PaddlePaddle / PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

PaddleOCR如何检测视频?

Keeping7 opened this issue · comments

检测图像是可以的,但是用图像的命令套用视频时,显示如下错误:

python3 ./paddle/PaddleOCR-release-2.5/tools/infer/predict_det.py --image_dir="./2-HC-YQ/HC-YQ.mp4" --det_model_dir="./output/db_mv3_inference_latest/l.save_infer/"
Traceback (most recent call last):
File "./paddle/PaddleOCR-release-2.5/tools/infer/predict_det.py", line 259, in
image_file_list = get_image_file_list(args.image_dir)
File "/home/jcuas/nanhang/tongk/paddle/PaddleOCR-release-2.5/ppocr/utils/utility.py", line 71, in get_image_file_list
raise Exception("not found any img file in {}".format(img_file))
Exception: not found any img file in ./2-HC-YQ/HC-YQ.mp4

PaddleOCR是不支持检测视频吗?检测视频的命令是什么呢?求大佬们指点,谢谢。

暂时不支持视频格式作为输入

谢谢。
那如果要对视频检测,有什么其他方法吗?

暂时不支持视频格式作为输入

谢谢。那如果要对视频检测,有什么其他方法吗?

可以先对视频进行切帧,以图片格式送入ocr检测识别