how to read video Frames directly into memory with Nodejs? - node.js

Question

What i am trying to do is taking a video and diving it to frames and passing this frames to a Model to detect objects in each frame but the problem is the extraction process cost so much time and i don't need the frames on my disk.

Answer 1

fmpeg-stream offers stream capabilities. So there is no need to write to a file.
It is also possible to use directly ffmpeg and spawn a new child process. Its .stdout property is a readable stream. On the event data, the chunk can be read.
const fs = require("fs");
const tf = require("#tensorflow/tfjs-node")
const logStream = fs.createWriteStream('./logFile.log');
const spawnProcess = require('child_process').spawn,
ffmpeg = spawnProcess('ffmpeg', [
'-i', 'videfile.mp4',
'-vcodec', 'png',
'-f', 'rawvideo',
'-s', 'h*w', // size of one frame
'pipe:1'
]);
ffmpeg.stderr.pipe(logStream); // for debugging
let i = 0
ffmpeg.stdout.on('data', (data) => {
try {
console.log(tf.node.decodeImage(data).shape)
console.log(`${++i} frames read`)
// dispose all tensors
} catch(e) {
console.log(e)
}
})
ffmpeg.on('close', function (code) {
console.log('child process exited with code ' + code);
});
Decoding the image is in a try catch block to prevent error raised when the chunk does not match a frame.
A more robust code to prevent decoding chunks that do not correspond to images will be the following:
const { Transform } = require("stream")
class ExtractFrames extends Transform {
constructor(delimiter) {
super({ readableObjectMode: true })
this.delimiter = Buffer.from(delimiter, "hex")
this.buffer = Buffer.alloc(0)
}
_transform(data, enc, cb) {
// Add new data to buffer
this.buffer = Buffer.concat([this.buffer, data])
const start = this.buffer.indexOf(this.delimiter)
if (start < 0) return // there's no frame data at all
const end = this.buffer.indexOf(
this.delimiter,
start + this.delimiter.length,
)
if (end < 0) return // we haven't got the whole frame yet
this.push(this.buffer.slice(start, end)) // emit a frame
this.buffer = this.buffer.slice(end) // remove frame data from buffer
if (start > 0) console.error(`Discarded ${start} bytes of invalid data`)
cb()
}
_flush(callback) {
// push remaining buffer to readable stream
callback(null, this.buffer);
}
}
const fs = require("fs");
const tf = require("#tensorflow/tfjs-node")
const logStream = fs.createWriteStream('./logFile.log');
const spawnProcess = require('child_process').spawn,
ffmpeg = spawnProcess('ffmpeg', [
'-i', 'generique.mp4',
'-vcodec', 'mjpeg',
'-f', 'rawvideo',
'-s', '420x360', // size of one frame
'pipe:1'
]);
ffmpeg.stderr.pipe(logStream); // for debugging
let i = 0
ffmpeg.stdout
.pipe(new ExtractFrames("FFD8FF")).on('data', (data) => {
try {
console.log(tf.node.decodeImage(data).shape)
console.log(`${++i} frames read`)
// dispose all tensors
} catch(e) {
console.log(e)
}
})
ffmpeg.on('close', function (code) {
console.log('child process exited with code ' + code);
});
Though, the above code works, it will still fill up quickly the memory. Separating the frame extraction from the data processing itself will help.
async function* frames() {
let resolve;
let promise = new Promise(r => resolve = r);
let bool = true;
ls.stdout.pipe(new ExtractFrames("FFD8FF")).on('data', data => {
resolve(data);
promise = new Promise(r => resolve = r);
});
ls.on('close', function (code) {
bool = false
console.log('code')
});
while (bool) {
const data = await promise;
yield data;
}
}
(async() => {
// data processing
// possibly create tf.dataset for training
for await (const data of stream()) {
console.log(tf.node.decodeImage(data).shape)
console.log(data);
}
})()