[论文解读] Vehicle trajectory prediction in top-view image sequences based on deep learning method

Zahra Salahshoori Nejad, Hamed Heravi+3 more|arXiv (Cornell University)|Feb 2, 2021

Traffic Prediction and Management Techniques被引用 6

一句话总结

本文提出一种轻量级深度学习模型，用于在鸟瞰图航拍图像序列中进行车辆轨迹预测，采用编码器-解码器架构，并引入社交张量以捕捉周围车辆之间的交互关系。在基于HighD数据集构建的自定义数据集上进行训练，该方法在5秒内的预测中达到1.91的RMSE，相比先前方法在计算复杂度较低的情况下实现了更高的准确性。

ABSTRACT

Annually, a large number of injuries and deaths around the world are related to motor vehicle accidents. This value has recently been reduced to some extent, via the use of driver-assistance systems. Developing driver-assistance systems (i.e., automated driving systems) can play a crucial role in reducing this number. Estimating and predicting surrounding vehicles' movement is essential for an automated vehicle and advanced safety systems. Moreover, predicting the trajectory is influenced by numerous factors, such as drivers' behavior during accidents, history of the vehicle's movement and the surrounding vehicles, and their position on the traffic scene. The vehicle must move over a safe path in traffic and react to other drivers' unpredictable behaviors in the shortest time. Herein, to predict automated vehicles' path, a model with low computational complexity is proposed, which is trained by images taken from the road's aerial image. Our method is based on an encoder-decoder model that utilizes a social tensor to model the effect of the surrounding vehicles' movement on the target vehicle. The proposed model can predict the vehicle's future path in any freeway only by viewing the images related to the history of the target vehicle's movement and its neighbors. Deep learning was used as a tool for extracting the features of these images. Using the HighD database, an image dataset of the road's aerial image was created, and the model's performance was evaluated on this new database. We achieved the RMSE of 1.91 for the next 5 seconds and found that the proposed method had less error than the best path-prediction methods in previous studies.

研究动机与目标

• 通过鸟瞰图图像序列提升自动驾驶车辆的轨迹预测准确性。
• 通过社交张量机制建模周围车辆对目标车辆运动的影响。
• 开发一种计算效率高的模型，适用于自动驾驶系统中的实时部署。
• 构建并利用源自HighD数据库的新型航拍图像数据集，用于训练与评估。
• 在复杂交通场景下的端到端轨迹预测中，相比现有方法降低预测误差。

提出的方法

• 该模型采用编码器-解码器架构，处理交通场景的鸟瞰图图像序列。
• 卷积神经网络（CNN）从序列中的每一帧图像中提取空间特征。
• 社交张量通过编码邻近车辆的相对位置和运动信息，捕捉车辆间的相互关系。
• 解码器通过关注编码后的特征表示和社交张量表示，生成未来的轨迹预测。
• 模型通过在未来的轨迹坐标上使用均方误差（MSE）损失函数，进行端到端训练。
• 构建了一个源自HighD数据集的自定义航拍图像数据集，以支持训练与评估。

实验结果

研究问题

• RQ1 在鸟瞰图图像序列上训练的深度学习模型，能否在复杂交通环境中准确预测车辆轨迹？
• RQ2 社交张量机制在多大程度上能有效建模周围车辆对目标车辆运动的影响？
• RQ3 与最先进方法相比，所提出的方法是否在轨迹预测中实现了更低的预测误差？
• RQ4 该模型在保持高精度的同时，其计算复杂度在多大程度上保持较低水平？
• RQ5 仅使用基于图像的输入，该模型能否在未见过的高速公路场景中实现良好泛化？

主要发现

• 所提出的模型在5秒未来轨迹预测中实现了1.91的RMSE，优于现有方法。
• 社交张量的引入显著提升了预测精度，通过建模车辆间交互关系实现。
• 该模型保持了较低的计算复杂度，适用于自动驾驶系统中的实时部署。
• 源自HighD的自定义航拍图像数据集，为基于图像的轨迹预测模型提供了有效的训练与评估支持。
• 该方法仅依赖目标车辆及邻近车辆的视觉输入，即可在未见过的高速公路场景中实现良好泛化。
• 该模型在无需显式运动模型或超出图像序列的轨迹历史的情况下，展现出对多样化交通条件的鲁棒性与高精度。