You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
First of all, thank you for your inspiring work. My question pertains to the number of points your radar sensor can detect. In our research group, we are using AWR1843BOOST and DCA1000EVM CLI cards. The point cloud data we obtained contains very few points. Typically, only 6-7 points can be detected. Some of these points also represent signals from surrounding objects rather than the person in front of the sensor.
Moreover, the number of points increases when the subject in front of the sensor moves, but returns to the original state when the person remains stationary. Therefore, the point data we obtained does not reflect the person's movement well, which affects the model's performance. When I looked at your data visualization GIFs, it seems that the movement and arm positions of the person can be understood from the point cloud images, and the number of points is quite high.
Have you encountered this problem before? If so, I would greatly appreciate any suggestions you may have for solving this issue.
The text was updated successfully, but these errors were encountered:
Hello sir,
First of all, thank you for your inspiring work. My question pertains to the number of points your radar sensor can detect. In our research group, we are using AWR1843BOOST and DCA1000EVM CLI cards. The point cloud data we obtained contains very few points. Typically, only 6-7 points can be detected. Some of these points also represent signals from surrounding objects rather than the person in front of the sensor.
Moreover, the number of points increases when the subject in front of the sensor moves, but returns to the original state when the person remains stationary. Therefore, the point data we obtained does not reflect the person's movement well, which affects the model's performance. When I looked at your data visualization GIFs, it seems that the movement and arm positions of the person can be understood from the point cloud images, and the number of points is quite high.
Have you encountered this problem before? If so, I would greatly appreciate any suggestions you may have for solving this issue.
The text was updated successfully, but these errors were encountered: