openvslam
openvslam copied to clipboard
xdspacelab
Running video is very slow in Jetson nano
Hello, i am using jetson nano to run openvslam and uses stereo camera for it. it is worked well but it is running very slow in jetson nano.
i am using config parameters like this and also for config i take Euroc dataset ref.,
intrinsic parameters after stereo-rectification are written
Camera.name: "temp" Camera.setup: "stereo" Camera.model: "perspective"
new "rectified" matrices is the first three cols of the projection matrix which is calculated with cv::stereoRectify()
e.g. fx = P1[0][0] or P2[0][0], cx = P1[0][2] or P2[0][2]
fy = P1[1][1] or P2[1][1], cy = P1[1][2] or P2[1][2]
Camera.fx: 435.2046959714599 Camera.fy: 435.2046959714599 Camera.cx: 367.4517211914062 Camera.cy: 252.2008514404297
there is no distortion after stereo rectification
Camera.k1: 0.0 Camera.k2: 0.0 Camera.p1: 0.0 Camera.p2: 0.0 Camera.k3: 0.0
focal_x_baseline is -P2[0][3] which is calculated with cv::stereoRectify()
Camera.fps: 30.0 Camera.cols: 640 Camera.rows: 480 Camera.focal_x_baseline: 47.90639384423901
Camera.color_order: "Gray"
#======================#
Stereo Rectification
#======================#
original intrinsic parameters (K, D) and stereo-recitification parameters (R)
matrices (K, R) are written in row-major order
StereoRectifier.K_left: [458.654, 0.0, 367.215, 0.0, 457.296, 248.375, 0.0, 0.0, 1.0] StereoRectifier.D_left: [-0.28340811, 0.07395907, 0.00019359, 1.76187114e-05, 0.0] StereoRectifier.R_left: [0.999966347530033, -0.001422739138722922, 0.008079580483432283, 0.001365741834644127, 0.9999741760894847, 0.007055629199258132, -0.008089410156878961, -0.007044357138835809, 0.9999424675829176] StereoRectifier.K_right: [457.587, 0.0, 379.999, 0.0, 456.134, 255.238, 0.0, 0.0, 1] StereoRectifier.D_right: [-0.28368365, 0.07451284, -0.00010473, -3.555907e-05, 0.0] StereoRectifier.R_right: [0.9999633526194376, -0.003625811871560086, 0.007755443660172947, 0.003680398547259526, 0.9999684752771629, -0.007035845251224894, -0.007729688520722713, 0.007064130529506649, 0.999945173484644]
#================#
ORB Parameters
#================#
Feature.max_num_keypoints: 1000 Feature.scale_factor: 1.2 Feature.num_levels: 8 Feature.ini_fast_threshold: 20 Feature.min_fast_threshold: 7
#========================#
Initializer Parameters
#========================#
Initializer.num_min_triangulated_pts: 100
#===========================#
PangolinViewer Parameters
#===========================#
PangolinViewer.keyframe_size: 0.07 PangolinViewer.keyframe_line_width: 1 PangolinViewer.graph_line_width: 1 PangolinViewer.point_size: 2 PangolinViewer.camera_size: 0.08 PangolinViewer.camera_line_width: 3 PangolinViewer.viewpoint_x: 0 PangolinViewer.viewpoint_y: -0.65 PangolinViewer.viewpoint_z: -1.9 PangolinViewer.viewpoint_f: 400
There is not enough information in this description. What is the dataset you used? What exactly is very slow?
Thanks for your replay. @ymd-stella I am running openvslam in jetson nano using my custom video and this video was recorded with stereo camera. After running ./run_camera_slam, the mapping video is running very slow like approx 4-5 FPS. And also it takes more time for tracking like 200-300 ms in maxn power mode.
I think it's just a problem of CPU and memory performance. You will need to use a profiler to investigate.
Hi @ymd-stella , I did monitoring of RAM, CPU, GPU usage in Jetson nano. I ran on video file and it was using all cpus upto 90%, GPU 30-40% and RAM 75%.
Hi @ymd-stella , I did monitoring of RAM, CPU, GPU usage in Jetson nano. I ran on video file and it was using all cpus upto 90%, GPU 30-40% and RAM 75%.
I am wondering why does your openvslam use GPU??
@surfii3z because i built opencv with cuda.
That's interesting. I have been trying to port openvslam to CUDA too (but not successful so far).
May I ask which part of the pipeline did you change to GPU computation?
@surfii3z because i built opencv with cuda.
That's interesting. I have been trying to port openvslam to CUDA too (but not successful so far).
May I ask which part of the pipeline did you change to GPU computation?
@surfii3z Compile opencv with CUDA
@surfii3z because i built opencv with cuda.
That's interesting. I have been trying to port openvslam to CUDA too (but not successful so far). May I ask which part of the pipeline did you change to GPU computation?
@surfii3z Compile opencv with CUDA
Yeah, I did exactly that, but it doesn't seem to use GPU directly without modifying the source code. Please kindly suggest me if I misunderstood anything.
