行人检测--OpenCV与TensorFlow SSD对比

Color Space

发布于 2020-01-13 15:35:40

3.2K0

发布于 2020-01-13 15:35:40

文章被收录于专栏：OpenCV与AI深度学习OpenCV与AI深度学习

OpenCV行人检测我们使用HOG特征提取+SVM训练，使用默认API检测，详细了解可参考：https://zhuanlan.zhihu.com/p/75705284

使用的测试原图：

OpenCV代码：

import cv2
import numpy as np

if __name__ == '__main__':
    img = cv2.imread("1.jpg")
    cv2.imshow("src", img)
    hog = cv2.HOGDescriptor()
    hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
    # Detect people in the image
    (rects, weights) = hog.detectMultiScale(img,
                                            winStride=(4, 4),
                                            padding=(8, 8),
                                            scale=1.05,
                                            useMeanshiftGrouping=False)
    for (x, y, w, h) in rects:
        cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 2)

    cv2.imshow("people_detector", img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

检测结果（不太理想）：

接下来使用TensorFlow SSD训练好的模型ssd_mobilenet_v1_coco_2018_01_28进行测试，代码如下：

import os
import sys
import tarfile
import cv2
import tensorflow as tf
import numpy as np

from utils import label_map_util
from utils import visualization_utils as vis_util

# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_2018_01_28'
#MODEL_FILE = 'D:/tensorflow/' + MODEL_NAME + '.tar.gz'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_FROZEN_GRAPH = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('D:/tensorflow/models/research/object_detection/data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90

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

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categorys = label_map_util.convert_label_map_to_categories(label_map,max_num_classes=NUM_CLASSES,use_display_name=True)
categorys_index = label_map_util.create_category_index(categorys)

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    image = cv2.imread("./4.jpg")
    image_np_expanded = np.expand_dims(image,axis = 0)
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
    boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
    scores = detection_graph.get_tensor_by_name('detection_scores:0')
    classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')
    (boxes,scores,classes,num_detections) = sess.run([boxes,scores,classes,\
                                num_detections],feed_dict={image_tensor:image_np_expanded})
    vis_util.visualize_boxes_and_labels_on_image_array(
      image,
      np.squeeze(boxes),
      np.squeeze(classes).astype(np.int32),
      np.squeeze(scores),
      categorys_index,
      min_score_thresh = 0.5,
      use_normalized_coordinates = True,
      line_thickness = 4  
      )
    cv2.imshow("object_detection", image)
    cv2.imwrite("result.jpg",image)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

检测结果：