概述

由于自动驾驶和服务机器人等人工智能新兴应用的需求不断增长，拥挤场景中的轨迹预测已成为近年来的一个重要话题。轨迹预测的一项重要挑战是有效地建模社交互动。在过去的几年中，已经提出了几种新颖的方法。然而，这些方法已经在可用数据的不同子集上进行了评估，因此很难客观地比较结果。
TrajNet++，是一个大规模的以交互为中心的基于轨迹的基准测试。不仅包含适当的轨迹采样数据，而且提供统一的广泛评估系统来测试收集的方法以进行公平比较。

标注格式

场景

{“scene”: {“id”: 266, “p”: 254, “s”: 10238, “e”: 10358, “fps”: 2.5, “tag”: 2}}

id: scene id
p: pedestrian ID
s, e: starting and ending frames id of pedestrian “p”
fps: frame rate.
tag: trajectory type. Discussed in detail below.

轨迹

{“track”: {“f”: 10238, “p”: 248, “x”: 13.2, “y”: 5.85, “pred_number”: 0, “scene_id”: 123}}

f: frame id
p: pedestrian ID
x, y: x and y coordinates in meters of pedestrian “p” in frame “f”.
pred_number: prediction number. This is useful when you are providing multiple predictions as opposed to a single prediction. Max 3 predictions allowed
scene_id: This is useful when you are providing predictions of other agents in the scene as opposed to only primary pedestrian prediction.

轨迹分类

评价

UNIMODAL METRICS: SINGLE PREDICTION

Average Displacement Error (ADE): Average L2 distance between the ground truth and prediction of the primary pedestrian over all predicted time steps. Lower is better.

Final Displacement Error (FDE): The L2 distance between the final ground truth coordinates and the final prediction coordinates of the primary pedestrian. Lower is better

Prediction Collision (Col-I): Calculates the percentage of collisions of primary pedestrian with neighbouring pedestrians in the scene. The model prediction of neighbouring pedestrians is used to check the occurrence of collisions. Lower is better.

Ground Truth Collision (Col-II): Calculates the percentage of collisions of primary pedestrian with neighbouring pedestrians in the scene. The ground truth of neighbouring pedestrians is used to check the occurrence of collisions. Lower is better.

MULTIMODAL METRICS: MULTIPLE PREDICTION

Topk Average Displacement Error (Topk_ADE): Given k output predictions for an observed scene, the metric calculates the ADE of the prediction which is closest to the groundtruth trajectory in terms of ADE. Lower is better. In this challenge, k=3

Topk Final Displacement Error (Topk_FDE): Given k output predictions for an observed scene, the metric calculate the FDE of the prediction which is closest to the groundtruth trajectory in terms of ADE. Lower is better. In this challenge, k=3

Average NLL (NLL): Given n output predictions for an observed scene, the metric calculates the average negative log-likelihood of groundtruth trajectory in the model prediction distribution over the prediction horizon. Higher is better. In this challenge, n=50.

Reference

aicrowd trajnet challenge
Awesome Interaction-aware Behavior and Trajectory Prediction
Human Trajectory Forecasting in Crowds:A Deep Learning Perspective
TrajNet++: Large-scale Trajectory Forecasting Benchmark

Trajectory Forecasting：TrajNet++相关推荐

KaggleM5 Forecasting：传统预测方法与机器学习预测方法对比
本文的出发点在于比较传统预测方法和机器学习预测方法. 本文使用的数据集来自 kaggle:M5 Forecasting - Accuracy. 该数据集包含有 California.Texas.Wis ...
自动驾驶关键环节：行人的行为意图建模和预测(上)
作者 | 黄浴出品 | AI科技大本营(ID:rgznai100) [导读]介绍一下最近行人行为意图建模和预测的研究工作,还是分上下两部分,本文为上半部分. Social LSTM: Human ...
Recursive Social Behavior Graph for Trajectory Prediction（CVPR2020阅读笔记）
Recursive Social Behavior Graph for Trajectory Prediction 摘要 1 引言 2 相关工作 3 方法 4 实验 5 结论用于轨迹预测的递归社会行 ...
CVPR2022论文速览--Vehicle trajectory prediction works, but not everywhere
车辆轨迹预测有效,但并非无处不在原文链接 [2112.03909] Vehicle trajectory prediction works, but not everywhere (arxiv.or ...
【论文解读】AAAI21最佳论文Informer：效果远超Transformer的长序列预测神器！
炼丹笔记干货作者:一元,四品炼丹师 Informer:最强最快的序列预测神器 01 简介在很多实际应用问题中,我们需要对长序列时间序列进行预测,例如用电使用规划.长序列时间序列预测(LSTF)要求 ...
AAAI21最佳论文Informer：效果远超Transformer的长序列预测神器？？？
Informer:最强最快的序列预测神器??? AAAI21最佳论文Informer:效果远超Transformer的长序列预测神器! 01 简介在很多实际应用问题中,我们需要对长序列时间序列进行预 ...
AAAI21最佳论文Informer：效果远超Transformer的长序列预测神器！
Informer:最强最快的序列预测神器 AAAI21最佳论文Informer:效果远超Transformer的长序列预测神器! 作者:一元,公众号:炼丹笔记 01 简介在很多实际应用问题中,我们需 ...
今日arXiv精选 | 35篇顶会论文：ICCV/ CIKM/ ACM MM
关于 #今日arXiv精选这是「AI 学术前沿」旗下的一档栏目,编辑将每日从arXiv中精选高质量论文,推送给读者. TSI: an Ad Text Strength Indicator usi ...
机器人中的轨迹规划（Trajectory Planning ）
Figure. Several possible path shapes for a single joint 五次多项式曲线(quintic polynomial) $$\theta(t)=a_0+ ...

Trajectory Forecasting：TrajNet++

概述