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 meters. Moreover, the proposed approach showed also a significant generalization capability over totally unobserved testing scenes during the training phase with only 0.58 meters in mean lateral position error.

Recently, the problem of intent and trajectory prediction of vulnerable road users (VRUs) in urban traffic environments has got some attention from the intelligent transportation research community. One of the main challenges that make this problem even harder is the uncertainty exists in the actions of pedestrians in urban traffic environments, as well as the difficulty in inferring their end goals. In this paper, we are proposing a data-driven framework based on inverse reinforcement learning (IRL) and the bidirectional recurrent neural network architecture (B-LSTM) for long-term prediction of VRUs' intention. We evaluated our framework on real-life datasets for agent behavior modeling in traffic environments, and it has achieved an overall average displacement error of only 2.93 and 4.12 pixels over 2.0 and 3.0 s ahead prediction horizons, respectively. In addition, we compared our framework against other baseline models based on sequence prediction models and planning-based approaches. We have outperformed these approaches with the lowest margin of average displacement error of more than 5 pixels. Furthermore, the performance of the proposed framework was evaluated on an additional vehicle-based video sequence dataset for path prediction of pedestrians and it continued to achieve robust results with higher generalization capabilities.

Traffic collisions between kangaroos and motorists are on the rise on Australian roads. According to a recent report, it was estimated that there were more than 20,000 kangaroo vehicle collisions that occurred only during the year 2015 in Australia. In this work, we are proposing a vehicle-based framework for kangaroo detection in urban and highway traffic environment that could be used for collision warning systems. Our proposed framework is based on region-based convolutional neural networks (RCNN). Given the scarcity of labeled data of kangaroos in traffic environments, we utilized our state-of-the-art data generation pipeline to generate 17,000 synthetic depth images of traffic scenes with kangaroo instances annotated in them. We trained our proposed RCNN-based framework on a subset of the generated synthetic depth images dataset. The proposed framework achieved a higher average precision (AP) score of 92% over all the testing synthetic depth image datasets. We compared our proposed framework against other baseline approaches and we outperformed it with more than 37% in AP score over all the testing datasets. Additionally, we evaluated the generalization performance of the proposed framework on real live data and we achieved a resilient detection accuracy without any further fine-tuning of our proposed RCNN-based framework.

Traffic accidents are often inaccurately reported, with incorrect location and disruption duration due to various external factors. This can result in imprecise predictions and inaccurate decision-making in data-driven models. To address these challenges, our study presents a comprehensive framework for traffic disruption segmentation from traffic speed data (obtained from Caltrans Performance Measurements system) in the time-space proximity of reported accidents (from Countrywide Traffic Accident dataset). Furthermore, we evaluate multiple machine learning models on reported, estimated, and manually marked disruption intervals, and demonstrate that our enhanced modelling approach reduces the root mean squared error (RMSE) of traffic accident duration prediction while providing higher similarity with disruptions observed in traffic speed. Our algorithm yields higher disruption detection precision than reported accident timelines. Although using multiple segments offers a slight decrease in the quality of results, it highlights more disruptions. Future research could explore expanding the algorithm’s complexity and applying it to improve traffic incident impact predictions.