approaching pedestrian, when avoiding collision with a stationary pedestrian, it showed a later onset time, a lager avoidance displacement, mediolateral COM trajectory, trunk rotation angle (p<.05). Conclusion: Results suggest that mobile phone text messaging while collision avoidance leads to delay the perception stage and alters the adaptation stage. Consequently, pedestrian executed in an exaggerated avoidance action to create a greater safety margin when attending to mobile phone test messages while avoiding another pedestrian.