I’m trying to connect an IMX477 camera module to the Jetson Orin 8GB (JetPack 6.2.1). This same camera previously worked fine on a Jetson Nano (the only difference is ribbon cable since orin has smaller CSI port), but on the Orin it’s not being detected at all.
What i have checked:
I Should expect I2C detects even without device tree support, right? do I need to install a custom device tree overlay?
*** Please note that this reply is generated by LLM automatically ***
To troubleshoot the issue with connecting an IMX477 camera module to the Jetson Orin 8GB with JetPack 6.2.1, let’s break down the steps you’ve taken and provide additional guidance.
Camera doesn’t appear on any I2C bus: This is a crucial step in verifying that the camera is not being detected by the system. The IMX477 camera module uses the I2C interface for communication, so it’s expected that it should appear on one of the I2C buses. Since it’s not being detected, it’s possible that there’s an issue with the camera module, the ribbon cable, or the CSI port on the Jetson Orin.
No dev/video devices are listed: This suggests that the camera is not being recognized by the system, which is consistent with the I2C detection issue.
Tried on CAM0: You’ve tried connecting the camera to the CAM0 interface, which is the correct interface for the IMX477 camera module.
Expect I2C detects even without device tree support: Yes, that’s correct. The I2C detection should work even without device tree support. However, device tree support is required for the camera to function properly.
To resolve the issue, you can try the following:
In comparison to the Jetson Nano, the Jetson Orin has a different CSI port and may require a different device tree overlay. Additionally, the Jetson Orin has a more complex camera architecture, which may require additional configuration.
To further troubleshoot the issue, you can try the following:
i2cdetect command: Run the i2cdetect command to scan the I2C buses and see if the camera module is detected.v4l2-ctl command: Run the v4l2-ctl command to query the camera module and see if it’s recognized by the system.By following these steps, you should be able to troubleshoot the issue and get the IMX477 camera module working on the Jetson Orin 8GB with JetPack 6.2.1.
*** Please give the thumbs up if you get answers you like. Or provide feedback to help us improve the answer. ***
You should be able enable the IMX477 by jetson-io to verify again.
Thanks
thanks it solved by modifying in jetson-io.
but it seems like gstreamer is not supported on jetson orin for imx477, if yes what’s the alternative way?
Hello @mshey904,
Sorry to hear you are having issues with the IMX477 camera on your Jetson Orin.
Let me ask you a couple questions to better understand your situation.
dmesg | grep imx?best regards,
Andrew
Embedded Software Engineer at ProventusNova
Hi ProventusNova,
Sorry I mean i have issue with gstreamer via nvarguscamerasrc. I saw some errors in argus daemon log after run the gstreamer with nvarguscamerasrc:
> gst-launch-1.0 nvarguscamerasrc sensor-id=0 num-buffers=1 ! \
'video/x-raw(memory:NVMM),width=1920,height=1080,framerate=30/1' ! \
fakesink
Log:
> sudo journalctl -u nvargus-daemon --since "5 minutes ago" | grep -i camera
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: === NVIDIA Libargus Camera Service (0.99.33)=== Listening for connections...=== gst-launch-1.0[3849]: Connection established (FFFF9962B840)OFParserListModules: module list: /proc/device-tree/tegra-camera-platform/modules/module0
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: OFParserListModules: module list: /proc/device-tree/tegra-camera-platform/modules/module1
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: OFParserGetVirtualDevice: NVIDIA Camera virtual enumerator not found in proc device-tree
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: ---- imager: Found override file [/var/nvidia/nvcam/settings/camera_overrides.isp]. ----
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: ---- imager: Found override file [/var/nvidia/nvcam/settings/camera_overrides.isp]. ----
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: (NvCamV4l2) Error ModuleNotPresent: V4L2Device not available (in /dvs/git/dirty/git-master_linux/camera/utils/nvcamv4l2/v4l2_device.cpp, function findDevice(), line 256)
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: (NvCamV4l2) Error ModuleNotPresent: (propagating from /dvs/git/dirty/git-master_linux/camera/utils/nvcamv4l2/v4l2_device.cpp, function initialize(), line 60)
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: (NvOdmDevice) Error ModuleNotPresent: (propagating from dvs/git/dirty/git-master_linux/camera-partner/imager/src/devices/V4L2SensorViCsi.cpp, function initialize(), line 111)
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: NvPclInitializeDrivers: error: Failed to init camera sub module v4l2_sensor
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: SCF: Error BadParameter: (propagating from src/api/CameraDriver.cpp, function addSourceByIndex(), line 382)
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: SCF: Error BadParameter: (propagating from src/api/CameraDriver.cpp, function getSource(), line 554)
Nov 10 21:55:38 ubuntu nvargus-daemon[868]: === gst-launch-1.0[3849]: CameraProvider initialized (0xffff94b1bad0)CAM: serial no file already exists, skips storing againLSC: LSC surface is not based on full res!
> sudo dmesg | grep imx
[ 10.331335] imx477 9-001a: tegracam sensor driver:imx477_v2.0.6
[ 10.631981] imx477 9-001a: imx477_board_setup: error during i2c read probe (-121)
[ 10.632013] imx477 9-001a: board setup failed
[ 10.632078] imx477: probe of 9-001a failed with error -121
[ 10.632301] imx477 10-001a: tegracam sensor driver:imx477_v2.0.6
[ 10.933299] tegra-camrtc-capture-vi tegra-capture-vi: subdev imx477 10-001a bound
[ 119.736245] tegra_aconnect(E) cfg80211(E) pwm_tegra_tachometer(OE) snd_hda_tegra(E) nv_imx477(OE) snd_hda_codec(E) snd_hda_core(E) at24(E) mc_hwpm(OE) spi_tegra114(E) host1x_fence(OE) nvhost_vi5(OE) nvhost_isp5(OE) nvhost_nvcsi_t194(OE) tegra_camera(OE) v4l2_dv_timings(E) nvhost_nvcsi(OE) capture_ivc(OE) snd_soc_tegra_machine_driver(OE) snd_soc_tegra_utils(OE) snd_soc_simple_card_utils(E) nvidia(OE) tegra234_oc_event(OE) crct10dif_ce(E) v4l2_fwnode(E) tegra_camera_platform(OE) tegra_camera_rtcpu(OE) nvpmodel_clk_cap(OE) v4l2_async(E) thermal_trip_event(OE) videobuf2_dma_contig(E) ivc_bus(OE) videobuf2_memops(E) nvidia_vrs_pseq(OE) hsp_mailbox_client(OE) videobuf2_v4l2(E) ivc_ext(OE) tegra_dce(OE) videobuf2_common(E) nvhost_capture(OE) tsecriscv(OE) videodev(E) host1x_nvhost(OE) mc(E) governor_userspace(E) tegra_drm(OE) tegra_wmark(OE) nvhwpm(OE) cec(E) drm_kms_helper(E) tpm_ftpm_tee(E) nvidia_p2p(OE) ina3221(E) nvgpu(OE) governor_pod_scaling(OE) host1x(OE) mc_utils(OE) nvmap(OE)
Hello @mshey904,
Understood. Thanks for sharing the extra details.
Seems like the driver is actually loading successfully.
And it’s finding 1 IMX477 camera module connected to your board.
You mentioned on your original post that there are no video devices registered under /dev/video*. Is that still the same ?
If there is now a video device registered, can you try capturing with v4l2-ctl to validate CSI config ?
v4l2-ctl -d /dev/video0 --set-fmt-video=width=1920,height=1080,pixelformat=RG10 --stream-mmap
Please check width, height and pixel format matches something your camera supports.
best regards,
Andrew
Embedded Software Engineer at ProventusNova
No, I fixed that issue by modifying with jetson-io.py
This is the captured image from my keyboard. looks cool and awful :)
4k:
full hd:
Thanks for sharing the images.
So just to recap.
Those images you shared, did you captured them with v4l2-ctl and then post-processed them ? Or are you capturing those with nvarguscamera?
best regards,
Andrew
Embedded Software Engineer at ProventusNova
Yes, I captured with v4l2-ctl. i am not able to capture with nvarguscamera. the image result with nvarguscamera is a corrupted frame.
Understood.
And does the image captured with v4l2-ctl looks good after processing it ?
Or does it show the same weird behavior ?
best regards,
Andrew
Embedded Software Engineer at ProventusNova
How to processing captured image with v4l2-ctl?
To process raw images captured with v4l2-ctl you can use several techniques:
If you want you can share a raw file captured with v4l2-ctl and I can take a look too.
best regards,
Andrew
Embedded Software Engineer at ProventusNova
Here the raw file:
image_3840x2160.raw.gz (23.4 MB)
v4l2-ctl -d /dev/video0 --set-fmt-video=width=3840,height=2160,pixelformat=RG10 --stream-mmap --stream-count=1 --stream-to=raw_image2.raw
I added a .gz at the end of the file name to be able to upload the file, which should be removed after the download.
and this is sensor info:
$ v4l2-ctl -d /dev/video0 --all
Driver Info:
Driver name : tegra-video
Card type : vi-output, imx477 10-001a
Bus info : platform:tegra-capture-vi:1
Driver version : 5.15.148
Capabilities : 0x84200001
Video Capture
Streaming
Extended Pix Format
Device Capabilities
Device Caps : 0x04200001
Video Capture
Streaming
Extended Pix Format
Media Driver Info:
Driver name : tegra-camrtc-ca
Model : NVIDIA Tegra Video Input Device
Serial :
Bus info :
Media version : 5.15.148
Hardware revision: 0x00000003 (3)
Driver version : 5.15.148
Interface Info:
ID : 0x0300000b
Type : V4L Video
Entity Info:
ID : 0x00000009 (9)
Name : vi-output, imx477 10-001a
Function : V4L2 I/O
Pad 0x0100000a : 0: Sink
Link 0x0200000f: from remote pad 0x1000003 of entity '13e00000.host1x:nvcsi@15a00000-' (Unknown sub-device (0002000a)): Data, Enabled
Priority: 2
Video input : 0 (Camera 1: ok)
Format Video Capture:
Width/Height : 4032/3040
Pixel Format : 'RG10' (10-bit Bayer RGRG/GBGB)
Field : None
Bytes per Line : 8064
Size Image : 24514560
Colorspace : sRGB
Transfer Function : Default (maps to sRGB)
YCbCr/HSV Encoding: Default (maps to ITU-R 601)
Quantization : Default (maps to Full Range)
Flags :
Streaming Parameters Video Capture:
Capabilities : timeperframe
Frames per second: 21.000 (21/1)
Read buffers : 0
Camera Controls
group_hold 0x009a2003 (bool) : default=0 value=0 flags=execute-on-write
sensor_mode 0x009a2008 (int64) : min=0 max=2 step=1 default=0 value=0 flags=slider
gain 0x009a2009 (int64) : min=16 max=357 step=1 default=16 value=352 flags=slider
exposure 0x009a200a (int64) : min=13 max=683710 step=1 default=2495 value=33333 flags=slider
frame_rate 0x009a200b (int64) : min=2000000 max=30000000 step=1 default=30000000 value=30000000 flags=slider
sensor_configuration 0x009a2032 (u32) : min=0 max=4294967295 step=1 default=0 dims=[22] flags=read-only, volatile, has-payload
sensor_mode_i2c_packet 0x009a2033 (u32) : min=0 max=4294967295 step=1 default=0 dims=[1026] flags=read-only, volatile, has-payload
sensor_control_i2c_packet 0x009a2034 (u32) : min=0 max=4294967295 step=1 default=0 dims=[1026] flags=read-only, volatile, has-payload
bypass_mode 0x009a2064 (intmenu): min=0 max=1 default=0 value=1 (1 0x1)
0: 0 (0x0)
1: 1 (0x1)
override_enable 0x009a2065 (intmenu): min=0 max=1 default=0 value=1 (1 0x1)
0: 0 (0x0)
1: 1 (0x1)
height_align 0x009a2066 (int) : min=1 max=16 step=1 default=1 value=1
size_align 0x009a2067 (intmenu): min=0 max=2 default=0 value=0 (1 0x1)
0: 1 (0x1)
1: 65536 (0x10000)
2: 131072 (0x20000)
write_isp_format 0x009a2068 (int) : min=1 max=1 step=1 default=1 value=1
sensor_signal_properties 0x009a2069 (u32) : min=0 max=4294967295 step=1 default=0 dims=[30][18] flags=read-only, has-payload
sensor_image_properties 0x009a206a (u32) : min=0 max=4294967295 step=1 default=0 dims=[30][16] flags=read-only, has-payload
sensor_control_properties 0x009a206b (u32) : min=0 max=4294967295 step=1 default=0 dims=[30][36] flags=read-only, has-payload
sensor_dv_timings 0x009a206c (u32) : min=0 max=4294967295 step=1 default=0 dims=[30][16] flags=read-only, has-payload
low_latency_mode 0x009a206d (bool) : default=0 value=0
preferred_stride 0x009a206e (int) : min=0 max=65535 step=1 default=0 value=0
override_capture_timeout_ms 0x009a206f (int) : min=-1 max=2147483647 step=1 default=2500 value=2500
sensor_modes 0x009a2082 (int) : min=0 max=30 step=1 default=30 value=2 flags=read-only
Thanks in advance.
Hello @mshey904,
Thanks for providing the captured file.
By doing some initial checks, it seems like although you are setting width and height to 3840x2160, the driver is actually providing 4032x3040 which is what it actually reports.
If you check the file size in bytes, you will get exactly what is configured for Image Size in the driver:
wc -c < image_3840x2160.raw
24514560
And if you divide that by 2 bytes each pixel requires since we are dealing with RG10, and then you divide it once more by 4032 which should be actual width, you get 3040 which is the reported hight. This means that at least in terms of data captured you have it properly configured for 4K. Although if you are trying to capture smaller resolutions you might be still getting full 4K image.
As per the purple-ish image you reported as a result of 4K capture, it seems like a possible problem with the ISP configuration file. Do you have any custom ISP config file we could provide the NVIDIA board to improve color ?
Now, when it comes to the issue you reported when capturing full HD, can you provide a raw file for that scenario ?
best regards,
Andrew
Embedded Software Engineer at ProventusNova
No, I don’t have any custom ISP config file.
This is raw file for Captured full HD. Here you go:
v4l2-ctl -d /dev/video0 --stream-mmap --stream-count=1 --stream-to=image_1920x1080.raw —set-fmt-video=width=1920,height=1080
image_1920x1080.raw.gz (23.4 MB)
I don’t know why it is the same size as 4K.
Hello @mshey904,
Interesting.
That might be the issue for Full HD, given that if the Jetson capture subsystem is expecting full hd, but then for some reason the camera is providing 4K, then those type of issues can be observed.
One of my colleagues mentioned that he saw a similar error on a different forum, and this was the solution that the person we were supporting found to work for them. You might want to give it a try.
And for 4K I would suggest you try this ISP configuration file:
camera_overrides.isp.gz (104.4 KB)
Note that I applied the same trick as you with the .gz file extension, please remove before use.
Also I would suggest you try one fix at the time.
I would first try the forum fix and then if 4K is still broke, you can try the config file.
Please keep me posted as you run the different tests.
best regards,
Andrew
Embedded Software Engineer at ProventusNova
I tried the forum fix:
orin@ubuntu:~$ bash install_full.sh -m imx477
install_full.sh: line 19: warning: command substitution: ignored null byte in input
NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
--2025-11-18 14:06:40-- https://github.com/ArduCAM/MIPI_Camera/releases/download/v0.0.3/modules.txt
Resolving github.com (github.com)... 140.82.121.3
Connecting to github.com (github.com)|140.82.121.3|:443... connected.
HTTP request sent, awaiting response... 302 Found
Location: https://release-assets.githubusercontent.com/github-production-release-asset/186627215/516f2e56-d6c2-45d7-b970-a03826464b35?sp=r&sv=2018-11-09&sr=b&spr=https&se=2025-11-18T11%3A34%3A30Z&rscd=attachment%3B+filename%3Dmodules.txt&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2025-11-18T10%3A34%3A06Z&ske=2025-11-18T11%3A34%3A30Z&sks=b&skv=2018-11-09&sig=H8JB7GizkvTbcTAvLpsxeUDyFO1%2FNMk9aecSYLP0RVQ%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc2MzQ2MjUwMSwibmJmIjoxNzYzNDYyMjAxLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.Rv2WWAWxOuZ4Ks6kp9MhPvM4PRlyn9zWXyquoWu8TNk&response-content-disposition=attachment%3B%20filename%3Dmodules.txt&response-content-type=application%2Foctet-stream [following]
--2025-11-18 14:06:41-- https://release-assets.githubusercontent.com/github-production-release-asset/186627215/516f2e56-d6c2-45d7-b970-a03826464b35?sp=r&sv=2018-11-09&sr=b&spr=https&se=2025-11-18T11%3A34%3A30Z&rscd=attachment%3B+filename%3Dmodules.txt&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2025-11-18T10%3A34%3A06Z&ske=2025-11-18T11%3A34%3A30Z&sks=b&skv=2018-11-09&sig=H8JB7GizkvTbcTAvLpsxeUDyFO1%2FNMk9aecSYLP0RVQ%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc2MzQ2MjUwMSwibmJmIjoxNzYzNDYyMjAxLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.Rv2WWAWxOuZ4Ks6kp9MhPvM4PRlyn9zWXyquoWu8TNk&response-content-disposition=attachment%3B%20filename%3Dmodules.txt&response-content-type=application%2Foctet-stream
Resolving release-assets.githubusercontent.com (release-assets.githubusercontent.com)... 185.199.109.133, 185.199.111.133, 185.199.110.133, ...
Connecting to release-assets.githubusercontent.com (release-assets.githubusercontent.com)|185.199.109.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 2454 (2.4K) [application/octet-stream]
Saving to: ‘modules.txt’
modules.txt 100%[========================================>] 2.40K --.-KB/s in 0.001s
2025-11-18 14:06:41 (2.50 MB/s) - ‘modules.txt’ saved [2454/2454]
--2025-11-18 14:06:41-- https://github.com/ArduCAM/MIPI_Camera/releases/download/v0.0.3/imx477_links.txt
Resolving github.com (github.com)... 140.82.121.3
Connecting to github.com (github.com)|140.82.121.3|:443... connected.
HTTP request sent, awaiting response... 302 Found
Location: https://release-assets.githubusercontent.com/github-production-release-asset/186627215/56726309-b667-4ca9-93f7-b7835552fb79?sp=r&sv=2018-11-09&sr=b&spr=https&se=2025-11-18T11%3A34%3A39Z&rscd=attachment%3B+filename%3Dimx477_links.txt&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2025-11-18T10%3A34%3A39Z&ske=2025-11-18T11%3A34%3A39Z&sks=b&skv=2018-11-09&sig=ch09m7rrFbDdiWPm5CXaNeT9WUhPDTr%2BpR2%2FeK1axnk%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc2MzQ2MjUwMiwibmJmIjoxNzYzNDYyMjAyLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.iQ_mqyW-2tPDHaZjzqkp8d1TjZI3eq5kOblo0tQxgJ4&response-content-disposition=attachment%3B%20filename%3Dimx477_links.txt&response-content-type=application%2Foctet-stream [following]
--2025-11-18 14:06:42-- https://release-assets.githubusercontent.com/github-production-release-asset/186627215/56726309-b667-4ca9-93f7-b7835552fb79?sp=r&sv=2018-11-09&sr=b&spr=https&se=2025-11-18T11%3A34%3A39Z&rscd=attachment%3B+filename%3Dimx477_links.txt&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2025-11-18T10%3A34%3A39Z&ske=2025-11-18T11%3A34%3A39Z&sks=b&skv=2018-11-09&sig=ch09m7rrFbDdiWPm5CXaNeT9WUhPDTr%2BpR2%2FeK1axnk%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc2MzQ2MjUwMiwibmJmIjoxNzYzNDYyMjAyLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.iQ_mqyW-2tPDHaZjzqkp8d1TjZI3eq5kOblo0tQxgJ4&response-content-disposition=attachment%3B%20filename%3Dimx477_links.txt&response-content-type=application%2Foctet-stream
Resolving release-assets.githubusercontent.com (release-assets.githubusercontent.com)... 185.199.109.133, 185.199.111.133, 185.199.108.133, ...
Connecting to release-assets.githubusercontent.com (release-assets.githubusercontent.com)|185.199.109.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 23980 (23K) [application/octet-stream]
Saving to: ‘imx477_links.txt’
imx477_links.txt 100%[========================================>] 23.42K --.-KB/s in 0.02s
2025-11-18 14:06:42 (1.43 MB/s) - ‘imx477_links.txt’ saved [23980/23980]
--2025-11-18 14:06:42-- https://github.com/ArduCAM/MIPI_Camera/releases/download/v0.0.1-orin-nx/arducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb
Resolving github.com (github.com)... 140.82.121.3
Connecting to github.com (github.com)|140.82.121.3|:443... connected.
HTTP request sent, awaiting response... 302 Found
Location: https://release-assets.githubusercontent.com/github-production-release-asset/186627215/004ffbe2-5c42-4463-a240-d58be261f6de?sp=r&sv=2018-11-09&sr=b&spr=https&se=2025-11-18T11%3A33%3A10Z&rscd=attachment%3B+filename%3Darducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2025-11-18T10%3A32%3A31Z&ske=2025-11-18T11%3A33%3A10Z&sks=b&skv=2018-11-09&sig=M1SN%2BElDI00YFj%2Fi5Lczx%2F8osTQEP01K2NIg3BQmsoY%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc2MzQ2NDAwMywibmJmIjoxNzYzNDYyMjAzLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.7K04t40xIEJ05pcefpykctFUt0pxWsHEj0vTw3c731E&response-content-disposition=attachment%3B%20filename%3Darducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb&response-content-type=application%2Foctet-stream [following]
--2025-11-18 14:06:43-- https://release-assets.githubusercontent.com/github-production-release-asset/186627215/004ffbe2-5c42-4463-a240-d58be261f6de?sp=r&sv=2018-11-09&sr=b&spr=https&se=2025-11-18T11%3A33%3A10Z&rscd=attachment%3B+filename%3Darducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb&rsct=application%2Foctet-stream&skoid=96c2d410-5711-43a1-aedd-ab1947aa7ab0&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skt=2025-11-18T10%3A32%3A31Z&ske=2025-11-18T11%3A33%3A10Z&sks=b&skv=2018-11-09&sig=M1SN%2BElDI00YFj%2Fi5Lczx%2F8osTQEP01K2NIg3BQmsoY%3D&jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmVsZWFzZS1hc3NldHMuZ2l0aHVidXNlcmNvbnRlbnQuY29tIiwia2V5Ijoia2V5MSIsImV4cCI6MTc2MzQ2NDAwMywibmJmIjoxNzYzNDYyMjAzLCJwYXRoIjoicmVsZWFzZWFzc2V0cHJvZHVjdGlvbi5ibG9iLmNvcmUud2luZG93cy5uZXQifQ.7K04t40xIEJ05pcefpykctFUt0pxWsHEj0vTw3c731E&response-content-disposition=attachment%3B%20filename%3Darducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb&response-content-type=application%2Foctet-stream
Resolving release-assets.githubusercontent.com (release-assets.githubusercontent.com)... 185.199.111.133, 185.199.108.133, 185.199.110.133, ...
Connecting to release-assets.githubusercontent.com (release-assets.githubusercontent.com)|185.199.111.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 10521652 (10M) [application/octet-stream]
Saving to: ‘arducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb’
arducam-nvidia-l4t-kernel-t 100%[========================================>] 10.03M 3.70MB/s in 2.7s
2025-11-18 14:06:46 (3.70 MB/s) - ‘arducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb’ saved [10521652/10521652]
[sudo] password for orin:
(Reading database ... 207730 files and directories currently installed.)
Preparing to unpack arducam-nvidia-l4t-kernel-t234-nx-5.15.148-tegra-36.4.7-20251023170635_arm64_imx477.deb ...
Unpacking arducam-nvidia-l4t-kernel (5.15.148-tegra-36.4.7-20251023170635) over (5.15.148-tegra-36.4.7-20251023170635) ...
ls: cannot access 'nv_imx477.ko.bak': No such file or directory
Setting up arducam-nvidia-l4t-kernel (5.15.148-tegra-36.4.7-20251023170635) ...
mv: cannot stat '/boot/arducam/arducam_csi2.ko': No such file or directory
But it did finish with error.
and for appling config:
orin@ubuntu:~$ sudo cp ~/camera_overrides.isp /var/nvidia/nvcam/settings/camera_overrides.isp
orin@ubuntu:~$ v4l2-ctl -d /dev/video0 --set-ctrl override_enable=1
orin@ubuntu:~$ v4l2-ctl -d /dev/video0 --get-ctrl override_enable
override_enable: 1 (1 0x1)
orin@ubuntu:~$ v4l2-ctl -d /dev/video0 --set-fmt-video=width=3840,height=2160,pixelformat=RG10 --stream-mmap --stream-count=1 --stream-to=raw_image_new.raw
Raw result:
raw_image_new.raw.gz (23.4 MB)
Someone told me that The bypass is used by argus to send frames to ISP. When using argus, such as using nvarguscamerasrc with gstreamer, the bypass V4L control is set to 1.
When capturing from V4L interface, you would disable the bypass:
v4l2-ctl ... --set-ctrl=bypass_mode=0 ...
raw_image_new-noBypass.raw.gz (23.4 MB)
Hello @mshey904,
Thanks for sharing the results.
It’s a bummer that the forum answer did not help to fix the issue.
Are RAW FULL HDR frames still the same size as 4K ?
And regarding 4K, can you share an image captured with GStreamer using nvarguscamerasrc after applying the ISP config ?
best regards,
Andrew
Embedded Software Engineer at ProventusNova
Are RAW FULL HDR frames still the same size as 4K ?
yes they are.
I’ll share the file once I’ve finished installing the new jetpack.
Thanks for helping