Pedestrian trajectory prediction is a key technology in many applications such as video surveillance, social robot navigation, and autonomous driving, and significant progress has been made in this research topic. However, there remain two limitations of previous studies. First, with the continuation of time, the prediction error at each time step increases significantly, causing the final displacement error to be impossible to ignore. Second, the prediction results of multiple pedestrians might be impractical in the prediction horizon, i.e., the predicted trajectories might collide with each other. To overcome these limitations, this work proposes a novel trajectory prediction method called CSR, which consists of a cascaded conditional variational autoencoder (CVAE) module and a socially-aware regression module. The cascaded CVAE module first estimates the future trajectories in a sequential pattern. Specifically, each CVAE concatenates the past trajectories and the predicted points so far as the input and predicts the location at the following time step. Then, the socially-aware regression module generates offsets from the estimated future trajectories to produce the socially compliant final predictions, which are more reasonable and accurate results than the estimated trajectories. Moreover, considering the large model parameters of the cascaded CVAE module, a slide CVAE module is further exploited to improve the model efficiency using one shared CVAE, in a slidable manner. Experiments results demonstrate that the proposed method exhibits improvements over state-of-the-art method on the Stanford Drone Dataset (SDD) and ETH/UCY of approximately 38.0% and 22.2%, respectively.


翻译:Pedestrian轨迹预测是许多应用中的关键技术,例如视频监控、社会机器人导航和自主驾驶,而且这一研究主题已经取得了显著进展。然而,以往研究仍有两个局限性。首先,随着时间的延续,每一步的预测错误都会大幅增加,导致最后的迁移错误无法忽视。第二,多个行人的预测结果在预测地平线上可能是不切实际的,即预测的轨迹可能会相互碰撞。为了克服这些限制,这项工作提出了一种叫CSR的新颖的轨迹预测方法,即CSR(CSR),包括一个分级的有条件的自动变换码(CVAE)模块和一个社会觉变色的回归模块。CVAE模块首先按顺序估算未来轨迹。具体地说,每个行人的预测结果将过去的轨迹和预测点混为过去轨迹,从而在下一个步骤中进行输入并预测地点。然后,社会觉悟回归模型从未来估计的轨迹轨迹(CVA-Slational-Slational-lational-lational-lational-lational-lational-lational-lational-leval-leval-lational-lational-leval-lational-lational-lational-lational-lational-lational-lational-lational-lational-lational-lational-lock-lational-lational-lational-lock-lational-l)到一个比C-lislational-lislational-lational-lational-lational-lisld-ld-d-l-ld-ld-ld-ld-l-l-lislislisl-l-l-ld-ld-l-l-l-l-l-l-l-l-l-l-ld-ld-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l-l

0
下载
关闭预览

相关内容

专知会员服务
29+阅读 · 2021年7月30日
CVPR2020接收论文开源代码
专知
30+阅读 · 2020年2月29日
Unsupervised Learning via Meta-Learning
CreateAMind
42+阅读 · 2019年1月3日
视觉机械臂 visual-pushing-grasping
CreateAMind
3+阅读 · 2018年5月25日
条件GAN重大改进!cGANs with Projection Discriminator
CreateAMind
8+阅读 · 2018年2月7日
carla 体验效果 及代码
CreateAMind
7+阅读 · 2018年2月3日
【论文】变分推断(Variational inference)的总结
机器学习研究会
39+阅读 · 2017年11月16日
gan生成图像at 1024² 的 代码 论文
CreateAMind
4+阅读 · 2017年10月31日
Adversarial Variational Bayes: Unifying VAE and GAN 代码
CreateAMind
7+阅读 · 2017年10月4日
Arxiv
0+阅读 · 2021年12月29日
Arxiv
3+阅读 · 2020年11月28日
Learning Discriminative Model Prediction for Tracking
VIP会员
相关VIP内容
专知会员服务
29+阅读 · 2021年7月30日
相关资讯
Top
微信扫码咨询专知VIP会员