opencv调用摄像头并输出位置信息

import cv2
import numpy as np
import onnxruntime
import xlsxwriter
import os

# coco80类别
CLASSES = ['card']


class YOLOV5():
    def __init__(self, onnxpath):
        self.onnx_session = onnxruntime.InferenceSession(onnxpath)
        self.input_name = self.get_input_name()
        self.output_name = self.get_output_name()

    def get_input_name(self):
        input_name = []
        for node in self.onnx_session.get_inputs():
            input_name.append(node.name)
        return input_name

    def get_output_name(self):
        output_name = []
        for node in self.onnx_session.get_outputs():
            output_name.append(node.name)
        return output_name

    def get_input_feed(self, img_tensor):
        input_feed = {}
        for name in self.input_name:
            input_feed[name] = img_tensor
        return input_feed

    def inference(self, img):
        or_img = cv2.resize(img, (640, 640))
        img = or_img[:, :, ::-1].transpose(2, 0, 1)  # BGR2RGB和HWC2CHW
        img = img.astype(dtype=np.float32)
        img /= 255.0
        img = np.expand_dims(img, axis=0)
        input_feed = self.get_input_feed(img)
        pred = self.onnx_session.run(None, input_feed)[0]
        return pred, or_img


# dets:  array [x,6] 6个值分别为x1,y1,x2,y2,score,class
# thresh: 阈值
def nms(dets, thresh):
    x1 = dets[:, 0]
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    areas = (y2 - y1 + 1) * (x2 - x1 + 1)
    scores = dets[:, 4]
    keep = []
    index = scores.argsort()[::-1]

    while index.size > 0:
        i = index[0]
        keep.append(i)
        x11 = np.maximum(x1[i], x1[index[1:]])
        y11 = np.maximum(y1[i], y1[index[1:]])
        x22 = np.minimum(x2[i], x2[index[1:]])
        y22 = np.minimum(y2[i], y2[index[1:]])

        w = np.maximum(0, x22 - x11 + 1)
        h = np.maximum(0, y22 - y11 + 1)

        overlaps = w * h
        ious = overlaps / (areas[i] + areas[index[1:]] - overlaps)
        idx = np.where(ious <= thresh)[0]
        index = index[idx + 1]
    return keep


def xywh2xyxy(x):
    y = np.copy(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2
    y[:, 1] = x[:, 1] - x[:, 3] / 2
    y[:, 2] = x[:, 0] + x[:, 2] / 2
    y[:, 3] = x[:, 1] + x[:, 3] / 2
    return y


def filter_box(org_box, conf_thres, iou_thres):
    org_box = np.squeeze(org_box)
    conf = org_box[..., 4] > conf_thres
    box = org_box[conf == True]
    cls_cinf = box[..., 5:]
    cls = []
    for i in  range(len(cls_cinf)):
        cls.append(int(np.argmax(cls_cinf[i])))
    all_cls = list(set(cls))
    output = []

    for i in range(len(all_cls)):
        curr_cls = all_cls[i]
        curr_cls_box = []
        curr_out_box = []
        for j in range(len(cls)):
            if cls[j] =  = curr_cls:
                box[j][5] = curr_cls
                curr_cls_box.append(box[j][:6])
        curr_cls_box = np.array(curr_cls_box)
        curr_cls_box = xywh2xyxy(curr_cls_box)
        curr_out_box = nms(curr_cls_box, iou_thres)
        for k in curr_out_box:
            output.append(curr_cls_box[k])
    output = np.array(output)
    return output


def draw(image, box_data):
    boxes = box_data[..., :4].astype(np.int32)
    scores = box_data[..., 4]
    classes = box_data[..., 5].astype(np.int32)

    for box, score, cl in zip(boxes, scores, classes):
        top, left, right, bottom = box
        print('class: {}, score: {}'.format(CLASSES[cl], score))
        print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))

        cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)
        cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),
                    (top, left),
                    cv2.FONT_HERSHEY_SIMPLEX,
                    0.6, (0, 0, 255), 2)


def write_to_excel(data, filename):
    with xlsxwriter.Workbook(filename) as workbook:
        worksheet = workbook.add_worksheet()
        worksheet.write('A1', '序号')
        worksheet.write('B1', '类别')
        worksheet.write('C1', '得分')
        worksheet.write('D1', 'x')
        worksheet.write('D1', 'y')
        worksheet.write('E1', 'w')
        worksheet.write('F1', 'h')

        for i, box in enumerate(data):
            x1, y1, x2, y2, score, cls = box
            x_center = (x1 + x2) / 2
            y_center = (y1 + y2) / 2
            width = x2 - x1
            height = y2 - y1

            worksheet.write(i + 2, 0, i)  # 序号
            worksheet.write(i + 2, 1, CLASSES[cls])  # 类别
            worksheet.write(i + 2, 2, score)  # 得分
            worksheet.write(i + 2, 3, x_center)  # x中心点
            worksheet.write(i + 2, 4, y_center)  # y中心点
            worksheet.write(i + 2, 5, width)  # 宽度
            worksheet.write(i + 2, 6, height)  # 高度


if __name__ == "__main__":
    onnx_path = 'C:\\yolov5-7.0\\runs\\train\\exp42\\weights\\best.onnx'
    model = YOLOV5(onnx_path)
    output_folder = 'oyt'
    excel_filename = 'result.xlsx'

    if not os.path.exists(output_folder):
        os.makedirs(output_folder)

    # 加载预训练的人脸识别分类器
    face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

    cap = cv2.VideoCapture(0)
    excel_data = []

    try:
        while True:
            ret, frame = cap.read()
            if not ret:
                break

            output, or_img = model.inference(frame)
            outbox = filter_box(output, 0.5, 0.5)
            if len(outbox) > 0:
                draw(or_img, outbox)
                cv2.imshow('YOLOv5 Detection', or_img)
                excel_data.extend(outbox)
                if cv2.waitKey(1) & 0xFF == ord('q'):
                    break

    except Exception as e:
        print(f"程序出现错误: {e}")
    finally:
        cap.release()
        cv2.destroyAllWindows()
        write_to_excel(excel_data, excel_filename)