J

Jalen_Xu

Hi Erik,

Thanks for your reply!

In one project we used three yolov5 neural network models simultaneously. One for detecting the vehicle and then intercepting the image of the vehicle target from the original image, one for detecting the license plate region, and finally one for OCR to recognize the license plate numbers and letters.

erik Thanks for your reply! The input frame size is 460x460. I can not find the yolov5s performance in the link. Another thing is that we will deploy neural network models on a camera with a number of 3.

Hi Luxonis Support Team,

We have now deployed three yolov5s neural network models on the OAK-1 camera, but we find that it runs very slowly. It takes a few seconds to process a frame. Is there any way to improve the computational efficiency? Or is there a better solution to improve the arithmetic performance of the processor?

I'm looking forward to your reply. Thank you very much!

Hi Luxonis Support Team,

We would like to use the OAK-1 camera for automobile license plate number recognition. Now that the OAK-1 is equipped with a 4.81mm focal length lens, is it possible to replace it with a 25mm focal length lens? If this is possible, we will have a need for several hundred units.

Hi Luxonis Support Team,

Is there any further progress on the depthai-viewer sdk development?

We want to give our customers a OAK-D-SR camera compatible SDK as soon as possible to help them develop their projects and test.

Thank you very much!

Sorry, I don't know how I can post this question to depthai-experiments. Could you send me a link? Thank you!

Yes, I used the required depthai-sdk version. As shown below.

Hi,

I want to save some RGB images and depth images from SR camera by running record.py file, but it reports an error.

Thanks for your support!

Great! I updated depthai to the latest version and now it can acquire depth images.

As shown below.

Hi Luxonis Support Team,

When I am recording a depth or point cloud, I run the command "python record.py -save pointcloud"(github). I finally capture only the json file.

Thanks!

When I am running SpatialLocationCalculator, I get some error messages.

As shown below.

[1844301071C55D1200] [1.3] [775.632] [system] [error] Attempted to start Mono Left camera - NOT detected! [1844301071C55D1200] [1.3] [775.632] [system] [error] Attempted to start Mono Right camera - NOT detected! Use WASD keys to move ROI. Use 'r' and 'f' to change ROI size.

Thank you very much!

Could you provide us with an example program that can debug parameters like exposure and iso of SR camera? Besides that, how do I get the depth data on each pixel point? Is there an API or example for us to use?

Thanks for your reply!

When I run the color camera control example, I am prompted with some error messages.

The error messages are as follows:
[1844301071C55D1200] [1.4] [1.094] [ColorCamera(0)] [error] Camera not detected on socket: 0 0.5 0.5 1280 360

Thank you very much. I understand it now.

I also want to know if it's because there are still some bugs that are not debugged so I can't connect to the oak-d-sr camera via depthai-viewer? If so, roughly when will these bugs be fixed and then we can connect to oak-d-sr via depthai-viewer?

Thanks for your reply and support!

Now it can get color streams. But if I don't have a SDK interface like depthai-viewer or depthai-demo, it will be inconvenient for me to debug the parameters while shooting images.

Hi  Erik,

Thank you for your reply.

We downloaded the developer version and the debugging results are as follows.

Hello Luxonis Support Team,

We connected the OAK-D-SR model camera to the PC and ran depthai-viewer but it did not work.

Now we try to run "python -mpip install depthai==2.21.2.0.dev0+72cddbb885eb6495ce74ffbe80e1492c612a5452 --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-snapshot-local" to upgrade depthai to the latest version. Then run the cam_test.py file, but it still outputs errors. The image is as follows

Hi Erik,

We have a customer who needs a wide field of view camera to capture the boxes inside a container in real time. The model we recommended to the customer is OAK-D-Pro W POE, but we don't have it at the moment. Could you use this camera to take depth images, point cloud maps and RGB images for us? By the way, what is the depth accuracy of OAK-D-Pro W POE at 1.5m working distance?

Thank you very much for your support!