the visualization of Social-STGCNN five datasets

[lyy0095]

Hello, when I look into the five datasets(eth/hotel/univ/zara01/zara02) and visualization them with matplotlib, i found they are some kind of similar, as shown below. The five datasets have obvious smilar boundarys, and horizontal movement is more than vertical movement.

I had collected some data below to make a traj-prediction, but my dataset is extremely randomness，without such similarity like five datasets. ( I download these scenes from Youtube and do not have Homography matrix , so my dataset are only in frame coordinates ，not in real world coordinates.)

So, Is there possible to use social-stgcnn in such randomness frame coordinates dataset with good effects? ( training with such dataset is not good, and the traj-inference effects is bad) Or is there any methods to deal with such randomness dataset before social-stgcnn training?

[abduallahmohamed]

I replied by email, thanks!

[chuli97]

您好， 当我查看五个数据集（eth/hotel/univ/zara01/zara02）并使用 matplotlib 可视化它们时，我发现它们有些相似，如下所示。五个数据集有明显的相似边界，水平移动多于垂直移动。

我在下面收集了一些数据来进行轨迹预测，但是我的数据集非常随机，没有五个数据集那样的相似性。（我从 Youtube 下载这些场景，没有 Homography 矩阵，所以我的数据集只有帧坐标，而不是真实世界坐标。）

那么，是否有可能在这样的随机框架坐标数据集中使用social-stgcnn，效果很好？（用这样的数据集训练不好，traj-inference 效果不好）或者在 social-stgcnn 训练之前有什么方法可以处理这种随机性数据集？

您好， 当我查看五个数据集（eth/hotel/univ/zara01/zara02）并使用 matplotlib 可视化它们时，我发现它们有些相似，如下所示。五个数据集有明显的相似边界，水平移动多于垂直移动。

我在下面收集了一些数据来进行轨迹预测，但是我的数据集非常随机，没有五个数据集那样的相似性。（我从 Youtube 下载这些场景，没有 Homography 矩阵，所以我的数据集只有帧坐标，而不是真实世界坐标。）

那么，是否有可能在这样的随机框架坐标数据集中使用social-stgcnn，效果很好？（用这样的数据集训练不好，traj-inference 效果不好）或者在 social-stgcnn 训练之前有什么方法可以处理这种随机性数据集？

Hello, when I look into the five datasets(eth/hotel/univ/zara01/zara02) and visualization them with matplotlib, i found they are some kind of similar, as shown below. The five datasets have obvious smilar boundarys, and horizontal movement is more than vertical movement.

I had collected some data below to make a traj-prediction, but my dataset is extremely randomness，without such similarity like five datasets. ( I download these scenes from Youtube and do not have Homography matrix , so my dataset are only in frame coordinates ，not in real world coordinates.)

So, Is there possible to use social-stgcnn in such randomness frame coordinates dataset with good effects? ( training with such dataset is not good, and the traj-inference effects is bad) Or is there any methods to deal with such randomness dataset before social-stgcnn training?

Hello, I've been learning about trajectory prediction recently, and I want this project to predict the trajectory of my own video data. Can you share your visualization code with me? If you can, please email me: liping971212@163.com , be deeply grateful

[abduallahmohamed]

Hi,

I'm not sure about Social-STGCNN performance on this matter, I'd simply train it with the dataset and see how it goes. For visualization please check: https://github.com/abduallahmohamed/Social-STGCNN/issues/58

Abduallah Mohamed abduallahmohamed.com

On Mon, 25 Apr 2022 at 05:48, chuli97 @.***> wrote:

您好， 当我查看五个数据集（eth/hotel/univ/zara01/zara02）并使用 matplotlib 可视化它们时，我发现它们有些相似，如下所示。五个数据集有明显的相似边界，水平移动多于垂直移动。 [image: 图片] https://user-images.githubusercontent.com/39576105/118383991-68a38180-b635-11eb-8e3b-017eff12c054.png

我在下面收集了一些数据来进行轨迹预测，但是我的数据集非常随机，没有五个数据集那样的相似性。（我从 Youtube 下载这些场景，没有 Homography 矩阵，所以我的数据集只有帧坐标，而不是真实世界坐标。） [image: 图片 (1)] https://user-images.githubusercontent.com/39576105/118384034-a7393c00-b635-11eb-829b-57aba26c653a.png

那么，是否有可能在这样的随机框架坐标数据集中使用social-stgcnn，效果很好？（用这样的数据集训练不好，traj-inference 效果不好）或者在 social-stgcnn 训练之前有什么方法可以处理这种随机性数据集？

您好， 当我查看五个数据集（eth/hotel/univ/zara01/zara02）并使用 matplotlib 可视化它们时，我发现它们有些相似，如下所示。五个数据集有明显的相似边界，水平移动多于垂直移动。 [image: 图片] https://user-images.githubusercontent.com/39576105/118383991-68a38180-b635-11eb-8e3b-017eff12c054.png

我在下面收集了一些数据来进行轨迹预测，但是我的数据集非常随机，没有五个数据集那样的相似性。（我从 Youtube 下载这些场景，没有 Homography 矩阵，所以我的数据集只有帧坐标，而不是真实世界坐标。） [image: 图片 (1)] https://user-images.githubusercontent.com/39576105/118384034-a7393c00-b635-11eb-829b-57aba26c653a.png

那么，是否有可能在这样的随机框架坐标数据集中使用social-stgcnn，效果很好？（用这样的数据集训练不好，traj-inference 效果不好）或者在 social-stgcnn 训练之前有什么方法可以处理这种随机性数据集？

Hello, when I look into the five datasets(eth/hotel/univ/zara01/zara02) and visualization them with matplotlib, i found they are some kind of similar, as shown below. The five datasets have obvious smilar boundarys, and horizontal movement is more than vertical movement. [image: image] https://user-images.githubusercontent.com/39576105/118383991-68a38180-b635-11eb-8e3b-017eff12c054.png

I had collected some data below to make a traj-prediction, but my dataset is extremely randomness，without such similarity like five datasets. ( I download these scenes from Youtube and do not have Homography matrix , so my dataset are only in frame coordinates ，not in real world coordinates.) [image: image (1)] https://user-images.githubusercontent.com/39576105/118384034-a7393c00-b635-11eb-829b-57aba26c653a.png

So, Is there possible to use social-stgcnn in such randomness frame coordinates dataset with good effects? ( training with such dataset is not good, and the traj-inference effects is bad) Or is there any methods to deal with such randomness dataset before social-stgcnn training?

Hello, I've been learning about trajectory prediction recently, and I want this project to predict the trajectory of my own video data. Can you share your visualization code with me? If you can, please email me: @.*** , be deeply grateful

— Reply to this email directly, view it on GitHub https://github.com/abduallahmohamed/Social-STGCNN/issues/49#issuecomment-1108526530, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFIVLG3VHJCQGTL7NAKJOKLVG2IBNANCNFSM446P4MYQ . You are receiving this because you modified the open/close state.Message ID: @.***>