ssmem/vdo-slam-data-preprocess

vdo-slam-data-preprocess

vdo-slam-data-preprocess's Issues

pose_gt.txt

would you mind telling me how to generate pose_gt.txt ? I'm looking forward to your early reply, thank you!

error correction

Thanks! I found some errors below:
found error in [gene_kitti_flo.py]

tenVolume = torch.nn.functional.leaky_relu(input=correlation.FunctionCorrelation(tenFirst=tenFirst, tenSecond=tenSecond), negative_slope=0.1, inplace=False)

change to:
tenVolume = torch.nn.functional.leaky_relu(input=correlation.FunctionCorrelation(tenOne=tenFirst, tenTwo=tenSecond), negative_slope=0.1, inplace=False)

label2objectpose.py

Thanks for your vdo-slam-data-preprocess!
Would you mind telling me have you finished writing the label2objectpose.py file of creating objectpose.txt , I got some error, such as

File "label2objectpose.py", line 38
^
SyntaxError: unexpected EOF while parsing

but the line 38 is empty

请问下载的数据集是Tracking下的哪一个

我下载了multi-object tracking这个数据集，找到了图片和label文件，但是没有找到times.txt

the demo in OMD

Hello, can you run OMD demo？ I faced some problems:

OpenCV Error: Assertion failed (npoints >= 4 && npoints == std::max(ipoints.checkVector(2, 5), ipoints.checkVector(2, 6))) in solvePnPRansac, file /tmp/binarydeb/ros-kinetic-opencv3-3.3.1/modules/calib3d/src/solvepnp.cpp, line 253
terminate called after throwing an instance of 'cv::Exception'
what(): /tmp/binarydeb/ros-kinetic-opencv3-3.3.1/modules/calib3d/src/solvepnp.cpp:253: error: (-215) npoints >= 4 && npoints == std::max(ipoints.checkVector(2, 5), ipoints.checkVector(2, 6)) in function solvePnPRansac

It seems like the problem of pnp-method. In fact, I found that it is caused by the few keypoints(only 2-5) in keypoints extract. In addition, not only did I have this problem:

halajun/VDO_SLAM#38

generate_mask.py

Hi @ssmem ,thanks for your work of VDO-dataset, I am trying to use the output of generate_mask.py directly . The issue is that the two objects (cars) have the same shade of color as shown in the figure below. I want a similar output as yours. How do I solve this?

but I am very Confused, the segmentation visualization interface shows instance segmentation. Can you tell me the details of your code implementation, How do I solve this problem? I look forward to your reply！