Unsupported combination of input and output array formats in function 'reduce' for a part of tum_rgb_datasets

[Kuan0110]

Hello,
My device is jetson nano, CUDA 10.2, OPENCV 4.1.0. I can build the build.sh. When I try to use ORBSLAM_cuda to run rgbd_datasets, for example rgbd_dataset_freiburg1_xyz, no problems appear.

Camera Parameters:

• fx: 517.306
• fy: 516.469
• cx: 318.643
• cy: 255.314
• k1: 0.262383
• k2: -0.953104
• k3: 1.16331
• p1: -0.005358
• p2: 0.002628
• fps: 30
• color order: RGB (ignored if grayscale)

ORB Extractor Parameters:

• Number of Features: 1000
• Scale Levels: 8
• Scale Factor: 1.2
• Initial Fast Threshold: 20
• Minimum Fast Threshold: 7

Depth Threshold (Close/Far Points): 3.86618

Start processing sequence ...
Images in the sequence: 792

New map created with 833 points

median tracking time: 0.132455
mean tracking time: 0.137917

Saving camera trajectory to CameraTrajectory.txt ...

---

but when I run another dataset rgbd_dataset_freiburg2_desk, at the begining it works well, but near the end of the process the programm breaks off suddenly

---

./build/rgbd_tum Vocabulary/ORBvoc.txt Examples/RGB-D/TUM2.yaml data/rgbd_dataset_freiburg2_desk/ data/rgbd_dataset_freiburg2_desk/association.txt

ORB-SLAM2 Copyright (C) 2014-2016 Raul Mur-Artal, University of Zaragoza.
This program comes with ABSOLUTELY NO WARRANTY;
This is free software, and you are welcome to redistribute it
under certain conditions. See LICENSE.txt.

Input sensor was set to: RGB-D

Loading ORB Vocabulary. This could take a while...
Vocabulary loaded!

Camera Parameters:

• fx: 520.909
• fy: 521.007
• cx: 325.141
• cy: 249.702
• k1: 0.231222
• k2: -0.784899
• k3: 0.917205
• p1: -0.003257
• p2: -0.000105
• fps: 30
• color order: RGB (ignored if grayscale)

ORB Extractor Parameters:

• Number of Features: 1000
• Scale Levels: 8
• Scale Factor: 1.2
• Initial Fast Threshold: 20
• Minimum Fast Threshold: 7

Depth Threshold (Close/Far Points): 3.83944

Start processing sequence ...
Images in the sequence: 2893

New map created with 791 points
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.1.0) /home/kuan/opencv-4.1.0/modules/core/src/matrix_operations.cpp:1116: error: (-210:Unsupported format or combination of formats) Unsupported combination of input and output array formats in function 'reduce'

Aborted (core dumped)

Besides I also use original ORB-SLAM2 code to run these datasets, every time it runs without error. I have searched the 'reduce' in the whole project, one is in Sim3Solver::ComputerCrentroid( ){ ...cv::reduce(P, c, 1, CV_REDUCE_SUM)... }, one is in Fast_gpu.cu( ...reduce<32>... )

Can anybody give some advice to fix it out. Thanks a lot!!!!!!