unmannedlab / lidarnet Goto Github PK

@maskjp @maskjptamu, I have recently read your pre-print for Image/Lidar feature matching (Contrastive Learning of Features between Images and LiDAR). I was wondering if your lab is planning to release the code at some point? I would like to test your method on some airborne data (images/Lidar) that I would like to register.

Hi, Peng Jiang.

Could you please share your code with me? I want to utilize your method on some other datasets. And I guarantee that the code will never be exposed to the public and will not be used for any commercial purposes.

Please help.......

Hey!

Thanks for the great work and releasing the code and dataset. I realized that there are a couple of minor issues in the poses.txt files. I was wondering if you can help me fix them?

1. For some sequences, number of rows in poses.txt is 1 or 2 lines fewer than the number of velodyne scans in the same sequence. The is the case '00', '02', '04', '05', '06', '07', '08', '09', '10', '11', '13', '14', '16', '17', '18', '19', '20', '22', '23', '24', '25', '26', '27', '28', '29', '30', '31', '33', '34', '35', '36', '37', '38', '39', '40', '41', '42', '43', '44', '45', '46', '47', '48', '49', '51', '53', '55', '57', '59', '61', '63', '65', '67', '68', '69', '70'
2. The first entry in poses.txt has very large values and seems to be wrong. This is the case for '16', '19', '59', '68', '69', '70'

How would you suggest to fix these issues?

Hi, Peng Jiang. Could you please share the code with me? I want to see some specific details of the code and learn from it. Thank you!

Hi, Peng Jiang.

Firstly, thank you for your brilliant work!

But I have a question. In Tab. I, there is an object class. I can't find object class in your paper, so I want to know which classes are turned into object class in your paper.

Please help......

Hi @maskjp

Thank you for the interesting work.

I have checked the SemnaticUSL dataset, and it seems that sequence 00 to 08 has some annotation, but they a lot of missing/unlabeled/ignored points.
i.e., ss = np.fromfile("00/labels/000001.label", dtype=np.int32)

np.unique(ss, return_counts=True)
(array([ 0, 44, 50, 70, 71], dtype=int32), array([125133, 474, 4297, 767, 401]))

Can you please tell me which sequence you have used for validating/Evaluating the model on this SemnaticUSL dataset?

Thank you.

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.