HELP!!!!

herrerajuans

Guys I have a video of a street where the people is walking, etc. I want to graph the movement patterns of the people, not only one person but many of them walking on the street. Then I want to create a heatmap from that information showing the areas with more people walking by. Is it possible to do using Processing?

TfGuy44

Assuming the camera's position is fixed, I'd skip the graph (unless you really need it) and go right for the heat map. Then you can just use frame differencing. Here's the example that comes with Processing:

/**
 * Frame Differencing 
 * by Golan Levin. 
 *
 * Quantify the amount of movement in the video frame using frame-differencing.
 */ 


import processing.video.*;

int numPixels;
int[] previousFrame;
Capture video;

void setup() {
  size(640, 480);

  // This the default video input, see the GettingStartedCapture 
  // example if it creates an error
  video = new Capture(this, width, height);

  // Start capturing the images from the camera
  video.start(); 

  numPixels = video.width * video.height;
  // Create an array to store the previously captured frame
  previousFrame = new int[numPixels];
  loadPixels();
}

void draw() {
  if (video.available()) {
    // When using video to manipulate the screen, use video.available() and
    // video.read() inside the draw() method so that it's safe to draw to the screen
    video.read(); // Read the new frame from the camera
    video.loadPixels(); // Make its pixels[] array available

    int movementSum = 0; // Amount of movement in the frame
    for (int i = 0; i < numPixels; i++) { // For each pixel in the video frame...
      color currColor = video.pixels[i];
      color prevColor = previousFrame[i];
      // Extract the red, green, and blue components from current pixel
      int currR = (currColor >> 16) & 0xFF; // Like red(), but faster
      int currG = (currColor >> 8) & 0xFF;
      int currB = currColor & 0xFF;
      // Extract red, green, and blue components from previous pixel
      int prevR = (prevColor >> 16) & 0xFF;
      int prevG = (prevColor >> 8) & 0xFF;
      int prevB = prevColor & 0xFF;
      // Compute the difference of the red, green, and blue values
      int diffR = abs(currR - prevR);
      int diffG = abs(currG - prevG);
      int diffB = abs(currB - prevB);
      // Add these differences to the running tally
      movementSum += diffR + diffG + diffB;
      // Render the difference image to the screen
      pixels[i] = color(diffR, diffG, diffB);
      // The following line is much faster, but more confusing to read
      //pixels[i] = 0xff000000 | (diffR << 16) | (diffG << 8) | diffB;
      // Save the current color into the 'previous' buffer
      previousFrame[i] = currColor;
    }
    // To prevent flicker from frames that are all black (no movement),
    // only update the screen if the image has changed.
    if (movementSum > 0) {
      updatePixels();
      println(movementSum); // Print the total amount of movement to the console
    }
  }
}

Just have detected differences increase the heat of any given pixel.

herrerajuans

Actually What I need the most are the graph. Show the displacement of an object between point A to point B

koogs

Please give this thread a better name

Chrisir

did you look at OpenCV and so on

it's a lib

PhiLho

As said by koogs, you should edit and change the subject: you wrote in all caps, which is seen as shouting, enforced by the multiple exclamation points. And the title is totally useless: nearly everybody ask for help.
Try to make a more descriptive subject, summarizing your message.

Also moved the topic.