Pedestrian Trajectories Research Articles

Attention-addressing and adaptive-intention-clustering based memory recall for pedestrian trajectory prediction

Attention-addressing and adaptive-intention-clustering based memory recall for pedestrian trajectory prediction

IGGCN: Individual-Guided Graph Convolution Network for Pedestrian Trajectory Prediction

Accurately predicting the future trajectory of pedestrians is crucial for applications such as autonomous driving and robot navigation. Graph convolution is widely used in trajectory prediction tasks due to its scalability and adaptive feature-learning capabilities. However, there are two problems with pedestrian trajectory prediction methods based on graph convolution: 1. Previous methods struggled to adjust social interactions according to the attributes of different pedestrians, making it difficult to accurately model the relative importance between different pedestrians and others; 2. Previous methods lacked dynamic processing of pedestrian spatial-temporal interaction features to capture high-level spatial-temporal interaction features effectively. Therefore, we propose an Individual-Guided Graph Convolution Network (IGGCN) for pedestrian trajectory prediction. To tackle problem 1, we design an individual-guided interaction module that can adjust pedestrian social interaction modeling according to the pedestrian's attributes, thereby achieving an accurate description of the relative importance of pedestrians. We extend the module to temporal interaction modeling to further achieve an accurate description of the relative importance of time frames. To address problem 2, we design a deformable convolution module to dynamically process spatial-temporal interaction features through deformable convolution kernels, facilitating the capture of high-level spatial-temporal interaction features. We evaluate our method on the ETH, UCY, and SDD datasets. Quantitative analysis shows that our method has lower prediction errors than the current state-of-the-art methods. Qualitative analysis further reveals that our method effectively eliminates the influence of irrelevant pedestrians and accurately models the spatial-temporal interaction relationship of pedestrians.

SISGAN: A Generative Adversarial Network Pedestrian Trajectory Prediction Model Combining Interaction Information and Scene Information

Accurate pedestrian trajectory prediction is crucial in many fields. This requires the full use and learning of pedestrians’ social interactions, movements, and environmental information. In view of the current research on pedestrian trajectory prediction, wherein most of the pedestrian interaction information is explored from the level of overall interaction, this paper proposes the SISGAN model, which designs a social interaction module from the perspective of the target pedestrian, and takes four kinds of interaction information as the influencing factors of pedestrian interaction, so as to describe the influence mechanism of pedestrian–pedestrian interaction. In addition, in terms of environmental information, the index density of pedestrian historical trajectory in space is taken into account in the extraction of environmental information, which increases the potential correlation between environmental information and pedestrians. Finally, we integrate social interaction information and environmental information and make the final trajectory prediction based on GAN. Experiments on ETH and UCY datasets demonstrate the effectiveness of the SISGAN model proposed in this paper.

STAFGCN:A spatial-temporal attention-based fusion graph convolution network for pedestrian trajectory prediction

Pedestrian trajectory prediction provides crucial data support for the development of smart cities. Existing pedestrian trajectory prediction methods often overlook the different types of pedestrian interactions and the micro-level spatial-temporal relationships when handling the interaction information in spatial dimension and temporal dimension. The model employs a spatial-temporal attention-based fusion graph convolutional framework to predict future pedestrian trajectories. For the different types of local and global relationships between pedestrians, it first employs spatial-temporal attention mechanisms to capture dependencies in pedestrian sequence data, obtaining the social interactions of pedestrians in spatial contexts and the movement trends of pedestrians over time. Subsequently, a fusion graph convolutional module merges the temporal weight matrix and the spatial weight matrix into a spatial-temporal fusion feature map. Finally, a decoder section utilizes TimeStacked Convolutional Neural Networks to predict future trajectories. The final validation on the ETH and UCY datasets yielded experimental results with an Average Displacement Error(ADE) of 0.34 and an Final Displacement Error(FDE) of 0.55. The visualization results further demonstrated the rationality of the model.

Graph Convolution Network Combining Spatiotemporal Self-Attention and Mutual Information for Pedestrian-Trajectory Prediction

Accurate pedestrian-trajectory prediction is significant and challenging for intelligent driving. There are two challenges in this field: most existing methods ignore pedestrian–vehicle interaction in the multiple pedestrian and vehicle scenario; and research on interaction modes and objects during the interaction process remains relatively limited in depth and scope. To tackle these challenges, a novel graph convolution network combining spatiotemporal self-attention and mutual information (STSAMI-GCN) is designed for predicting pedestrian trajectories. First, to model the spatiotemporal interaction between pedestrians and vehicles, we build a spatiotemporal graph interaction module that integrates graph convolutional networks and self-attention mechanisms. Second, to filter redundant interactions and optimize feature extraction in the spatiotemporal graph interaction module, a mutual information graph network module is designed as an auxiliary network, which can reduce information redundancy and simplify graph complexity. In addition, to address the problem of propagation and accumulation of prediction errors, we design a trajectory decoder to generate future trajectories. Finally, a suitable dataset for our research scenario is built to validate the proposed model. We also evaluate it on two publicly available datasets. Experimental results show that, in the multiple pedestrian and vehicle scenario, STSAMI-GCN can be used to predict the future trajectories of multiple pedestrians, and to predict socially acceptable future trajectories. Specifically, STSAMI-GCN achieves 0.25 and 0.27 average and final deviation error, respectively, and outperforms various mainstream methods. Furthermore, ablation studies demonstrate the effectiveness of the spatiotemporal dual self-attention mechanism and mutual information graph network in improving pedestrian-trajectory prediction accuracy.

Multi-Scale Learnable Gabor Transform for Pedestrian Trajectory Prediction From Different Perspectives

Multi-Scale Learnable Gabor Transform for Pedestrian Trajectory Prediction From Different Perspectives

M2Tames: Interaction and Semantic Context Enhanced Pedestrian Trajectory Prediction

Autonomous driving pays considerable attention to pedestrian trajectory prediction as a crucial task. Constructing effective pedestrian trajectory prediction models depends heavily on utilizing the motion characteristics of pedestrians, along with their interactions among themselves and between themselves and their environment. However, traditional trajectory prediction models often fall short of capturing complex real-world scenarios. To address these challenges, this paper proposes an enhanced pedestrian trajectory prediction model, M2Tames, which incorporates comprehensive motion, interaction, and semantic context factors. M2Tames provides an interaction module (IM), which consists of an improved multi-head mask temporal attention mechanism (M2Tea) and an Interaction Inference Module (I2). M2Tea thoroughly characterizes the historical trajectories and potential interactions, while I2 determines the precise interaction types. Then, IM adaptively aggregates useful neighbor features to generate a more accurate interactive feature map and feeds it into the final layer of the U-Net encoder to fuse with the encoder’s output. Furthermore, by adopting the U-Net architecture, M2Tames can learn and interpret scene semantic information, enhancing its understanding of the spatial relationships between pedestrians and their surroundings. These innovations improve the accuracy and adaptability of the model for predicting pedestrian trajectories. Finally, M2Tames is evaluated on the ETH/UCY and SDD datasets for short- and long-term settings, respectively. The results demonstrate that M2Tames outperforms the state-of-the-art model MSRL by 2.49% (ADE) and 8.77% (FDE) in the short-term setting and surpasses the optimum Y-Net by 6.89% (ADE) and 1.12% (FDE) in the long-term prediction. Excellent performance is also shown on the ETH/UCY datasets.

Effect of A-Pillar Blind Spots on a Driver's Pedestrian Visibility during Vehicle Turns at an Intersection.

This study aims to elucidate the impact of A-pillar blind spots on drivers' visibility of pedestrians during left and right turns at an intersection. An experiment was conducted using a sedan and a truck, with a professional test driver participating. The driver was instructed to maintain sole focus on a designated pedestrian model from the moment it was first sighted during each drive. The experimental results revealed how the blind spots caused by A-pillars occur and clarified the relationship between the pedestrian visible trajectory distance and specific vehicle windows. The results indicated that the shortest trajectory distance over which a pedestrian remained visible in the sedan was 17.6 m for a far-side pedestrian model during a right turn, where visibility was exclusively through the windshield. For the truck, this distance was 20.9 m for a near-side pedestrian model during a left turn, with visibility through the windshield of 9.5 m (45.5% of 20.9 m) and through the passenger-side window of 11.4 m (54.5% of 20.9 m). Additionally, we quantified the trajectory distances where pedestrians became invisible when the driver's view was obstructed by A-pillars. The sedan exhibited the highest invisibility rate at 46.1% for a far-side pedestrian model during a right turn, followed by the truck at 17.8% for the same model. These findings will be instrumental in developing new driving support systems aimed at enhancing visibility in situations where pedestrians are obscured by A-pillars.

SSAGCN: Social Soft Attention Graph Convolution Network for Pedestrian Trajectory Prediction.

Pedestrian trajectory prediction is an important technique of autonomous driving. In order to accurately predict the reasonable future trajectory of pedestrians, it is inevitable to consider social interactions among pedestrians and the influence of surrounding scene simultaneously, which can fully represent the complex behavior information and ensure the rationality of predicted trajectories obeyed realistic rules. In this article, we propose one new prediction model named social soft attention graph convolution network (SSAGCN), which aims to simultaneously handle social interactions among pedestrians and scene interactions between pedestrians and environments. In detail, when modeling social interaction, we propose a new social soft attention function, which fully considers various interaction factors among pedestrians. Also, it can distinguish the influence of pedestrians around the agent based on different factors under various situations. For the scene interaction, we propose one new sequential scene sharing mechanism. The influence of the scene on one agent at each moment can be shared with other neighbors through social soft attention; therefore, the influence of the scene is expanded both in spatial and temporal dimensions. With the help of these improvements, we successfully obtain socially and physically acceptable predicted trajectories. The experiments on public available datasets prove the effectiveness of SSAGCN and have achieved state-of-the-art results. The project code is available at https://github.com/WW-Tong/ssagcn_for_path_prediction.

A Unified Framework for Pedestrian Trajectory Prediction and Social-Friendly Navigation

A Unified Framework for Pedestrian Trajectory Prediction and Social-Friendly Navigation

GSTGM: Graph, spatial–temporal attention and generative based model for pedestrian multi-path prediction

Pedestrian trajectory prediction in urban environments has emerged as a critical research area with extensive applications across various domains. Accurate prediction of pedestrian trajectories is essential for the safe navigation of autonomous vehicles and robots in pedestrian-populated environments. Effective prediction models must capture both the spatial interactions among pedestrians and the temporal dependencies governing their movements. Existing research primarily focuses on forecasting a single trajectory per pedestrian, limiting its applicability in real-world scenarios characterised by diverse and unpredictable pedestrian behaviours. To address these challenges, this paper introduces the Graph Convolutional Network, Spatial–Temporal Attention, and Generative Model (GSTGM) for pedestrian trajectory prediction. GSTGM employs a spatiotemporal graph convolutional network to effectively capture complex interactions between pedestrians and their environment. Additionally, it integrates a spatial–temporal attention mechanism to prioritise relevant information during the prediction process. By incorporating a time-dependent prior within the latent space and utilising a computationally efficient generative model, GSTGM facilitates the generation of diverse and realistic future trajectories. The effectiveness of GSTGM is validated through experiments on real-world scenario datasets. Compared to the state-of-the-art models on benchmark datasets such as ETH/UCY, GSTGM demonstrates superior performance in accurately predicting multiple potential trajectories for individual pedestrians. This superiority is measured using metrics such as Final Displacement Error (FDE) and Average Displacement Error (ADE). Moreover, GSTGM achieves these results with significantly faster processing speeds.

Study on Nighttime Pedestrian Trajectory-Tracking from the Perspective of Driving Blind Spots

With the acceleration of urbanization and the growing demand for traffic safety, developing intelligent systems capable of accurately recognizing and tracking pedestrian trajectories at night or under low-light conditions has become a research focus in the field of transportation. This study aims to improve the accuracy and real-time performance of nighttime pedestrian-detection and -tracking. A method that integrates the multi-object detection algorithm YOLOP with the multi-object tracking algorithm DeepSORT is proposed. The improved YOLOP algorithm incorporates the C2f-faster structure in the Backbone and Neck sections, enhancing feature extraction capabilities. Additionally, a BiFormer attention mechanism is introduced to focus on the recognition of small-area features, the CARAFE module is added to improve shallow feature fusion, and the DyHead dynamic target-detection head is employed for comprehensive fusion. In terms of tracking, the ShuffleNetV2 lightweight module is integrated to reduce model parameters and network complexity. Experimental results demonstrate that the proposed FBCD-YOLOP model improves lane detection accuracy by 5.1%, increases the IoU metric by 0.8%, and enhances detection speed by 25 FPS compared to the baseline model. The accuracy of nighttime pedestrian-detection reached 89.6%, representing improvements of 1.3%, 0.9%, and 3.8% over the single-task YOLO v5, multi-task TDL-YOLO, and the original YOLOP models, respectively. These enhancements significantly improve the model’s detection performance in complex nighttime environments. The enhanced DeepSORT algorithm achieved an MOTA of 86.3% and an MOTP of 84.9%, with ID switch occurrences reduced to 5. Compared to the ByteTrack and StrongSORT algorithms, MOTA improved by 2.9% and 0.4%, respectively. Additionally, network parameters were reduced by 63.6%, significantly enhancing the real-time performance of nighttime pedestrian-detection and -tracking, making it highly suitable for deployment on intelligent edge computing surveillance platforms.

Block-based construction worker trajectory prediction method driven by site risk

Different from pedestrian trajectory prediction, construction worker trajectories are usually affected by risks and have complex movement patterns. Track point-based prediction methods require high prediction accuracy for safety management. This paper presents a block-based construction worker trajectory prediction method driven by site risk. First, the construction site is divided into multiple blocks and the site safety risk within different blocks is quantified. Second, stopping, large and small turning segments in worker's trajectory are detected to divide the dataset. Finally, a transformer-based trajectory prediction model for construction workers is developed and trained separately for different datasets. The worker's next go-to block and the duration within the next block are predicted. The results show that the accuracy of block direction prediction within 120° reach 93%, and the error of duration prediction can be 0.52 s. The study has theoretical and practical value for promoting block-based safety management and enhancing safety proactivity.

EVALUATING PEDESTRIAN CROSSING ATTRIBUTES AT INTERSECTIONS IN KABUL CITY, AFGHANISTAN: A COMPUTER VISION APPROACH

This study aims to evaluate pedestrian crossing attributes in heterogeneous traffic environments using computer vision. For this purpose, YoloV8 models were optimised to detect pedestrian crossing attributes. Moreover, an OpenCV-based Python programme was developed to track pedestrian trajectories manually. For accuracy, the inverse perspective mapping method is applied to obtain a bird's eye view. Finally, a heatmap of pedestrian trajectories was provided to visualise the pedestrian crossing attributes. The results show that more than three-quarters of pedestrians are engaging in noncompliance crossing behaviours at major intersections in Kabul City, Afghanistan. In addition, pedestrians tend to walk longer, more frequent routes at corners and outside of crosswalks. Furthermore, statistical analysis reveals that pedestrian crossing speed decreased by 5.8% when disobeying crossing rules, indicating the significant effect of pedestrian attributes on crossing speed. In conclusion, this study contributes to a better understanding of pedestrian behaviour in heterogeneous traffic environments using computer vision. The results would provide insightful information to traffic engineers and planners for traffic management.

Vehicle-Pedestrian near miss analysis at signalized mid-block crossings

IntroductionThis study aims to identify the factors related to pedestrian and roadway characteristics that affect vehicle–pedestrian Post Encroachment Time (PET) and Relative Time to Collision (RTTC) under traffic control systems at mid-block pedestrian crossings. MethodologyA total of 112 h of video data were collected using multiple cameras from Pedestrian Hybrid Beacon (PHB) and Rectangular Rapid Flashing Beacon (RRFB) sites. To extract vehicle and pedestrian trajectories and construct an accurate dataset, where each observation corresponds to a specific timeframe, with a recorded speeds of both vehicles and pedestrians, a self-developed cutting-edge Computer Vision (CV) technology was deployed. A bivariate regression approach is employed to capture the relationship between near misses and various factors. Results and ConclusionsThe findings reveal that both pedestrian and roadway characteristics significantly influence PET and RTTC. Pedestrian characteristics, such as gender, clothing color, distraction, waiting time, and crossing speed, significantly affect both PET and RTTC. The presence of children as pedestrians, eye contact with drivers, and pedestrian signal compliance rate has a significant influence on PET. Among roadway characteristics, the presence of a median, hourly traffic flow, and land use diversity of the crossing area were found to be significant determinants of both PET and RTTC. The results indicate that there is no difference in the influence of RRFB and PHB on PET values, but there is a significant difference in the influence of RRFB and PHB on RTTC values. PHB increases RTTC relative to RRFB. Finally, this study enriches existing literature by incorporating unique factors that impact pedestrian safety. Practical ApplicationsThe findings underscore the importance of data-driven approach to pedestrian safety, encouraging transportation agencies to implement targeted and effective safety strategies. In the future, the integration of artificial intelligence (AI) in traffic management and safety systems could greatly benefit from incorporating these findings.

Destination intention estimation-based convolutional encoder-decoder for pedestrian trajectory multimodality forecast

Forecasting pedestrian trajectory is a vital area of research in smart urban mobility, which can be applied to intelligent transportation and intelligent surveillance. Current approaches employ conditional variational autoencoders to model future trajectory multimodality. However, these methods generate multi-modal trajectories for one single destination, ignoring the trajectory multimodality caused by the uncertainty of the pedestrians’ destination intention. Besides, they can lead to mode collapse and training instability. To address this issue, we propose a novel destination intention estimation-based convolutional encoder-decoder framework for multimodal trajectory forecast. Specially, we design a destination intention estimator to forecast pedestrian future destination intentions at the last time step. Then, we devise a trajectory decoder module to forecast pedestrian trajectories at each time step with the assistance of the destination intentions. To evaluate our method, we perform experiments on publicly available benchmark datasets and demonstrate that our proposed method achieves the superior results compared with state-of-the-art approaches.

Impact of Perception Errors in Vision-Based Detection and Tracking Pipelines on Pedestrian Trajectory Prediction in Autonomous Driving Systems.

Pedestrian trajectory prediction is crucial for developing collision avoidance algorithms in autonomous driving systems, aiming to predict the future movement of the detected pedestrians based on their past trajectories. The traditional methods for pedestrian trajectory prediction involve a sequence of tasks, including detection and tracking to gather the historical movement of the observed pedestrians. Consequently, the accuracy of trajectory prediction heavily relies on the accuracy of the detection and tracking models, making it susceptible to their performance. The prior research in trajectory prediction has mainly assessed the model performance using public datasets, which often overlook the errors originating from detection and tracking models. This oversight fails to capture the real-world scenario of inevitable detection and tracking inaccuracies. In this study, we investigate the cumulative effect of errors within integrated detection, tracking, and trajectory prediction pipelines. Through empirical analysis, we examine the errors introduced at each stage of the pipeline and assess their collective impact on the trajectory prediction accuracy. We evaluate these models across various custom datasets collected in Taiwan to provide a comprehensive assessment. Our analysis of the results derived from these integrated pipelines illuminates the significant influence of detection and tracking errors on downstream tasks, such as trajectory prediction and distance estimation.

A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory

A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory

Multi Attention Generative Adversarial Network for Pedestrian Trajectory Prediction Based on Spatial Gridding

Multi Attention Generative Adversarial Network for Pedestrian Trajectory Prediction Based on Spatial Gridding

Physics constrained pedestrian trajectory prediction with probability quantification

Accurately understanding and predicting the future trajectories of pedestrians around autonomous vehicles is a major challenge. Due to the uncertainty and diversity of pedestrian trajectories, current research focuses on the multimodality of trajectory prediction. Currently, multimodal pedestrian prediction methods mainly use deep generative networks to generate mutually independent trajectories through independent sampling strategy, thus focusing on modes with a large number of samples. Moreover, deep generative networks are black-box models that are entirely data-driven and cannot effectively explain trajectory generation. In addition, current research lacks an effective measure for each trajectory. Therefore, in our paper, we propose a physics constrained pedestrian trajectory prediction with probability quantification. We divide multimodal trajectory prediction into two phases: trajectory generation phase and trajectory selection phase. During the trajectory generation phase, rather than directly predicting trajectories, we incorporate a differential constraint module to ensure that the generated trajectories adhere to pedestrian motion laws. This approach enhances the interpretability of the model prediction process. Subsequently, we generate a set of candidate trajectory proposals with specific correlations through the correlated sampling module. During the trajectory selection phase, a probability selection module is proposed to establish explicit probability distributions for the candidate trajectory proposals and to select the proposal with the highest probability as the final output. Extensive experiments on a public real-world pedestrian trajectory dataset show that our proposed model exhibits significant advantages over existing models in multimodal trajectory prediction, which not only effectively reduces the error but also mitigates mode collapse. Moreover, we provide probabilities for each trajectory to better capture the model uncertainty and provide more comprehensive information for downstream decision-making systems.