depthai-experiments
depthai-experiments copied to clipboard
luxonis
Experimental projects we've done with DepthAI.
Displays both the `raw` output of a mono camera (left) and the ISP processed `out`. (`raw` output added in https://github.com/luxonis/depthai-python/pull/265) Key controls: ``` 'IOKL' for manual exposure/iso: Control: key[dec/inc] min..max...
MediaPipe selfie segmentation draft pull request. It uses a landscape model that's faster. WIP, need to add joint bilateral filter for better segmentation and NN warnings.
Use blobconverter for the gen2-ocr experiment. 1st stage NN is the text detection model, which can be found on [PINTOs model zoo](https://github.com/PINTO0309/PINTO_model_zoo/tree/main/051_East_Text_Detection). We would preferably upload xml/bin to artifactory and...
I tried to migrate [this example](https://github.com/luxonis/depthai-experiments/tree/master/gen2-color-isp-raw) to latest DepthAI Gen2 API (commit hash `45765d01ad9c7d8d9ae99ca0f76c5b03b706a1c4`), and got the following error after running against this version ``` Traceback (most recent call last):...
With the latest API version (`2.7.2.0`), the `gen2-gaze-estimation` experiment yields an incorrect gaze vector (random gaze direction). Worth checking how can we use the new detection network nodes to optimize...
…nt and replace the purchase link in the Chinese document
Hi, I am using the Luxonis Rpi Compute module 3 and am having some trouble with the depthAI. I replaced the SD card that came with the device with another...
Hi, I'm trying to run a NN model on the RGB preview stream and planned to use the stereo depth to generate the depth of each prediction. Seemed relatively straightforward...
Hello, I have been trying the license plate recognition sample and it is not working as shown in the video. I used the chinese_traffic.mp4 as input and I only get...
