Intent Prediction of Pedestrians via Motion Trajectories Using Stacked Recurrent Neural Networks
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
The problem of intent understanding between highly and fully automated vehicles and vulnerable road users (VRUs) such as pedestrians in urban traffic environment has got some momentum over the past few years. Previous work has been tackling the problem using two common approaches, namely dynamical motion modeling and motion planning. In this paper, a novel radical end-to-end data-driven approach is proposed for long-term intent prediction of VRUs in urban traffic environment based solely on their motion trajectories. In the proposed approach, we utilized the widely adopted architecture of recurrent neural networks with Long-Short Term Memory (LSTM) modules to form a deep stacked LSTM network. Three common approaches used in the literature were compared against our proposed approach over two different real-world datasets involving pedestrians collected from vehicle-based stereo cameras. The results over the testing datasets showed that the proposed approach achieved higher accuracies over most of the scenarios of the testing datasets with a small mean lateral position error of 0.48 m. Moreover, the proposed approach showed also a significant generalization capability over totally unobserved testing scenes during the training phase with only 0.58 m in mean lateral position error.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“| RNN | Process sequential data via recurrent structures | Simple temporal analysis, low latency | Basic motion recognition (e.g., arm |”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [147]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 11×
“They have also introduced two data-driven approaches for the pedestrian intent recognition task based on CNNs and RNNs respectively.”
MethodInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We utilized the Adam optimizer [32], to minimize the”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“have witnessed a huge success in a number of different spatial and sequential tasks [12], [17]–[19].”
BackgroundFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 1×
“have witnessed a huge success in a number of different spatial and sequential tasks [12], [17]–[19].”
BackgroundRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 2×
“Recurrent Neural Networks (RNN) have been commonly used in many sequence-based prediction tasks such as handwriting imitation [24], driver behavior modeling [25], human gait”
BackgroundMethodUnscented Filtering and Nonlinear Estimation
Julier, S. J., & Uhlmann, J. K. (2004) · Proceedings of the IEEE · doi:10.1109/jproc.2003.823141 · Cited by 6,588 · cited 7×
“In [6], a dynamical motion model based on Extended Kalman filter (EKF) [14] with different motion models was proposed for short time prediction (i.e. less than 2 seconds) of pedestrians’ motion trajectories.”
MethodInfluentialOn the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310 · cited 1×
“Since traditional RNNs have difficult times in giving an accurate prediction when it comes to memorizing past long sequences [28].”
Background
Research works printed but not linked: 1
- lee, 2007, Loss functions in time series forecasting, International Encyclopedia of the Social Sciences
Cited by
Industry 5.0—A Human-Centric Solution
Nahavandi, S. (2019) · Sustainability · doi:10.3390/su11164371 · Cited by 1,695
“Computer vision [28], combined with deep learning [29], reinforcement learning, and GPU-based computation [30], has shown great promise in replicating primitive vision and sensory capabilities.”
BackgroundSelf-citationHuman motion trajectory prediction: a survey
Rudenko, A., Palmieri, L., Herman, M., Kitani, K. M., Gavrila, D. M., & Arras, K. O. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920917446 · Cited by 658
Mourtzis, D., Angelopoulos, J., & Panopoulos, N. (2022) · Journal of Machine Engineering · doi:10.36897/jme/147160 · Cited by 174
“Combining computer vision [81] with DL [82], reinforcement learning [83], and GPU-based computation [84] has shown great promise in replicating primitive vision and sensory abilities.”
MethodBehavioral Intention Prediction in Driving Scenes: A Survey
Fang, J., Wang, F., Xue, J., & Chua, T. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3374342 · Cited by 149
“For example, Saleh et al. [134], [211] predict the long-term intention of pedestrians by a stacked LSTM over the trajectory points.”
BackgroundGhorai, P., Eskandarian, A., Kim, Y., & Mehr, G. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3160932 · Cited by 128
Pedestrian Behavior Prediction Using Deep Learning Methods for Urban Scenarios: A Review
Zhang, C., & Berger, C. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3281393 · Cited by 115
“Later trajectory prediction methods such as [20], [21], [22], [29],”
BackgroundMethodInfluentialSpatiotemporal Residual Graph Attention Network for Traffic Flow Forecasting
Zhang, Q., Li, C., Su, F., & Li, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3243122 · Cited by 85
“With the study on the memory capability of recurrent neural networks (RNNs), RNN and its variant models are widely used for time-series forecasting tasks [20], [21], [22], e.g., the long short-term memory (LSTM) and the gated recurrent units (GRUs) [23].”
BackgroundPedestrian Crossing Intention Prediction at Red-Light Using Pose Estimation
Zhang, S., Abdel-Aty, M. A., Wu, Y., & Zheng, O. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3074829 · Cited by 81
Pedestrian Intention Prediction for Autonomous Vehicles: A Comprehensive Survey
Sharma, N., Dhiman, C., & Indu, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.07.085 · Cited by 98
Attention-Based Interrelation Modeling for Explainable Automated Driving
Zhang, Z. J., Tian, R., Sherony, R., Domeyer, J. E., & Ding, Z. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3229682 · Cited by 90
“…and implemented to either break down automated driving into sub-tasks such as lane detection, obstacle avoidance [8], [9], and pedestrian intent prediction [10], [11], [12], or develop holistic systems to design an end-to-end network that executes multiple tasks simultaneously [13], [14], [15].”
BackgroundA Review of Deep Reinforcement Learning Algorithms for Mobile Robot Path Planning
Singh, R., Ren, J., & Lin, X. (2023) · Vehicles · doi:10.3390/vehicles5040078 · Cited by 92
A Survey on Deep Learning Based Approaches for Scene Understanding in Autonomous Driving
Guo, Z., Huang, Y., Hu, X., Wei, H., & Zhao, B. (2021) · Electronics · doi:10.3390/electronics10040471 · Cited by 85
“A recurrent NN with long short-term memory modules for long-term intent prediction of pedestrians was employed in [121].”
BackgroundCai, J., Zhang, Y., Yang, L., Cai, H., & Li, S. (2020) · Advanced Engineering Informatics · doi:10.1016/j.aei.2020.101173 · Cited by 71
Scheduling Under Uncertainty for Industry 4.0 and 5.0
Bakon, K. A., Holczinger, T., Süle, Z., Jaskó, S., & Abonyi, J. (2022) · IEEE Access · doi:10.1109/access.2022.3191426 · Cited by 78
Pedestrian-Aware Statistical Risk Assessment
Shen, X., & Raksincharoensak, P. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3074522 · Cited by 56
Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets With Multi-Stream Inputs
Zhang, C., Li, R., Kim, W., Yoon, D., & Patras, P. (2020) · IEEE Access · doi:10.1109/access.2020.3032344 · Cited by 66
“Underpinned by recent advances in parallel computing, deep neural networks [8] have achieved remarkable results in various areas, including computer vision [9], control [10], and autonomous driving [11], [12], as they can automatically extract features from raw data without requiring expen-”
BackgroundPedestrian Path Prediction for Autonomous Driving at Un-Signalized Crosswalk Using W/CDM and MSFM
Zhang, X., Chen, H., Yang, W., Jin, W., & Zhu, W. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2979231 · Cited by 50
“[16] proposed a radical end-to-end data-driven approach for long-term intent prediction of pedestrians’ trajectories based on Long Short-Term Memory (LSTM) network.”
MethodLearning From Interaction-Enhanced Scene Graph for Pedestrian Collision Risk Assessment
Liu, X., Zhou, Y., & Gou, C. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3309274 · Cited by 49
“…but also achieve highly complex semantics for an accurate understanding of scenarios and dynamic activities, such as driver behavior analysis [13], [14], driving behavior understanding [15], [16], [17], [18], pedestrian intent prediction [19], [20], [21], [22], [23], and risk assessment [24], [25].”
BackgroundSpatial-Temporal-Spectral LSTM: A Transferable Model for Pedestrian Trajectory Prediction
Zhang, C., Ni, Z., & Berger, C. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3285804 · Cited by 55
“Using deterministic positions of ( x, y ) coordinates is the simplest way to represent the output, with mean square error (MSE) or L2 loss as the loss function, as in studies [9], [15], [23], [31].”
Uncovering drone intentions using control physics informed machine learning
Perrusquía, A., Guo, W., Fraser, B., & Wei, Z. (2024) · Communications Engineering · doi:10.1038/s44172-024-00179-3 · Cited by 50
Contextual Recurrent Predictive Model for Long-Term Intent Prediction of Vulnerable Road Users
Saleh, K., Hossny, M., & Nahavandi, S. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2927770 · Cited by 43
Self-citationPedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights
Xie, J., Zhang, S., Xia, B., Xiao, Z. Q., Jiang, H., Zhou, S., Qin, Z., & Chen, H. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3368931 · Cited by 31
“In the context of autonomous driving [7], [8], [9], [10] and smart mobility [11], [12], vehicles are required to predict the trajectories of nearby pedestrians to avoid collisions [13], [14].”
BackgroundStatistical models of near-accident event and pedestrian behavior at non-signalized intersections
Shen, X., & Raksincharoensak, P. (2021) · Journal of Applied Statistics · doi:10.1080/02664763.2021.1962263 · Cited by 30
“[25] proposed a pedestrian intent prediction method using an architecture of recurrent neural networks with Long Short-TermMemory (LSTM)modules.”
MethodSaleh, K., Hossny, M., & Nahavandi, S. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.12.091 · Cited by 32
Self-citationBRAM-ED: Vehicle Trajectory Prediction Considering the Change of Driving Behavior
Li, L., Zhao, W., Wang, C., Chen, Q., & Chen, F. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3188011 · Cited by 30
“Most research on long short-term memory has been carried out in trajectory prediction [6].”
BackgroundVision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey
Zhou, W., Yang, L., Zhao, L., Zhang, R., Cui, Y., Huang, H., Qie, K., & Wang, C. (2025) · ACM Computing Surveys · doi:10.1145/3760525 · Cited by 52
“As shown in Figure 9, current methodologies classify into three categories: Trajectory-based [178–180], Pose-based [179, 181–183], and Hybrid CIR models [1, 58, 184–187].”
Yang, Z., Tang, R., Bao, J., Lu, J., & Zhang, Z. (2020) · Sensors · doi:10.3390/s20247061 · Cited by 26
Applying Deep Learning to Autonomous Vehicles: A Survey
Ren, J., Gaber, H. A., & Jabar, S. S. A. (2021) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd51990.2021.9458968 · Cited by 31
Detection of Malicious Intent in Non-cooperative Drone Surveillance
Liang, J., Ahmad, B. I., Jahangir, M., & Godsill, S. (2021) · Sensor Signal Processing for Defence (SSPD) · doi:10.1109/sspd51364.2021.9541485 · Cited by 31
Zhou, X., Zhao, W., Wang, A., Wang, C., & Zheng, S. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3206826 · Cited by 27
“Long Short-Term Memory (LSTM) network can learn long-term dependency information, overcome the shortcomings of RNN gradient explosion and disappearance, and has a good effect in predicting trajectories [28], [29], [30], [31].”
BackgroundA Two-Block RNN-Based Trajectory Prediction From Incomplete Trajectory
Fujii, R., Vongkulbhisal, J., Hachiuma, R., & Saitô, H. (2021) · IEEE Access · doi:10.1109/access.2021.3072135 · Cited by 28
Feng, Y., Zhang, T., Sah, A. P., Han, L., & Zhang, Z. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3094678 · Cited by 25
“Following [5], [24], and [3], we formulate pedestrian trajectory prediction as a temporal regression task.”
BackgroundMethodBayesian Inference of Collision Avoidance Intent During Ship Encounters
Jia, C., Ma, J., de Vries, B., & Kouw, W. M. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3383819 · Cited by 26
“Many machine learning models, such as the support vector machine (SVM) [7], random forest (RF) [19], long short-term memory network (LSTM) [20], ensemble LSTM (ELSTM) [9] have been developed to relate motion features to hidden intent classes.”
Hybrid Verification Technique for Decision-Making of Self-Driving Vehicles
Al-Nuaimi, M., Wibowo, S., Hongyang Qu, B., Aitken, J. M., & Veres, S. M. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10030042 · Cited by 26
“[82,83] instead of the limited approach adopted in this work.”
MethodCSIR: Cascaded Sliding CVAEs With Iterative Socially-Aware Rethinking for Trajectory Prediction
Zhou, H., Yang, X., Ren, D., Huang, H. Y., & Fan, M. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3300730 · Cited by 22
“The corresponding objective function generally aggregates the losses with respect to all time steps in a summation or a multiplication [17], [18].”
BackgroundVulnerable road user detection and safety enhancement: A comprehensive survey
Silva, R. M., Azevedo, G. F., Berto, M. V. V., Rocha, J. R., Fidelis, E. C., Nogueira, M. V., Lisboa, P., & Almeida, T. A. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128529 · Cited by 34
“Although this approach is simple, it struggles to capture spontaneous behaviors of targets.”
Zhao, B., Zhang, X., Chen, H., & Zhu, W. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3215199 · Cited by 21
“Secondly, the future trajectories of pedestrians are predicted [7], [8], [9].”
BackgroundDrone’s Objective Inference Using Policy Error Inverse Reinforcement Learning
Perrusquía, A., & Guo, W. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3333551 · Cited by 23
Reservoir Computing for Drone Trajectory Intent Prediction: A Physics Informed Approach
Perrusquía, A., & Guo, W. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3379381 · Cited by 25
“On the other hand, RNNs are useful for temporal-data by incorporating memory in the network [22], [23].”
BackgroundSun, Y., Xu, T., Li, J., Chu, Y., & Ji, X. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3268373 · Cited by 23
“In the technical field of ITS, the accurate trajectory prediction of agents, namely, vehicles [5], [6], pedestrians [7], [8], and bicycles [9], has emerged as one of the core problems.”
Yang, Q., Mei, Q., Fan, C., Ma, M., & Li, X. (2023) · Buildings · doi:10.3390/buildings13061502 · Cited by 16
Cao, M., Wang, R., Chen, N., & Wang, J. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3077388 · Cited by 18
Assistive Self-Driving Car Networks to Provide Safe Road Ecosystems for Disabled Road Users
Ibáñez, J. A. G., Contreras-Castillo, J. J., Valdovinos, I. A., & Reyes, A. (2023) · Machines · doi:10.3390/machines11100967 · Cited by 18
Tianyi, J., Zhao, C., Ji, Y., & Du, Y. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124548 · Cited by 16
Nahavandi, S. (2019) · IEEE Systems Man and Cybernetics Magazine · doi:10.1109/msmc.2019.2916239 · Cited by 15
“A sample prediction of the intended crossing action and trajectory of a pedestrian using the framework proposed in [17].”
BackgroundMethodSelf-citationFraser, B., Perrusquía, A., Panagiotakopoulos, D., & Guo, W. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10252859 · Cited by 14
Fraser, B., Perrusquía, A., Panagiotakopoulos, D., & Guo, W. (2023) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci52147.2023.10371877 · Cited by 15
“The proposed window lengths are set to 8, 16, 32, and 64.”
BackgroundMirzabagheri, A., Ahmadi, M., Zhang, N., Alirezaee, R., Mozaffari, S., & Alirezaee, S. (2025) · Vehicles · doi:10.3390/vehicles7020057 · Cited by 21
A Survey on Deep-Learning Methods for Pedestrian Behavior Prediction from the Egocentric View
Chen, T., & Tian, R. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9565041 · Cited by 17
Local and Global Contextual Features Fusion for Pedestrian Intention Prediction
Azarmi, M., Rezaei, M., Hussain, T., & Qian, C. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-43763-2_1 · Cited by 15
Zhang, Y., Zhang, X., Fujinami, Y., & Raksincharoensak, P. (2023) · IEEE Access · doi:10.1109/access.2023.3347779 · Cited by 13
“In [13], Long Short Term Memory (LSTM) modules based recurrent neural networks were adopted to make a pedestrian intent prediction.”
MethodUncertainty-Aware Pedestrian Crossing Prediction via Reinforcement Learning
Dai, S., Liu, J., & Cheung, N. M. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3400391 · Cited by 15
“The pedestrian is walking towards the road during observation but finally turns away thus is labeled not crossing . such as [9], [10], [11], [12], [13], [14], and [15] for crossing prediction and [16], [17], [18], [19], [20], [21], [22], [23], and [24] for trajectory prediction.”
BackgroundHu, D., Li, S., Cai, J., & Hu, Y. (2020) · Winter Simulation Conference · doi:10.1109/wsc48552.2020.9384077 · Cited by 16
Gaussian Process Auto Regression for vehicle center coordinates Trajectory Prediction
Lim, Q., Johari, K., & Tan, U.-X. (2019) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2019.8929719 · Cited by 11
“[12] L. Xin, P. Wang, C. Chan, J. Chen, S. E. Li and B. Cheng, "Intentionaware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks," 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, 2018, pp. 1441-1446.”
MethodInfluentialEarly intention prediction of pedestrians using contextual attention-based LSTM
Lian, J., Yu, F., Li, L., & Zhou, Y. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13814-y · Cited by 12
“It should be noted here, the drawing of the LSTM cell structure is referred to the literature [20].”
BackgroundZhou, Z., Liu, B., Yuan, C., & Zhang, P. (2023) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2023.3331817 · Cited by 10
“These models utilize deep learning techniques to comprehensively consider pedestrian trajectory features, behavioral characteristics, scene semantics, and agent interaction features [22], [23], [25].”
Chen, S., Peng, C., Yang, B., Lin, J., Zhou, L., Jiang, Z., Liu, Z., Liu, Y., & Tang, L. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00083-5 · Cited by 9
Dik, C., Emmanouilidis, C., & Duqueroie, B. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10369-x · Cited by 9
“Assuming that the nature of the movement is determined by internal human motivation towards a goal, methods which seek to account for the intention in the human movement [25] [12] have been developed.”
Lee, M. B., Lee, C. T., Abas, M. A., & Chong, W. W. F. (2025) · Journal of Traffic and Transportation Engineering (English Edition) · doi:10.1016/j.jtte.2024.05.004 · Cited by 17
FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving
Yi, Z., Shi, H., Yang, K., Jiang, Q., Ye, Y., Wang, Z., Ni, H., & Wang, K. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3317933 · Cited by 12
“Additionally, Recurrent Neural Networks (RNNs) have been successfully employed for predicting the intent of pedestrians [11].”
BackgroundMethodW/CDM-MSFM-driven pedestrian path prediction at signalized crosswalk with mixed traffic flow
Chen, H., Zhang, X., Yang, W., Jin, W., Zhu, W., & Zhao, B. (2020) · Transportmetrica B Transport Dynamics · doi:10.1080/21680566.2020.1828197 · Cited by 8
Robust Human Upper-Limbs Trajectory Prediction Based on Gaussian Mixture Prediction
Li, Q., Zhang, L., Zhang, M., Du, Y., Liu, K., & Feng, C. (2023) · IEEE Access · doi:10.1109/access.2023.3239009 · Cited by 6
“In order to evaluate the prediction performance of RGMTP algorithm, tests were conducted on public data sets [26] and own dataset.”
BackgroundMethodDATraj: A Dynamic Graph Attention Based Model for Social-Aware Pedestrian Trajectory Prediction
Si, Z., Ye, P., Xiong, G., Lv, Y., & Zhu, F. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588693 · Cited by 9
“Interactions between multiple people are hard to capture and model [3].”
BackgroundFOOTREST: Safety on Roads Through Intelligent Transportation System
Sharma, A., & Battula, R. B. (2020) · International Conference on Information Networking · doi:10.1109/icoin48656.2020.9016473 · Cited by 6
Trajectory Intent Prediction of Autonomous Systems Using Dynamic Mode Decomposition
Perrusquía, A., Wei, Z., & Guo, W. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3462790 · Cited by 6
“Research in trajectory intent prediction has been applied in the fields of robotics and smart navigation, e.g., in lane changing prediction of vehicles [6], pedestrian intent [7], [8], maritime vessel intent forecasting [9], aircraft trajectory prediction [10], [11].”
Liu, H., & Hirayama, T. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3560621 · Cited by 5
“Additionally, various studies are currently focusing on using machine learning-based methods to model interactions between pedestrians and AVs to improve pedestrian behavior prediction [40], [41], [42].”
LLaMAPed: Multi-modal Pedestrian Crossing Intention Prediction
Ham, J.-S., Kim, S., Jia, H., Jiang, P., Moon, J., Saripalli, S., & Kim, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91813-1_10 · Cited by 13
The Current Trends of Deep Learning in Autonomous Vehicles: A Review
Ren, J., Huang, R. N., Ren, J., & Gabbar, H. A. (2022) · Journal of Engineering Research and Sciences · doi:10.55708/js0110008 · Cited by 5
“[7] Unmanned Vehicles LSTM LSTM Pedestrian Detection”
MethodRefined Continuous Control of DDPG Actors via Parametrised Activation
Hossny, M., Iskander, J., Attia, M., Saleh, K., & Abobakr, A. (2021) · AI · doi:10.3390/ai2040029 · Cited by 10
Self-citationThe Model of the Automatic Control System for a Treadmill Based on Neural Networks
Obukhov, A. D., Siukhin, A., & Dedov, D. L. (2020) · International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon) · doi:10.1109/fareastcon50210.2020.9271589 · Cited by 5
“As an architecture, it is recommended to use a multilayer dense or recurrent network [18-21], which will make it possible to compensate for the lack of knowledge caused by discrete time, and MAX p should be considered automatically as a deviation of the input signals.”
MethodPose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks
Kreß, V., Schreck, S., Zernetsch, S., Doll, K., & Sick, B. (2020) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci47803.2020.9308462 · Cited by 5
“For example, Saleh et al. [14] forecast the trajectories of pedestrians with help of stacked Long Short-Term Memory (LSTM) cells.”
BackgroundFang, J., Wu, Z., Xu, M., & Chen, H. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05503-0 · Cited by 4
Pedestrian Crossing Intention Prediction via Spatio-Temporal Visual Data in Urban Traffic Scenes
Manzour, M. A., Shehata, O. M., & Morgan, E.-S. I. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625360 · Cited by 4
Multimodal understanding with GPT-4o to enhance generalizable pedestrian behavior prediction
Ham, J.-S., Huang, J., Jiang, P., Moon, J., Kwon, Y., Saripalli, S., & Kim, C. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110741 · Cited by 3
Ghiya, A., AlShami, A. K., & Kalita, J. K. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00077 · Cited by 6
Novel trajectory prediction algorithm using a full dataset: comparison and ablation studies
Shipman, A., Mead, D. R., Feng, Y., Macias, J. J. E., Angeloudis, P., & Demiris, Y. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9922591 · Cited by 3
SSDPose: A Single Shot Deep Pose Estimation and Analysis
Abobakr, A., Abdelkader, H., Iskander, J., Nahavandi, D., Saleh, K., Attia, M., Hossny, M., & Nahavandi, S. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8913964 · Cited by 3
“It has also been incorporated in highly automated vehicles to build an understanding of the behaviours and intentions of the humans around them [7], [8].”
BackgroundSelf-citationXu, M., Wu, Z., Cai, S., Shi, Y., & Fang, J. (2025) · IET Intelligent Transport Systems · doi:10.1049/itr2.70042 · Cited by 2
Social-Pose: Enhancing Trajectory Prediction With Human Body Pose
Gao, Y., Saadatnejad, S., & Alahi, A. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3594889 · Cited by 6
“While some works have explored using 2D pose keypoints for intention prediction [42], [49] and trajectory prediction in the image/pixel space [59], [10], our focus lies in trajectory prediction in camera/world coordinates, which holds more practical applications.”
A competitive and cooperative spatio-temporal framework for urban traffic flow forecasting
Yu, H., Liu, K., Wang, Z., Tan, S., & Lü, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132096 · Cited by 2
Manzour, M. A., Elias, C. M., Morgan, E.-S. I., & Shehata, O. M. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3491972 · Cited by 2
“In 2018 year, Long-Short Term Memory (LSTM) was used by both Saleh et al. and Ghori et al. [12], [13] to predict the intentions of pedestrians in four scenarios; starting, stopping, bending-in, and crossing scenarios.”
Marketing 5.0: Artificial Intelligence and Human Mimicking Approach
Shrivastava, A., & More, A. B. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83797-815-120251001 · Cited by 2
Carbon Emission Forecasting for Urban Road Traffic at Topological Level Based on Improved Informer
Zhang, L., Shi, Y., Ke, X., & Wang, J. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3591122 · Cited by 2
Chen, L.-L., Chen, L.-B., Wang, H.-Y., & Zhao, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331095 · Cited by 1
Pedestrian Trajectory Prediction in Crowd Scene Using Deep Neural Networks
Zeibo, J., Mishra, M. K., Panda, A. R., Mishra, B. S. P., & Mallick, P. K. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-7504-4_27 · Cited by 1
Diminution of Pedestrian Accident on Crowded Urban Streets Using Content-Based Video Retrieval
Arzhmand, E., Rashid, H., & Hosseini, F. S. (2023) · International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and Data Analytics (ICoABCD) · doi:10.1109/icoabcd59879.2023.10390925 · Cited by 1
“Saleh et al. [5][6] have also proposed data-driven approaches for predicting pedestrian trajectory in urban traffic environments using recurrent neural networks and LSTM. Alahi et al. introduced a social layer in [7] that allows LSTMs of spatially close sequences to share their hidden states with…”
BackgroundDeep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction
Dabrowski, J. J., de Villiers, J. P., Rahman, A., & Beyers, C. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-36808-1_50 · Cited by 1
Neural network method of adaptive control system of imitation of physical forces
Obukhov, A. D., & Siukhin, A. (2020) · Vestnik of Samara State Technical University. Technical Sciences Series · doi:10.14498/tech.2020.3.4
Pedestrian Path Prediction at Un-signalized Crosswalk by Integrating MSFM and Att-LSTM
Chen, H., Zhang, X., Yang, W., Liu, Y., Shi, D., & Zhu, W. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327517 · Cited by 1
“A radical end-to-end data-driven approach for pedestrian path prediction based on the LSTM was proposed, and a higher accuracy with a small lateral position error of 0.48m over the current approaches was achieved [10].”
MethodContrastive learning of graph encoder for accelerating pedestrian trajectory prediction training
Yao, Z., Yu, J., & Ding, J. (2021) · IET Image Processing · doi:10.1049/ipr2.12185 · Cited by 2
“Previous works always intended to deploy handcrafted feature extraction encoders such as graph neural networks (GNN) [5], long short-term memory (LSTM) [6], both LSTM and GNN [7], recurrent neural network (RNN) [8] and transformer model [1] to discriminate different state of pedestrian crowds.”
BackgroundImproving Pedestrian Safety Using Video Data, Surrogate Safety Measures and Deep Learning
Zhang, S. (2021) · Journal of International Crisis and Risk Communication Research
Behavior Analysis and Modeling of Traffic Participants
Song, X., & Cao, H. (2021) · Synthesis lectures on advances in automotive technology · doi:10.2200/s01134ed1v01y202109aat015
2018 Index IEEE Transactions on Intelligent Vehicles Vol. 3
(2018) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2018.2879711
Bi, M., Wang, X., Gao, Q., Wang, Y., Jiao, Z., Gao, R., Li, J., & He, M. (2023) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2504/1/012032
“Shaohua Liu et al[9] proposed a multi-precision interactive social force model for pedestrian trajectory prediction, Zetian Wang et al[10] used improved Markov chains to model and learn pedestrian trajectories, Shaojie Qiao ICCBDAI-2022 Journal of Physics: Conference Series 2504 (2023) 012032 IOP Publishing doi:10.108…”
MethodInfluentialA Wearable Sensor Network for Cyclists Safety in Mixed Traffic, a Pilot Study
Sanseverino, G., Rothermel, M., & Odenwald, S. (2023) · IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT) · doi:10.1109/metroind4.0iot57462.2023.10180150
“[3] proposed a novel approach to predict intentions of pedestrians by means of motion trajectories and neural networks.”
Data-Driven Robust Designs of Performance Prediction and Its Application in High-speed Trains
Chen, H., Wang, W., Guo, D., Xu, S., & Cheng, C. (2023) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm58088.2023.10218967
Galloul, M. K., Aboelwafa, M., & Gadallah, Y. (2023) · IEEE International Automated Vehicle Validation Conference (IAVVC) · doi:10.1109/iavvc57316.2023.10328106
“Alternatively, Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTMs), can capture dependencies in long sequences to anticipate the pedestrians’ intention [9].”
BackgroundTemporal Attention-Based Interactive Dynamic Graph Convolutional Network For Traffic Flow Prediction
Chen, L., Chen, L., Wang, H., & Li, Z. (2024) · International Conference on Information Technology in Medicine and Education · doi:10.1109/itme63426.2024.00044
LocFormer: Predicting Future Locations of Pedestrians from an Ego-centric view via Transformer
Gui, C., & Peng, Y. (2025) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3727648.3727805
“Researchers [ 7 ][ 8 ] have employed LSTM or GRU models to capture motion dynamics.”
Liu, X., Guo, B., Jin, L., An, C. K., Zhang, H., Luo, G. L. J., & Han, Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3612879
“For methods based on the pedestrian’s own motion temporal characteristics, models such as LSTM [6] and Transformer [7], [8] are employed to capture the temporal dependencies and dynamic changes in the pedestrian’s bounding box sequence, enabling intention recognition.”
Metadata
- Authors
- Saleh, K., Hossny, M., & Nahavandi, S.
- Affiliations
- Deakin University (AU)
- Venue
- IEEE Transactions on Intelligent Vehicles
- Published
- 2018-12
- Volume
- 3
- Issue
- 4
- Pages
- 414-424
- ISSN
- 2379-8858 (ISSN-L)
- 2379-8904
- OpenAlex
- W2895763020
- Cited by
- 103
- References
- 32
- Citations by year
- 2026: 4 · 2025: 16 · 2024: 13 · 2023: 22 · 2022: 11 · 2021: 17 · 2020: 12 · 2019: 7 · 2018: 1
- FWCI
- 4.92
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Locations
- IEEE Transactions on Intelligent Vehicles (publishedVersion)
- Deakin Research Online (Deakin University) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- Institute for Intelligent Systems Research and Innovation (IISRI)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Traffic and Road Safety
- Social Sciences › Safety Research › Evacuation and Crowd Dynamics
- Keywords
- vulnerable road users, movement trajectories, stacked LSTM, long short-term memory, end-to-end learning, autonomous vehicles, urban traffic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.