【深度学习】Tensorflow object detection API 实现视频目标检测

最近使用Tensorflow object detection API搭建了一个变压器铭牌位置检测模型，因为先试试练手，所以只是训练了70张图片，图片来源是由现场拍摄视频分帧来的，我前面的博客有所介绍，效果如图：

我又尝试了另外一种变压器，效果很差，因为之前完全没有使用该种类变压器，之后的项目中，会加上去改进

最后，使用训练得到的参数文件，进行视频流的目标检测，效果依然很好（只适用于该种类变压器）

 

import numpy as np
import tensorflow as tf
import cv2

from utils import label_map_util
from utils import visualization_utils as vis_util

cap = cv2.VideoCapture('D:/code/Detection/data/1.mp4')
ret, image_np = cap.read()
out = cv2.VideoWriter('D:/code/Detection/data/1_out.mp4', -1, cap.get(cv2.CAP_PROP_FPS), (image_np.shape[1], image_np.shape[0]))

PATH_TO_CKPT = 'D:/code/Detection/training/pb/frozen_inference_graph.pb'
PATH_TO_LABELS = 'D:/code/Detection/data/tf.pbtxt'
NUM_CLASSES = 90

detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        od_graph_def.ParseFromString(fid.read())
        tf.import_graph_def(od_graph_def, name='')

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
                                                            use_display_name=True)
category_index = label_map_util.create_category_index(categories)

with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
        detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
        detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
        detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')
        while cap.isOpened():
            ret, image_np = cap.read()
            if len((np.array(image_np)).shape) == 0:
                break
            image_np = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
            image_np_expanded = np.expand_dims(image_np, axis=0)
            (boxes, scores, classes, num) = sess.run(
                [detection_boxes, detection_scores, detection_classes, num_detections],
                feed_dict={image_tensor: image_np_expanded})
            vis_util.visualize_boxes_and_labels_on_image_array(image_np, np.squeeze(boxes),
                                                               np.squeeze(classes).astype(np.int32), np.squeeze(scores),
                                                               category_index, use_normalized_coordinates=True,
                                                               line_thickness=8)
            out.write(cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR))

cap.release()
out.release()
cv2.destroyAllWindows()

讲道理，代码并没有完全看懂，但是还会继续学习，学习python，学习tensorflow