Image Stitching for NVIDIA Jetson/Resources/360 data: Difference between revisions

Image Stitching for NVIDIA Jetson/Resources/360 data (view source)

Revision as of 17:40, 6 October 2023

3,328 bytes added , 6 October 2023

no edit summary

Kcarvajal

335

edits

@@ Line 32: / Line 32: @@
 Each folder contains three video files named as the folder with a suffix indication of the sensor id from s0 to s2.
+== Triple videos results ==
+Using the [[RidgeRun_Image_Projector/User_Guide/Calibration | 360 Calibration tool]] the following projection parameters and homography matrix can be obtained.
+<syntaxhighlight lang=bash>
+</syntaxhighlight>
+To watch the stitching result of any of the clip groups, save the above parameters and homography matrix in a JSON file named <code>360-triple.json</code> and run the following commands. This pipeline will save the stitching result in a <code>360_triple_stitched_video.mp4</code> file.
+<syntaxhighlight lang=bash>
+</syntaxhighlight>
+<!--
+An example stitched video of the triple_fisheye_vid1_30s clip group can be found in the following Google Drive file.
+-->
 = Dual Fisheye Videos =
@@ Line 57: / Line 73: @@
 {{Review|Don't forget the links. We can add them to the table. I will also add the calibration and stitched video |efernandez}}
+== Dual videos results ==
+Using the [[RidgeRun_Image_Projector/User_Guide/Calibration | 360 Calibration tool]] the following projection parameters and homography matrix can be obtained.
+<syntaxhighlight lang=bash>
+{
+    "projections": [
+        {
+            "0": {
+                "radius": 750.0,
+                "lens": 187.0,
+                "center_x": 993.0,
+                "center_y": 762.0,
+                "rot_x": 0.0,
+                "rot_y": 0.0,
+                "rot_z": -89.6,
+                "fisheye": true
+            }
+        },
+        {
+            "1": {
+                "radius": 750.3,
+                "lens": 186.0,
+                "center_x": 1044.0,
+                "center_y": 776.0,
+                "rot_x": 0.0,
+                "rot_y": 0.0,
+                "rot_z": 88.7,
+                "fisheye": true
+            }
+        }
+    ],
+    "homographies": [
+        {
+            "images": {
+                "target": 1,
+                "reference": 0
+            },
+            "matrix": {
+                "h00": 1,
+                "h01": 0,
+                "h02": 0.0,
+                "h10": 0,
+                "h11": 1,
+                "h12": 0,
+                "h20": 0,
+                "h21": 0,
+                "h22": 1
+            }
+        }
+    ]
+}
+</syntaxhighlight>
+To watch the stitching result of any of the clip groups, save the above parameters and homography matrix in a JSON file named <code>360-dual.json</code> and run the following commands. This pipeline will save the stitching result in a <code>360_dual_stitched_video.mp4</code> file.
+<syntaxhighlight lang=bash>
+S0_C_X=993
+S0_C_Y=762
+S0_rad=750
+S0_R_X=0
+S0_R_Y=0
+S0_R_Z=-89.6
+S0_LENS=187
+S1_C_X=1044
+S1_C_Y=776
+S1_rad=750
+S1_R_X=0
+S1_R_Y=0
+S1_R_Z=88.7
+S1_LENS=186
+CONFIG_FILE="360-dual.json"
+HOMOGRAPHIES="`cat $CONFIG_FILE | tr -d "\n" | tr -d " "`"
+GST_DEBUG=WARNING gst-launch-1.0 -e -v \
+	cudastitcher name=stitcher homography-list=$HOMOGRAPHIES \
+	filesrc location=360-s0.mp4 ! qtdemux ! queue ! h264parse ! nvv4l2decoder ! queue ! nvvidconv ! rreqrprojector center_x=$S0_C_X center_y=$S0_C_Y radius=$S0_rad rot-y=$S0_R_Y rot-z=$S0_R_Z lens=$S0_LENS name=proj0 !  queue ! stitcher.sink_0 \
+	filesrc location=360-s1.mp4 ! qtdemux ! queue ! h264parse ! nvv4l2decoder ! queue ! nvvidconv !  rreqrprojector center_x=$S1_C_X center_y=$S1_C_Y radius=$S1_rad rot-y=$S1_R_Y rot-x=$S1_R_Y rot-z=$S1_R_Z lens=$S1_LENS name=proj1 !  queue ! stitcher.sink_1 \
+	stitcher.  ! queue ! nvvidconv ! nvv4l2h264enc bitrate=30000000 ! h264parse ! queue !  qtmux ! filesink location=360_dual_stitched_video.mp4
+</syntaxhighlight>
 <noinclude>
 {{Image_Stitching_for_NVIDIA_Jetson/Foot|Data Set/Panoramic data|Examples}}
 </noinclude>