DEV Community

Cover image for Dorm Room Doorbell: Web Sockets & Detection
Jacob Woods
Jacob Woods

Posted on

1

Dorm Room Doorbell: Web Sockets & Detection

Detection Stabilization

First things first, we needed to keep the face detector from doing some sort of action every time the loop runs. So to keep the detector from continuing to detect faces I used two tricks: 1.) Use an array to look at previous frames and see if it detected a face. If we see that the last 40 or so frames detected a face then we can determine that there is in fact a face there. The Cascade Classifier that comes with OpenCV can be a bit buggy and I didn't want a new event happening should the detection not detect a person in one frame. 2.) If we detected a face in the last pass of the frame loop then we don't want to do a new event because we know a face is already there. Super neat stuff!

Web Socket Server

I knew for this project I would need to pickup web sockets so I started up on that. I have never used web sockets so I used a Tech With Tim video Still learning and processing it!

def handle_cleint(conn, addr):
    print(f"[NEW CONNECTION] {addr} connected.") 
    connected = True
    while connected == True:
        message_length = conn.recv(HEADER).decode(FORMAT) # Receive message
        if message_length:
            message_length = int(message_length)
            msg = conn.recv(message_length).decode(FORMAT) # Receive message
         # Print message
            if msg == DISCONNECT_MESSAGE:
                connected = False
            print(f"[{addr}] {msg}")
            conn.send(f"Message received: | {msg} |".encode(FORMAT))
    print(f"[{addr}] ** Has left the chat.**")
    conn.close()
Enter fullscreen mode Exit fullscreen mode

Here is the handle client function in the server.py script

def start():
    server.listen() 
    print(f"SEVER IS LISTENING ON {SERVER}") # Listen for incoming connections
    while True:
        conn, addr = server.accept() # Accept connection

        thread = threading.Thread(target=handle_cleint, args=(conn, addr))
        print("[ACTIVE CONNECTIONS] ", threading.activeCount() - 1 ) # Show active connections
        thread.start()
Enter fullscreen mode Exit fullscreen mode

Here is the start function, also using threading (YAY!)

    if len(array_cache) >= 39:
        array_cache.pop(0)
        if face_detected == False:
            if check_array_cache_sum(array_cache) >= 38:
                print("Face Detected")
                face_detected = True
                web_hook.send("Face Detected")
                array_cache = []
        if check_array_cache_sum(array_cache) <= 38 and (len(array_cache) != 0):
            print("Face Not Detected")
            face_detected = False
            array_cache = []
Enter fullscreen mode Exit fullscreen mode

Here is some of the code for smoothing out the detection.

Hostinger image

Get n8n VPS hosting 3x cheaper than a cloud solution

Get fast, easy, secure n8n VPS hosting from $4.99/mo at Hostinger. Automate any workflow using a pre-installed n8n application and no-code customization.

Start now

Top comments (0)

Billboard image

The Next Generation Developer Platform

Coherence is the first Platform-as-a-Service you can control. Unlike "black-box" platforms that are opinionated about the infra you can deploy, Coherence is powered by CNC, the open-source IaC framework, which offers limitless customization.

Learn more

👋 Kindness is contagious

Please leave a ❤️ or a friendly comment on this post if you found it helpful!

Okay