Use a Raspberry Pi and a camera to detect and track a coloured object in real time with Python and OpenCV.
Every step includes a visual reference and a plain-language explanation, so you always know what to do next.
Flash Raspberry Pi OS, connect the camera module (or a USB webcam), and confirm it works with a quick test capture before writing any AI code.
Open a terminal on the Pi and install the OpenCV Python library, which handles image capture and processing for us.
pip install opencv-python numpyThis script captures live video, converts each frame to HSV colour space, filters for a chosen colour range, and draws a box around the largest matching object.
import cv2
import numpy as np
cap = cv2.VideoCapture(0)
# Example range: tune these for your object's colour (here: orange)
lower_color = np.array([5, 150, 150])
upper_color = np.array([15, 255, 255])
while True:
ret, frame = cap.read()
if not ret:
break
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
mask = cv2.inRange(hsv, lower_color, upper_color)
contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
if contours:
largest = max(contours, key=cv2.contourArea)
if cv2.contourArea(largest) > 500:
x, y, w, h = cv2.boundingRect(largest)
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.putText(frame, "Object", (x, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
cv2.imshow("AI Object Detection", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()Run the script, hold up an object matching the tuned colour range in front of the camera, and confirm a green bounding box tracks it as it moves.
Confirm the camera is enabled (raspi-config → Interface Options → Camera) and that no other program is currently using it.
Your object's colour range likely differs from the example — use an HSV colour picker tool to find the right lower/upper values for your object and lighting.
Lower the camera resolution, or run on a Raspberry Pi 4/5 for better performance — the Pi 3 can struggle with larger frame sizes.
Loved building this for free? Our instructor-led workshops go deeper with kits, live guidance and more advanced builds.
Learn how to control an LED using Arduino UNO by making it turn ON and OFF automatically. This is the basic concept behind indicator lights, warning lights, and signal systems used in real-world electronic devices.
View Free Project →Use a PIR sensor to detect human movement and automatically switch ON an LED. This demonstrates the technology used in security systems, automatic lights, smart homes, and occupancy detection.
View Free Project →Build a smart street light that automatically turns ON when it gets dark and OFF during daylight using an LDR sensor. This concept is commonly used in street lights, garden lights, parking areas, and energy-saving lighting systems.
View Free Project →