/depthai-experiments

Experimental projects we've done with DepthAI.

Primary LanguageJupyter NotebookMIT LicenseMIT

depthai_experiments中文文档

depthai-experiments

Discord Forum Docs

Projects we've done with DepthAI. These can be anything from "here's some code and it works most of the time" to "this is almost a tutorial".

The following list isn't exhaustive (as we randomly add experiments and we may forget to update this list):

Gaze Estimation (here)

Peek.2021-01-28.14-45.mp4

Age and Gender Recognition (here)

Gen2 Age & Gender recognition

Automated Face-Blurring (here)

Blur Face

Spatial Calculation - On Host to Show/Explain Math That Happens in OAK-D for the Spatial Location Calculator (here)

Demo

Multi-camera spatial-detection-fusion (here)

demo

Stereo Depth from Camera and From Host (here)

image

Automatic JPEG Encoding and Saving Based on AI Results (here)

raw_frame example

  • overlay_frame represents a path to RGB frame with detection overlays (bounding box and label)

    raw_frame example

  • cropped_frame represents a path to cropped RGB frame containing only ROI of the detected object

    raw_frame example

An example entries in dataset.csv are shown below

timestamp,label,left,top,right,bottom,raw_frame,overlay_frame,cropped_frame
16125187249289,bottle,0,126,79,300,data/raw/16125187249289.jpg,data/bottle/16125187249289_overlay.jpg,data/bottle/16125187249289_cropped.jpg
16125187249289,person,71,37,300,297,data/raw/16125187249289.jpg,data/person/16125187249289_overlay.jpg,data/person/16125187249289_cropped.jpg
16125187249653,bottle,0,126,79,300,data/raw/16125187249653.jpg,data/bottle/16125187249653_overlay.jpg,data/bottle/16125187249653_cropped.jpg
16125187249653,person,71,36,300,297,data/raw/16125187249653.jpg,data/person/16125187249653_overlay.jpg,data/person/16125187249653_cropped.jpg
16125187249992,bottle,0,126,80,300,data/raw/16125187249992.jpg,data/bottle/16125187249992_overlay.jpg,data/bottle/16125187249992_cropped.jpg
16125187249992,person,71,37,300,297,data/raw/16125187249992.jpg,data/person/16125187249992_overlay.jpg,data/person/16125187249992_cropped.jpg
16125187250374,person,37,38,300,299,data/raw/16125187250374.jpg,data/person/16125187250374_overlay.jpg,data/person/16125187250374_cropped.jpg
16125187250769,bottle,0,126,79,300,data/raw/16125187250769.jpg,data/bottle/16125187250769_overlay.jpg,data/bottle/16125187250769_cropped.jpg
16125187250769,person,71,36,299,297,data/raw/16125187250769.jpg,data/person/16125187250769_overlay.jpg,data/person/16125187250769_cropped.jpg
16125187251120,bottle,0,126,80,300,data/raw/16125187251120.jpg,data/bottle/16125187251120_overlay.jpg,data/bottle/16125187251120_cropped.jpg
16125187251120,person,77,37,300,298,data/raw/16125187251120.jpg,data/person/16125187251120_overlay.jpg,data/person/16125187251120_cropped.jpg
16125187251492,bottle,0,126,79,300,data/raw/16125187251492.jpg,data/bottle/16125187251492_overlay.jpg,data/bottle/16125187251492_cropped.jpg
16125187251492,person,74,38,300,297,data/raw/16125187251492.jpg,data/person/16125187251492_overlay.jpg,data/person/16125187251492_cropped.jpg

Face Mask Detection (here)

COVID-19 mask-no-mask megaAI

Crowd Counting (here)

Image example

Cumulative Object Counting (here)

cumulative object counting

How to Run Customer CV Models On-Device (here)

Concatenate frames

Concat frames

Blur frames

Blur frames

Corner detection

Laplacian corner detection

Semantic Segmentation of Depth (here)

Deeplabv3 Depth GIF

Multi-Class Semantic Segmentation (here)

Multi-class Semantic Segmentation

Depth-Driven Focus (here)

Depth driven focus

Monocular Depth Estimation - Neural Network Based (here)

Image example

Tutorial on How To Display High-Res Object Detections (here)

edit_bb

Running EfficientDet Object Detector On-Camera (here)

Watch the demo

Running EfficientNet Image Classifier On-Camera (here)

result

Facial Expression (Emotion) Recognition On-Camera (here)

Demo

Face Detection On-Camera (libfacedetection) (here)

libfacedetection

Face Recognition On-Camera (here)

Face recognition

Facial Landmarks On-Camera (here)

Facial Landmarks

Fire Detection On-Camera (here)

Fire Detection

Head Posture Detection On-Camera (here)

Head Pose Detection

Human-Machine Safety Example On-Camera (here)

Watch the demo

Human Skeletal Pose Estimation (here)

Gen2 Age & Gender recognition

LaneNet Lane Segmentation On-Camera (here)

LaneNet Lane Segmentation

License Plate Recognition On-Camera (here)

Gen2 License Plates recognition

Lossless Zooming (4K to 1080p Zoom/Crop) On-Camera (here)

Lossless Zooming

Running Mask-RCNN On-Camera (here)

Example

MegaDepth Neural Depth Running On-Camera (here)

MegaDepth

MJPEG Streaming From On-Camera (here)

MJPEG Streaming DepthAI

Class Agnostic Object Detector Running On-Camera (here)

Image example

How to Use Multiple Cameras Simultaneously (here)

Multiple devices per host

How to Sync NN Data with Image Data for Custom Neural Networks (here)

image

Optical Character Recognition in the Wild On-Camera (here)

Text Detection + OCR on DepthAI

Palm Detection On-Camera (here)

Palm Detection

Pedestrian Re-Identification (here)

Pedestrian Re-Identification

People Counting On-Camera (here)

image

People Direction-Tracker and Counter (here)

demo

Playing an On-Camera Encoded Stream on the Host (here)

Encoding demo

Recording and Playing Back Depth in RealSense -Compatible Format (here)

depth gif

Road Segmentation On-Camera (here)

Road Segmentation on DepthAI

Roboflow Integration (here)

oak_roboflow_demo_short.mp4

Social Distancing Example (here)

COVID-19 Social Distancing with DepthAI

Text Blurring On-Device (here)

Text Blurring

Image Classification On-Device (here)

Pedestrian Re-Identification

Facial Key-point Triangulation On-Camera (here)

Stereo Inference GIF

WebRTC Streaming Example (here)

Gen2 WebRTC

YOLO V3 V4 V5 X and P On-Camera (here)

yolo-logo