app_helper.py

import cv2 as cv
from model import model
import tensorflow as tf
import numpy as np
from display import draw_bouding_box
import tempfile


def detect_objects(video_file):

    # Output video setup
    output_file = tempfile.NamedTemporaryFile(suffix=".mp4").name

    # Define the codec and create VideoWriter object
    fourcc = cv.VideoWriter_fourcc(*'mp4v')
    fps = 3.0  # Frames per second
    frame_width = 640
    frame_height = 640
    out = cv.VideoWriter(output_file, fourcc, fps, (frame_width, frame_height))

    cam = cv.VideoCapture(video_file)
    count = 1
    while True:
        ret, frame = cam.read()
        if not ret:
            break  # Break the loop if no frame is returned
        if count % 20:
            count += 1
            continue
        count += 1
        frame = cv.resize(frame, (640, 640), interpolation=cv.INTER_CUBIC)
        image = cv.cvtColor(frame, cv.COLOR_BGR2RGB)
        image = tf.expand_dims(image, axis=0)
        y_pred = model.predict(image)
        y_pred = {'boxes': tf.ragged.constant(y_pred['boxes'][y_pred['confidence'] != -1]),
                  'confidence': tf.ragged.constant(y_pred['confidence'][y_pred['confidence'] != -1]),
                  'classes': tf.ragged.constant(y_pred['classes'][y_pred['confidence'] != -1]),
                  'num_detections': np.count_nonzero(y_pred['confidence'] != -1)
                  }

        frame = draw_bouding_box(frame, y_pred)
        out.write(frame)

    cam.release()
    return output_file