Trajectory Forecasting：TrajNet++

Bertha 。 2022-09-13 11:29 113阅读 0赞

# 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 #

![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAenh1Y3Zlcg_size_20_color_FFFFFF_t_70_g_se_x_16]  
![在这里插入图片描述][c2444440e162466da59758ee09e7eb63.png]  
![在这里插入图片描述][6ed9503e54bd49dfb16ec9684cf54870.png]

# 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][Human Trajectory Forecasting in Crowds_A Deep Learning Perspective]
 *  [TrajNet++: Large-scale Trajectory Forecasting Benchmark][TrajNet_ Large-scale Trajectory Forecasting Benchmark]

[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAenh1Y3Zlcg_size_20_color_FFFFFF_t_70_g_se_x_16]: /images/20220828/f54cc9a0aa44418d855a554b0bde42fa.png
[c2444440e162466da59758ee09e7eb63.png]: /images/20220828/bb285ae4cb604c0d8e8cd7e5a7264021.png
[6ed9503e54bd49dfb16ec9684cf54870.png]: /images/20220828/de16192fefda4b47b74539e80720f5a1.png
[aicrowd trajnet challenge]: https://www.aicrowd.com/challenges/trajnet-a-trajectory-forecasting-challenge
[Awesome Interaction-aware Behavior and Trajectory Prediction]: https://github.com/jiachenli94/Awesome-Interaction-aware-Trajectory-Prediction
[Human Trajectory Forecasting in Crowds_A Deep Learning Perspective]: https://arxiv.org/pdf/2007.03639.pdf
[TrajNet_ Large-scale Trajectory Forecasting Benchmark]: https://thedebugger811.github.io/publications/2015-10-01-paper-title-number-3/