Which field is used for remission ?

[rohithsaro]

Dear @maskjp

Thank you for your impressive work. I would like to know which field ( range, intensity, reflectivity ..... ) did you for the dataset and where the values normalized in anyway as i am having trouble with the results after training a network with your dataset. ( Using the same Lidar ).

Also why is the field of view set to 16.6 when the OS1-64 can do 22.5 ?

Eager to hear from you soon.

Regards, Rohith.

[maskjp]

Hi, @rohithsaro,

If I remember correctly, we used intensity.

Sorry, I can't remember clearly. Where did you see the field view is 16.6?

Thanks! Best wishes!

[rohithsaro]

Hi, @maskjp Thank you for replying.

Usually the intensity values in OS1-64 range from 0-7000 but In semanticusl.yaml file, it is mentioned the following:

[proj_remission_mean: 0.20054443 proj_remission_std: 0.17679570000549158 proj_remission_max: 1.0 proj_remission_min: 0.0]

Hence why i asked if there was any normalization done for the intensity values.

As for the field of view, when downloading the zip file containing the datasets, there is a file named OS1-Lidar.yml which has the following:

v_start_angle: 16.6 v_end_angle: -16.6 h_start_anlge: 180 h_end_angle: -180 num_beams: 64 num_hsize: 2048 max_range: 80 min_range: 1 front: False norm_remission: 1000

[maskjp]

Hi, @rohithsaro,

The ouster we used is the first generation. It only has a field of view between 16.6 to -16.6. I clipped the remission maximum to 1000. I believe.

https://data.ouster.io/downloads/datasheets/datasheet-gen1-v2p4-os1.pdf

I hope it helps!

Best wishes!

[rohithsaro]

Hi, @maskjp

When you use the term 'clipped', do you mean you excluded all the points above 1000 or re-valued all points above 1000 as 1000 ?

Best regards

[maskjp]

@rohithsaro, I think I revalued it to 1000

[rohithsaro]

@maskjp Thank you, Is there a reason why you had done this ?

Also as mentioned earlier in the semanticusl.yaml file, the remission_max is 1.0, Wouldn't it have to be 1000 ??