Co-Creation Challenge Vehicle KIT

/usr/bin/dreamkit/prototypes

/usr/bin/dreamkit/prototypes

{
  "id": "YOUR_UNIQUE_IDENTIFIER",
  "lastdeploy": "CURRENT_DATE_TIME",
  "name": "Discomfort Recognition"
}

import cv2
import logging as log
import datetime as dt
from time import sleep
from PIL import Image
from landingai.predict import Predictor
import json 

# Path to the Haar Cascade file for face detection
cascPath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascPath)

# Configure logging
log.basicConfig(filename='webcam.log', level=log.INFO)

# Initialize the video capture from the default camera (camera index 0)
video_capture = cv2.VideoCapture(0)
anterior = 0
font = cv2.FONT_HERSHEY_SIMPLEX
label_name = "normal"

# Enter your LandingAI API Key and Endpoint ID
endpoint_id = "Endpoint_ID"
api_key = "Your_API_KEY"

while True:
    if not video_capture.isOpened():
        print('Unable to load camera.')
        sleep(5)
        pass

    # Capture frame-by-frame
    ret, frame = video_capture.read()

    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # Detect faces in the grayscale frame
    faces = faceCascade.detectMultiScale(
        gray,
        scaleFactor=1.1,
        minNeighbors=5,
        minSize=(30, 30)
    )

    # Draw rectangles around detected faces
    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)

    if anterior != len(faces):
        anterior = len(faces)
        log.info("faces: " + str(len(faces)) + " at " + str(dt.datetime.now()))

    # Capture a new frame
    check2, frame2 = video_capture.read()

    # Save the current frame as an image
    cv2.imwrite(filename='image.png', img=frame2)

    # Load the saved image
    image = Image.open("image.png")

    # Run inference using LandingAI Predictor
    predictor = Predictor(endpoint_id, api_key=api_key)
    predictions = predictor.predict(image)

    # Extract information from predictions
    score = predictions[0].score
    if predictions[0].label_name:
        label_name = predictions[0].label_name

    # Draw a black background rectangle for displaying the label
    cv2.rectangle(frame, (50, 50), (225, 125), (0, 0, 0), -1)

    # Add the predicted label text to the frame
    cv2.putText(frame, label_name, (50 + int(125/10), 50 + int(75/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)

    # Display the resulting frame with live video and predictions
    cv2.imshow('Video', frame)

    # Check for key presses
    key = cv2.waitKey(1)
    
    if key & 0xFF == ord('s'):
        # Save the current frame as an image
        check, frame = video_capture.read()
        cv2.imshow("Capturing", frame)
        cv2.imwrite(filename='saved_img.jpg', img=frame)
        video_capture.release()
        img_new = cv2.imread('saved_img.jpg', cv2.IMREAD_GRAYSCALE)
        img_new = cv2.imshow("Captured Image", img_new)
        cv2.waitKey(1650)
        print("Image Saved")
        print("Program End")
        cv2.destroyAllWindows()
        break
    elif key & 0xFF == ord('q'):
        # Turn off the camera and exit the program
        print("Turning off camera.")
        video_capture.release()
        print("Camera off.")
        print("Program ended.")
        cv2.destroyAllWindows()
        break

Vehicle.Acceleration.Longitudinal
Vehicle.Acceleration.Lateral
Vehicle.Acceleration.Vertical
Vehicle.AngularVelocity.Roll
Vehicle.AngularVelocity.Pitch
Vehicle.AngularVelocity.Yaw
Vehicle.Cabin.HVAC.AmbientAirTemperature