【问题标题】:Saving image in a real time object detector将图像保存在实时对象检测器中
【发布时间】:2020-05-31 00:31:33
【问题描述】:

我目前正在使用 TensorFlow 1.x 中的 SSD MobileNetv2 运行实时对象检测器,我想知道当视频流检测到其中一个类时是否有任何方法可以保存图像。

PATH_TO_FROZEN_GRAPH = 'path-to-inference-graph.pb'
PATH_TO_LABEL_MAP = 'path-to-label-map.pbtxt'
NUM_CLASSES = 4
cap = cv2.VideoCapture(0)

基本上,我已经构建了检测器来检测 4 个类,并希望在检测到其中一个类时保存图像(也许它可能会以一系列图像的形式出现,仍然可以)。

label_map = label_map_util.load_labelmap(PATH_TO_LABEL_MAP)
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:
        while True:
            ret, image_np = cap.read()
            image_np_expanded = np.expand_dims(image_np, 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,
                np.squeeze(boxes),
                np.squeeze(classes).astype(np.int32),
                np.squeeze(scores),
                category_index,
                use_normalized_coordinates=True,
                line_thickness=3,
                )

            cv2.imshow('Detection', cv2.resize(image_np, (1200, 800)))
            if cv2.waitKey(25) & 0xFF == ord('q'):
                cv2.destroyAllWindows()
                break

我如何实现这一目标?它还有其他变体吗?

【问题讨论】:

    标签: tensorflow object-detection object-detection-api mobilenet


    【解决方案1】:

    在 session.run 之后,您会在 (boxes, scores, classes, num_detections) 中获得结果

    您只需要遍历它们并查看课程和分数,最后保存

    if 'req_class_name' in classes:
       #check for confidence score also
       cv2.imwrite('/path/to/destination/image.png', image_np)
    

    【讨论】:

      猜你喜欢
      • 2019-05-22
      • 1970-01-01
      • 2019-12-05
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 2012-01-25
      • 1970-01-01
      相关资源
      最近更新 更多