# Smoothed Dataset
### Description
Here you can find the smoothed dataset in CSV format. We provide two version of the smoothed dataset. Each is smoothed using a different smoothing window. The Savitzky-Golay filter requires a **smoothing window** which dictates the number of points used to smooth a current data point.
### Table of Content
1. [Description](#Description)
2. [Smoothing Window](#File-Structure)
3. [Folder Structure](#Folder-Structure)
4. [File Structure](#Smoothing-Window)
### Smoothing Window
We use separately a window of 11 and a window of 21. We specifically chose 11 and 21 because they represent, respectively, 10 and 20 data points excluding the target data point. This in turn corresponds, respectively, to 1 second and 2 seconds of trajectory data respectively. In other words, we use the trajectory data of 1 seconds and 2 seconds to smooth the data. Both datasets can be found in the folder window-11 and window-21 respectively.
**NOTE.** the filter is applied to the Local_X and Local_Y and not the Global_X and Global_Y values since they are based on the california state plane coordinate system.
Below is a figure dipicting the original and the smoothed trajectory, using smoothing window 11, for the Vehicle with ID 2
![Drag Racing](x_y_smoothed_11.png)
Below is a figure dipicting the original and the smoothed trajectory, using smoothing window 21, for the Vehicle with ID 2 trajectory is smother than the previous one.
![Drag Racing](x_y_smoothed_21.png)
### Folder Structure
Each folder contains three main files:
1. 0750_0805_us101_smoothed_*_.zip
2. 0805_0820_us101_smoothed_*_.zip
3. 0820_0835_us101_smoothed_*_.zip
where * is the value set for the smoothing window. Each file contains all the smoothed vehicle trajectories for the following times respectively 7:50 am - 8:05 am, 8:05 am - 8:20 am, 8:20 am - 8:35 am
In addition, you can find three plot images displaying x & y, accelration and velocity before and after smoothing for a sample car from the dataset.
### File Structure
Each file is structured in CSV format i.e. in comma separated values. The columns are ordered in the same manner as the original non-smoothed dataset. Nevertheless for reference and ease of use we rewrite the description of the original dataset here. Each column is described in order of appearance:
* **Vehicle_ID** Vehicle identification number
* **Frame_ID** Frame Identification number
* **Total_Frames** Total number of frames in which the vehicle appears in this data set
* **Global_Time** Elapsed time in milliseconds since Jan 1, 1970.
* **Local_X Lateral** (X) coordinate of the front center of the vehicle in feet with respect to the left-most edge of the section in the direction of travel
* **Local_Y** Longitudinal (Y) coordinate of the front center of the vehicle in feet with respect to the entry edge of the section in the direction of travel
* **Global_X** of the front center of the vehicle in feet based on the coordinate CA State Plane III in NAD83
* **Global_Y** Y Coordinate of the front center of the vehicle in feet based on the coordinate CA State Plane III in NAD83
* **v_Length** Length of vehicle in feet
* **v_Width** Width of vehicle in feet
* **v_Class** Vehicle type: 1 - motorcycle, 2 - auto, 3 - truck
* **v_Vel** Instantaneous velocity of vehicle in feet/second
* **v_Acc** Instantaneous acceleration of vehicle in feet/second square
* **Lane_ID** Current lane position of vehicle. Lane 1 is farthest left lane; lane 5 is farthest right lane. Lane 6 is the auxiliary lane between Ventura Boulevard on-ramp and the Cahuenga Boulevard off-ramp. Lane 7 is the on-ramp at Ventura Boulevard, and Lane 8 is the off-ramp at Cahuenga Boulevard
* **Preceding** Vehicle ID of the lead vehicle in the same lane. A value of '0' represents no preceding vehicle - occurs at the end of the study section and off-ramp due to the fact that only complete trajectories were recorded by this data collection effort
* **Following** Vehicle ID of the vehicle following the subject vehicle in the same lane. A value of '0' represents no following vehicle - occurs at the beginning of the study section and on ramp due to the fact that only complete trajectories were recorded by this data collection effort
* **Space_Headway** Space Headway in feet. Spacing provides the distance between the front-center of a vehicle to the front-center of the preceding vehicle.
* **Time_Headway** Time Headway provides the time in seconds needed to travel from the front-center of a vehicle (at the speed of the vehicle) to the front-center of the preceding vehicle. A headway value of 9999.99 means that the vehicle is traveling at zero speed (congested conditions).
没有合适的资源?快使用搜索试试~ 我知道了~
NGSIM-US-101-trajectory-dataset-smoothing:使用Savitzky-Golay滤波器平滑N...
共20个文件
png:9个
zip:6个
md:3个
需积分: 34 54 下载量 151 浏览量
2021-05-24
14:09:44
上传
评论 14
收藏 348.28MB ZIP 举报
温馨提示
NGSIM US-101数据集平滑 描述 NGSIM US-101数据集平滑功能使用提供了众所周知的轨迹NGSIM US-101数据集的低噪点和平滑版本。 平滑过程分为两个步骤,该过程包括:首先,平滑X和Y值,然后相对于平滑的X,Y值重新计算速度和加速度。 表中的内容 NGSIM US-101数据集 自2005年发布以来,NGSIM US 101数据集一直是研究人员进行轨迹预测的最终开源数据集。包括[1-3]在内的许多研究人员都指出数据集中存在噪声,这主要是由于其具有是从位于加利福尼亚州洛杉矶的俯瞰好莱坞高速公路的建筑物上安装的8台摄像机的视频录像中自动提取的,也称为美国南行101。用于提取NGSIM US-101数据集的软件称为NG-VIDEO软件。 另外,NGSIM文档明确指出: 尚未对数据集进行准确性评估 [我们不对数据完整性提出任何要求。 提供的数据可能存在差距 我们发现,绘制加
资源详情
资源评论
资源推荐
收起资源包目录
NGSIM-US-101-trajectory-dataset-smoothing-master.zip (20个子文件)
NGSIM-US-101-trajectory-dataset-smoothing-master
smoothed-dataset
x_y_smoothed_11.png 110KB
window-21
vel_smoothed_21.png 181KB
0820_0835_us101_smoothed_21_.zip 58.77MB
x_y_smoothed_21.png 118KB
accel_smoothed_21.png 683KB
0750_0805_us101_smoothed_21_.zip 59.39MB
0805_0820_us101_smoothed_21_.zip 58.65MB
x_y_smoothed_21.png 118KB
README.md 5KB
window-11
vel_smoothed_11.png 172KB
x_y_smoothed_11.png 172KB
accel_smoothed_11.png 611KB
0805_0820_us101_smoothed_11_.zip 55.98MB
0820_0835_us101_smoothed_11_.zip 56.04MB
0750_0805_us101_smoothed_11_.zip 56.88MB
acceleration_vehicle_2.png 457KB
README.md 4KB
smothing-code
ngsim_us101_smoothing.py 9KB
README.md 1KB
velocity_smoothing_process_2.gif 110KB
共 20 条
- 1
蓝星神
- 粉丝: 24
- 资源: 4714
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0