Question

我正在研究一种手语识别系统，该系统可以从网络摄像头中获取实时视频。我为整个系统协调使用了两个系统。第一个系统提供手语用户的手的关键点和骨架，第二个系统获取该关键点和骨架数据并对其进行分析，以给出说话人想要说的话。所以我的问题是将指向关键点的视频文件传递给分析部分。我不知道我的问题在这里有多清晰，但我急需帮助。

我已经尝试过在互联网上找到的几种方法，但是这些解决方案似乎都不起作用。

cv2.imshow（'输出骨架'，框架）＃cv2.imwrite（“ video_output / {：03d} .jpg” .format（k），frame）

key = cv2.waitKey(1)
if key == 27:
    break

print("total = {}".format(time.time() - t))

vid_writer.write(frame)


def predict(image_data):
    predictions = sess.run(softmax_tensor, \
                           {'DecodeJpeg/contents:0': image_data})

    # Sort to show labels of first prediction in order of confidence
    top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]

    max_score = 0.0
    res = ''
    for node_id in top_k:
        human_string = label_lines[node_id]
        score = predictions[0][node_id]
        if score > max_score:
            max_score = score
            res = human_string
    return res, max_score


# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line in tf.gfile.GFile("logs/trained_labels.txt")]

# Unpersists graph from file
with tf.gfile.FastGFile("logs/trained_graph.pb", 'rb') as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
    _ = tf.import_graph_def(graph_def, name='')

with tf.Session() as sess:
    # Feed the image_data as input to the graph and get first prediction
    softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')

    c = 0
    input_source =  cv2.imshow('frame',frame1)
    cap = cv2.VideoCapture(input_source)

    res, score = '', 0.0
    i = 0
    mem = ''
    consecutive = 0
    sequence = ''

使用python openCV进行视频处理

0 个答案: