arclab-hku/ecmd

ECMD: An Event-Centric Multisensory Driving Dataset for SLAM

Website for the ECMD datasets.

Webpage: https://arclab-hku.github.io/ecmd/

Homepase: https://github.com/arclab-hku/Event_based_VO-VIO-SLAM

If you have any suggestions or questions, do not hesitate to propose an issue.

If you find this repositorie is helpful in your research, a simple star or citation of our works should be the best affirmation for us. 😊

ecmd's Issues

Some problems about Spatial Calibration

Hello! Thank you for your wonderful work.
I observed that in the sensor settings, the infrared camera, RGB camera, and event camera are placed on the same horizontal line. How can I achieve precise spatial calibration of the three cameras?

Event Topic name

Hi, I've noticed that the type of events stream topics in the dataset is /dv_ros_msgs/EventArray, while the rpg_dvs_driver defines the type as /dvs_msgs/EventArray. Do you have any instructions on how to get around this? The dvs driver failed to recognize the message type.

Data timestamp issues

Thanks for your great work of the ECMD dataset!

But I found some timestamp issues when using ECMD dataset.

The following figure shows the image of left industial camera, the time surface map of left DVXplorer camera and the middle LiDAR pointclouds with very close timestamps, but it seems that the timestamps of DVXplorer has a large timeshift (the image of industial camera and LiDAR pointclouds indicate that there is still some distance left before the car enters the tunnel, but the the DVXplorer indicate that the car has already entered the tunnel). Besides, the timeshift varies in different sequences. In some sequences, the timeshift is not that obvious.

Dataset Download

Hi, I am interested in your dataset, may I ask where I can download the dataset? And could you provide related paper link? Thanks.

Some problems about Time Synchronization

Hi PEIYU, WaiPang
@KwanWaiPang @cpymaple

Firstly, I would like to express my gratitude for your exceptional work on the ECMD dataset. I am interested in utilizing your dataset for my research and have some questions regarding sensor time synchronization:

1. In the ECMD paper, it is mentioned that the Precision Time Protocol (PTP) was employed for multi-sensor time synchronization, with the clock source being the satellite time provided by the u-blox M8T GNSS receiver. Could you please specify which sensors were involved in the PTP time synchronization process? Did the Infrared Camera, Event Camera, Industrial Camera, and Xsens also participate in this synchronization?

2. I noticed that the primary clock source in your setup was the u-blox M8T GNSS receiver, even though you also have the NovAtel SPAN-CPT. May I ask why the NovAtel SPAN-CPT was not used directly for satellite time synchronization?

Thank you for your time and effort in advancing this field. I look forward to your response and am eager to explore your dataset further.

Best regards,
Kaho

sensor_msgs/CompressedImage

This is a very good job, providing us with data for algorithm verification. Thank you very much. However, I encountered some issues when trying to use /camera_left/image_color/compressed in the downloaded bag file. I couldn't view the images of this topic in RViz, although there is data when using the rostopic echo command. I attempted to convert the compressed image of type sensor_msgs/CompressedImage to sensor_msgs/Image using the following configuration in my launch file, but it still didn't work:
<node name="image_transport" pkg="image_transport" type="republish" args="compressed in:=/camera_left/image_color/compressed raw out:=/camera_left/image_color" />
I saw on Bilibili that you have successfully run lvi-sam's code using this dataset. Could you please guide me on how to modify it to work with this type of image data? Additionally, I couldn't find the noise parameters for IMU calibration. Could you tell me what the random walk noise parameters for the IMU are? Once again, thank you for your work!

关于论文中SLAM评估的小问题

你好
感谢你们的工作！我看到论文中说到使用EVO对多种SLAM算法的精度进行了评估，指标为MPE，单位是百分比，请问具体是如何完成的呢？在EVO的介绍中我只看到无单位，m，角度和弧度的误差评估

GNSS Receiver (Ublox F9P)Data

Hi, thanks for your great work on the ECMD dataset.

Your paper mentioned that your platform has two ublox gnss receiver, but I couldn't find any ublox related topics in the downloaded rosbag file. Have you collected their raw data?

I'm looking forward to hearing back from you. Thank you very much.