import cv2
import numpy as np
import yaml
from openvino.runtime import Core


class SAFETY_DETECT:

    def __init__(self, path, conf_thres=0.35, iou_thres=0.5):
        self.conf_threshold = conf_thres
        self.iou_threshold = iou_thres

        # Initialize model
        self.initialize_model(path)
        self.color_palette = [(np.random.randint(0, 255), np.random.randint(0, 255), np.random.randint(0, 255)) for _ in
                              range(100)]

    def __call__(self, image):
        return self.detect_objects(image)

    def read_config(self, path):
        file_path = path+'/metadata.yaml'
        with open(file_path, 'r', encoding="utf-8") as file:
            config = yaml.safe_load(file)
        return config

    def initialize_model(self, path):
        model_path = path + '/best.xml'
        # Initialize OpenVINO Runtime
        self.core = Core()
        # Load the model
        self.model = self.core.read_model(model=model_path)
        # Compile the model
        self.compiled_model = self.core.compile_model(model=self.model, device_name="CPU")
        # Get input and output layers
        self.input_layer = self.compiled_model.input(0)
        self.output_layer = self.compiled_model.output(0)
        # Get class names
        self.class_names = CLASSES = self.read_config(path)['names']

    def detect_objects(self, frame):
        # 获得模型输出节点

        ir = self.compiled_model.create_infer_request()
        [height, width, _] = frame.shape
        length = max((height, width))
        image = np.zeros((length, length, 3), np.uint8)
        image[0:height, 0:width] = frame
        self.scale = length / 640

        blob = cv2.dnn.blobFromImage(image, scalefactor=1 / 255, size=(640, 640), swapRB=True)
        outputs = ir.infer(blob)[self.output_layer]
        outputs = np.array([cv2.transpose(outputs[0])])
        rows = outputs.shape[1]

        boxes = []
        scores = []
        class_ids = []

        for i in range(rows):
            classes_scores = outputs[0][i][4:]
            (minScore, maxScore, minClassLoc, (x, maxClassIndex)) = cv2.minMaxLoc(classes_scores)
            if maxScore >= 0.25:
                box = [outputs[0][i][0] - (0.5 * outputs[0][i][2]), outputs[0][i][1] - (0.5 * outputs[0][i][3]),
                       outputs[0][i][2], outputs[0][i][3]]
                boxes.append(box)
                scores.append(maxScore)
                class_ids.append(maxClassIndex)



        return boxes, scores, class_ids

    def draw_bounding_box(self, img, class_id, confidence, x, y, x_plus_w, y_plus_h):

        label = f'{self.class_names[class_id]} ({confidence:.2f})'
        color = self.color_palette[class_id]
        cv2.rectangle(img, (x, y), (x_plus_w, y_plus_h), color, 2)
        cv2.putText(img, label, (x - 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

    def draw_detections(self, frame, class_ids, scores, boxes):
        result_boxes = cv2.dnn.NMSBoxes(boxes, scores, 0.25, 0.45, 0.5)

        for i in range(len(result_boxes)):
            index = result_boxes[i]
            box = boxes[index]
            self.draw_bounding_box(frame, class_ids[index], scores[index], round(box[0] * self.scale), round(box[1] * self.scale),
                              round((box[0] + box[2]) * self.scale), round((box[1] + box[3]) * self.scale))
        return frame