Отслеживание объектов с помощью YOLOv3 python - PullRequest
0 голосов
/ 07 мая 2020

Я работал с Yolov3 Object Detection and Tracking. Ниже приведен код для обнаружения объектов и отслеживания центроидов для отмеченных объектов. Я могу нарисовать линию трассировки для этого объекта. Мой вопрос: как назначить уникальный идентификатор для каждого объекта в общем видео и отслеживать их.

import os 
os.chdir("C:/Users/PavanGoli/YOLO_Implementation/")
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
from YOLO_Implementation.tracker import Tracker
import copy
import colorsys
#import os
from timeit import default_timer as timer
import cv2
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
Image.MAX_IMAGE_PIXELS = None
from YOLO_Implementation.yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from YOLO_Implementation.yolo3.utils import image_preporcess
#from keras.utils import multi_gpu_model
import csv
class YOLO(object):
    _defaults = {
        "model_path": 'C:/Users/PavanGoli/OIDv4_ToolKit/logs/trained_weights_final.h5',
        "anchors_path": 'C:/Users/PavanGoli/OIDv4_ToolKit/model_data/tiny_yolo_anchors.txt',
        "classes_path": 'C:/Users/PavanGoli/OIDv4_ToolKit/4_CLASS_test_classes.txt',
        "score" : 0.5,
        "iou" : 0.5,
        "model_image_size" : (416, 416),
        #"gpu_num" : 0,
    }

    @classmethod
    def get_defaults(cls, n):
        if n in cls._defaults:
            return cls._defaults[n]
        else:
            return "Unrecognized attribute name '" + n + "'"

    def __init__(self, **kwargs):
        self.__dict__.update(self._defaults) # set up default values
        self.__dict__.update(kwargs) # and update with user overrides
        self.class_names = self._get_class()
        self.anchors = self._get_anchors()
        self.sess = K.get_session()
        self.boxes, self.scores, self.classes = self.generate()

    def _get_class(self):
        classes_path = os.path.expanduser(self.classes_path)
        with open(classes_path) as f:
            class_names = f.readlines()
        class_names = [c.strip() for c in class_names]
        return class_names

    def _get_anchors(self):
        anchors_path = os.path.expanduser(self.anchors_path)
        with open(anchors_path) as f:
            anchors = f.readline()
        anchors = [float(x) for x in anchors.split(',')]
        return np.array(anchors).reshape(-1, 2)

    def generate(self):
        model_path = os.path.expanduser(self.model_path)
        assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'

        # Load model, or construct model and load weights.
        num_anchors = len(self.anchors)
        num_classes = len(self.class_names)
        is_tiny_version = num_anchors==6 # default setting
        try:
            self.yolo_model = load_model(model_path, compile=False)
        except:
            self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
                if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
            self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
        else:
            assert self.yolo_model.layers[-1].output_shape[-1] == \
                num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
                'Mismatch between model and given anchor and class sizes'

        print('{} model, anchors, and classes loaded.'.format(model_path))

        # Generate colors for drawing bounding boxes.
        hsv_tuples = [(x / len(self.class_names), 1., 1.)
                      for x in range(len(self.class_names))]
        self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
        self.colors = list(
            map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
                self.colors))
        #np.random.seed(10101)  # Fixed seed for consistent colors across runs.
        np.random.shuffle(self.colors)  # Shuffle colors to decorrelate adjacent classes.
        #np.random.seed(None)  # Reset seed to default.

        # Generate output tensor targets for filtered bounding boxes.
        self.input_image_shape = K.placeholder(shape=(2, ))

        boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
                len(self.class_names), self.input_image_shape,
                score_threshold=self.score, iou_threshold=self.iou)
        return boxes, scores, classes

    def detect_image(self, image):
        start = timer()
        centers=[]
        images = []
        Objects_list = []
        image_id = 0
        if self.model_image_size != (None, None):
            assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
            assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
            boxed_image = image_preporcess(np.copy(image), tuple(reversed(self.model_image_size)))

            image_data = boxed_image

        out_boxes, out_scores, out_classes = self.sess.run(
            [self.boxes, self.scores, self.classes],
            feed_dict={
                self.yolo_model.input: image_data,
                self.input_image_shape: [image.size[1], image.size[0]], #[image.shape[0], image.shape[1]]
                K.learning_phase(): 0
            })
        #print(len(out_boxes))

        #print('Found {} boxes for {}'.format(len(out_boxes), 'img'))

        font = ImageFont.truetype(font='arial.ttf',size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
        thickness = (image.size[0] + image.size[1]) // 300

        for i, c in reversed(list(enumerate(out_classes))):
            predicted_class = self.class_names[c]
            box = out_boxes[i]
            score = out_scores[i]
            number=len(out_boxes)
            label = '{} {:.2f}'.format(predicted_class, score)
            draw = ImageDraw.Draw(image)
            tracker = Tracker(160, 30, 6, 1)
            label_size = draw.textsize(label, font)

            top, left, bottom, right = box
            center=(int ((left+right)//2),int((top+bottom)//2))
            b=np.array([[(left+right)//2],[(top+bottom)//2]])
            #boxes.append([top,left,bottom,right])
            centers.append(b)
            top = max(0, np.floor(top + 0.5).astype('int32'))
            left = max(0, np.floor(left + 0.5).astype('int32'))
            bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
            right = min(image.size[0], np.floor(right + 0.5).astype('int32'))

            Objects_list.append([top,left,bottom,right])

            if top - label_size[1] >= 0:
                text_origin = np.array([left, top - label_size[1]])
            else:
                text_origin = np.array([left, top + 1])



            # My kingdom for a good redistributable image drawing library.
            for i in range(thickness):
                draw.rectangle([left + i, top + i, right - i, bottom - i],outline=self.colors[c])

            draw.rectangle([tuple(text_origin), tuple(text_origin + label_size)],fill=self.colors[c])

                #draw.rectangle(
                    #[tuple(text_origin), tuple(text_origin + label_size)],
                    #fill=self.colors[c])
            draw.text(text_origin, label, fill=(0, 0, 0), font=font)

            del draw


        end = timer()
        #print(end - start)
        return image,centers,number,Objects_list

    def close_session(self):
        self.sess.close()

def detect_video(yolo, video_path, output_path=""):
    tracker_id = []
    vid = cv2.VideoCapture(video_path)
    if not vid.isOpened():
        raise IOError("Couldn't open webcam or video")

    fourcc = cv2.VideoWriter_fourcc(*'mp4v')

    out = cv2.VideoWriter(output_path,fourcc,25.0, (1280,720),isColor = True)
    tracker = Tracker(160, 30, 6, 1)
    # Variables initialization
    skip_frame_count = 0
    track_colors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0),
                    (0, 255, 255), (255, 0, 255), (255, 127, 255),
                    (127, 0, 255), (127, 0, 127)]

    frame_id = 0
   # count = 0
    while True:
        return_value, frame = vid.read()

        if not return_value:
            break

        image = Image.fromarray(frame)
        image,centers,number,Objects_list = yolo.detect_image(image)

        result = np.asarray(image)

        font = cv2.FONT_HERSHEY_SIMPLEX

        if (len(centers) > 0):

            # Track object using Kalman Filter
            tracker.Update(centers)

            # For identified object tracks draw tracking line
            # Use various colors to indicate different track_id
            for i in range(len(tracker.tracks)):
               # print(tracker.tracks[i].track_id)
                if (len(tracker.tracks[i].trace) > 1):
                    for j in range(len(tracker.tracks[i].trace) - 1):
                        # Draw trace line
                        x1 = tracker.tracks[i].trace[j][0][0]
                        y1 = tracker.tracks[i].trace[j][1][0]
                        x2 = tracker.tracks[i].trace[j + 1][0][0]
                        y2 = tracker.tracks[i].trace[j + 1][1][0]

                        clr = tracker.tracks[i].track_id % 9
                        cv2.line(result, (int(x1), int(y1)), (int(x2), int(y2)),track_colors[clr], 4)

            # Display the resulting tracking frame
            cv2.imshow('Tracking', result)
            ###################################################
        cv2.namedWindow("result", cv2.WINDOW_NORMAL)
        cv2.imshow("result", result)
        #out.write(result)
        if cv2.waitKey(100) & 0xFF == ord('q'):
            break
    vid.release()
    cv2.destroyAllWindows()
    yolo.close_session()

if __name__ == '__main__':
    yolo = YOLO()
    detect_video(yolo,"C:/Users/PavanGoli/YOLO_Implementation/New_Video1.mp4","C:/Users/PavanGoli/YOLO_Implementation/Example_4_tracker.mp4")

Как назначить уникальный идентификатор для каждого объекта в верхней части окна и отслеживать их?

...