CODEWITHSUNDEEP
pythonperformanceimage-processingvideoanalysis
RookiePie
RookiePie

Reputation: 1

How to increase the speed of video analysis?

I have a video that is over 1 hr long and has 110000+ frames. I am using the code below to analyze facial emotions in the video. However, the entire process takes too long and the estimated timeframe to complete this task is over 34 hrs! My question is the following: is there any way that I can speed up this process (e.g. by skipping frames? Analyzing every 3rd frame?)

Here is the code:

from fer import Video
from fer import FER
import os
import sys
import pandas as pd

location_videofile = "/Users/M/Desktop/videoplayback.mp4"
input_video = Video(location_videofile)

processing_data = input_video.analyze(face_detector, display=False)

Upvotes: 0

Views: 322

Answers (1)

chris
chris

Reputation: 1322

Didn't see this explained in fer's documentation explicitly, but if you look at the source code for the Video object, analyze accepts a bunch of keyword arguments. Source code is here https://github.com/justinshenk/fer/blob/master/src/fer/classes.py

and the relevant bit is:

def analyze(
        self,
        detector, # fer.FER instance
        display: bool = False,
        output: str = "csv",
        frequency: Optional[int] = None,
        max_results: int = None,
        save_fps: Optional[int] = None,
        video_id: Optional[str] = None,
        save_frames: bool = True,
        save_video: bool = True,
        annotate_frames: bool = True,
        zip_images: bool = True,
        detection_box: Optional[dict] = None
    ) -> list:
        """Recognize facial expressions in video using `detector`.
        
        Args:
        
            detector (fer.FER): facial expression recognizer
            display (bool): show images with cv2.imshow
            output (str): csv or pandas
            frequency (int): inference on every nth frame (higher number is faster)
            max_results (int): number of frames to run inference before stopping
            save_fps (bool): inference frequency = video fps // save_fps
            video_id (str): filename for saving
            save_frames (bool): saves frames to directory
            save_videos (bool): saves output video
            annotate_frames (bool): add emotion labels
            zip_images (bool): compress output
            detection_box (dict): dict with bounding box for subimage (xmin, xmax, ymin, ymax)

So looks like you can set use frequency to sample less frequently, for example to sample every 3rd frame:

processing_data = input_video.analyze(face_detector, display=False, frequency=3)

Upvotes: 1

Related Questions