• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• 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.

• 한국멀티미디어학회논문지
• /
• 제18권5호
• /
• pp.575-582
• /
• 2015

Obtaining the complete trajectory of the object is a very important task in computer vision applications, such as video surveillance. Previous studies to recover the trajectory between two disconnected trajectory segments, however, do not takes into account the object's motion characteristics and uncertainty of trajectory segments. In this paper, we present a novel approach to recover the trajectory between two disjoint but associated trajectory segments, called goal-directed tracking. To incorporate the object's motion characteristics and uncertainty, the goal-directed state equation is first introduced. Then the goal-directed tracking framework is constructed by integrating the equation to the object tracking and trajectory linking process pipeline. Evaluation on challenging dataset demonstrates that proposed method can accurately recover the missing trajectory between two disconnected trajectory segments as well as appropriately constrain a motion of the object to the its goal(or the target state) with uncertainty.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1995년도 춘계공동학술대회논문집; 전남대학교; 28-29 Apr. 1995
• /
• pp.787-796
• /
• 1995

A man model is a useful design tool for the evaluation of man machine systems and products. An arm reach trajectory prediction for such a model will be specifically useful to present human activities and, consequently, could increase the accuracy and reality of the evaluation. In this study, a three-dimensional reach trajectory prediction model was developed using an inverse kinematics technique. The upper body was modeled as a four link open kinematic chain with seven degrees of freedom. The Resolved Motion Method used for the robot kinematics problem was used to predict the joint movements. The cost function of the perceived discomfort developed using the central composite design was also used as a performance function. This model predicts the posture by moving the joints to minimize the discomfort on the constraint of the end effector velocity directed to a target point. The results of the pairwise t-test showed that all the joint coordinates except the shoulder joint's showed statistically no differences at .alpha. = 0.01. The reach trajectory prediction model developed in this study was found to accurately simulate human arm reach trajectory and the model will help understand the human arm reach movement.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2011년도 춘계학술대회 논문집
• /
• pp.89-90
• /
• 2011

• Journal of Positioning, Navigation, and Timing
• /
• 제12권4호
• /
• pp.409-421
• /
• 2023

In order to develop navigation systems, simulators that provide navigation sensors data are required. A trajectory generator that simulates vehicle motion is needed to generate navigation sensors data in the simulator. In this paper, a trajectory generator for evaluating navigation system performance is proposed. The proposed trajectory generator consists of two parts. The first part obtains parameters from the motion scenario file whereas the second part generates position, velocity, and attitude from the parameters. In the proposed trajectory generator six degrees of freedom, halt, climb, turn, accel turn, spiral, combined, and waypoint motions are given as basic motions with parameters. These motions can be combined to generate complex trajectories of the vehicle. Maximum acceleration and jerk for linear motion and maximum angular acceleration and velocity for rotational motion are considered to generate trajectories. In order to show the usefulness of the proposed trajectory generator, trajectories were generated from motion scenario files and the results were observed. The results show that the proposed trajectory generator can accurately simulate complex vehicle motions that can be used to evaluate navigation system performance.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• 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.

• 대한방사선기술학회지:방사선기술과학
• /
• 제42권1호
• /
• pp.39-46
• /
• 2019

This study conducted a comparative analysis of differences between cartesian trajectory in a linear rectangular coordinate system and MultiVane trajectory in a nonlinear rectangular coordinate system axial T1 and axial T2 images using an American College of Radiology(ACR) phantom. The phantom was placed at the center of the head coil and the top-to-bottom and left-to-right levels were adjusted by using a level. The experiment was performed according to the Phantom Test Guidance provided by the ACR, and sagittal localizer images were obtained. As shown in Figure 2, slices # 1 and # 11 were scanned after placing them at the center of a $45^{\circ}$ wedge shape, and a total of 11 slices were obtained. According to the evaluation results, the image intensity uniformity(IIU) was 93.34% for the cartesian trajectory, and 93.19% for the MultiVane trajectory, both of which fall under the normal range in the axial T1 image. The IIU for the cartesian trajectory was 0.15% higher than that for the MultiVane trajectory. In axial T2, the IIU was 96.44% for the cartesian trajectory, and 95.97% for the MultiVane trajectory, which fall under the normal range. The IIU for the cartesian trajectory was by 0.47% higher than that for the MultiVane trajectory. As a result, the cartesian technique was superior to the MultiVane technique in terms of the high-contrast spatial resolution, image intensity uniformity, and low-contrast object detectability.

• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• Journal of Positioning, Navigation, and Timing
• /
• 제1권1호
• /
• pp.45-49
• /
• 2012

The flight performance evaluation of navigation system is very significant because the reliability of navigation data directly affect the safety of aircraft. Especially, the high-level navigation system such as DGPS/INS, need more precise flight performance evaluation method. The performance analysis is evaluated by comparing between the navigation system in aircraft and reference trajectory which is more precise than navigation system in aircraft. In order to verify DGPS/INS performance of m-level, the GPS receiver, which is capable post-processed Carrier-phase Differential GPS(CDGPS) method of cm-level, have to be used as reference system. The DGPS/INS is estimated the Center of Gravity (CG) point of aircraft to offer precise performance while the reference system is output the position of GPS antenna which is mounted on the outside of aircraft. Therefore, in order to more precise performance evaluation, it needs to compensate the lever arm and coordinates transformation. This paper use quaternion and Direct Cosine Matrix(DCM) methods as coordinate transformation matrix in lever arm compensation of CDGPS reference trajectory. And it compares NED errors of DCM and quaternion transformation in lever arm of reference trajectory via DGPS/INS result.

• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.533-545
• /
• 2017

Massive volumes of GPS trajectory data bring challenges to storage and processing. These issues can be addressed by compression algorithm which can reduce the size of the trajectory data. A key requirement for GPS trajectory compression algorithm is to reduce the size of the trajectory data while minimizing the loss of information. Synchronized Euclidean distance (SED) as an important error measure is adopted by most of the existing algorithms. In order to further reduce the SED error, an improved algorithm for open window time ratio (OPW-TR) called local optimum open window time ratio (LO-OPW-TR) is proposed. In order to make SED error smaller, the anchor points are selected by calculating point's accumulated synchronized Euclidean distance (ASED). A variety of error metrics are used for the algorithm evaluation. The experimental results show that the errors of our algorithm are smaller than the existing algorithms in terms of SED and speed errors under the same compression ratio.