common_detection.py

# common_detection.py
import cv2
import numpy as np
from PIL import Image

def perform_detection(image, interpreter, labels, input_details, output_details, height, width, floating_model):
    imH, imW, _ = image.shape
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    image_resized = cv2.resize(image_rgb, (width, height))
    input_data = np.expand_dims(image_resized, axis=0)

    input_mean = 127.5
    input_std = 127.5
    if floating_model:
        input_data = (np.float32(input_data) - input_mean) / input_std

    interpreter.set_tensor(input_details[0]['index'], input_data)
    interpreter.invoke()

    boxes = interpreter.get_tensor(output_details[0]['index'])[0]
    classes = interpreter.get_tensor(output_details[1]['index'])[0]
    scores = interpreter.get_tensor(output_details[2]['index'])[0]

    detections = []
    for i in range(len(scores)):
        if (scores[i] > 0.5):
            ymin = int(max(1, (boxes[i][0] * imH)))
            xmin = int(max(1, (boxes[i][1] * imW)))
            ymax = int(min(imH, (boxes[i][2] * imH)))
            xmax = int(min(imW, (boxes[i][3] * imW)))
            
            cv2.rectangle(image, (xmin, ymin), (xmax, ymax), (10, 255, 0), 2)
            object_name = labels[int(classes[i])]
            label = f'{object_name}: {int(scores[i] * 100)}%'
            labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)
            label_ymin = max(ymin, labelSize[1] + 10)
            cv2.rectangle(image, (xmin, label_ymin - labelSize[1] - 10), (xmin + labelSize[0], label_ymin + baseLine - 10), (255, 255, 255), cv2.FILLED)
            cv2.putText(image, label, (xmin, label_ymin - 7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2)

            detections.append([object_name, scores[i], xmin, ymin, xmax, ymax])
    return image