Gesture-Controlled Tello Drone- Rapolas Kairys - Revision history

Robot: /* Gesture Controlled Tello Drone Project */

2025-02-02T17:00:27Z

‎Gesture Controlled Tello Drone Project

Robot: /* Gesture Controlled Tello Drone Project */

2025-02-02T15:47:16Z

‎Gesture Controlled Tello Drone Project

Robot: /* Gesture Controlled Tello Drone Project */

2025-02-02T15:11:05Z

‎Gesture Controlled Tello Drone Project

Robot: /* Gesture Controlled Tello Drone Project */

2025-02-02T15:05:36Z

‎Gesture Controlled Tello Drone Project

Robot: /* Gesture-Controlled Tello Drone Project */

2025-02-02T14:51:15Z

‎Gesture-Controlled Tello Drone Project

Robot: /* Abstract */

2025-02-02T14:34:55Z

‎Abstract

Robot: /* Abstract */

2025-02-02T14:34:03Z

‎Abstract

Robot: /* Abstract */

2025-02-02T14:32:22Z

‎Abstract

Robot: /* Gesture-Controlled Tello Drone Project */

2025-01-29T13:22:39Z

‎Gesture-Controlled Tello Drone Project

Robot: Created page with "== Gesture-Controlled Tello Drone Project =="

2025-01-29T13:22:14Z

Created page with "== Gesture-Controlled Tello Drone Project =="

New page

== Gesture-Controlled Tello Drone Project ==

← Older revision		Revision as of 17:00, 2 February 2025
Line 67:		Line 67:
	# HUD & Feedback		# HUD & Feedback
	#* The system displays the command currently recognized, the active command (the one being executed by the drone) and battery level.		#* The system displays the command currently recognized, the active command (the one being executed by the drone) and battery level.
		+
		+	=== Links ===
		+	* [https://github.com/RafalasTypeBeat/Gesture-controlled-drone Source code]
		+	* [https://www.youtube.com/watch?v=hZfRaGYyeyY Video example]

@@ Line 14: / Line 14: @@
 * Multithreading to ensure that drone commands (which can block) do not freeze the camera feed or the user interface.
 * Custom gesture logic to determine gestures (LEFT arm up, RIGHT arm up, both arms up, or none).
 === Controlls ===
@@ Line 29: / Line 30: @@
 === Steps Taken ===
-# Environment Setup Installed necessary Python libraries: mediapipe, opencv-python, djitellopy. Created a virtual environment to keep dependencies organized.
+# Environment Setup:
+#* Installed necessary Python libraries: mediapipe, opencv-python, djitellopy.
-# Implemented Gesture Detection
+#* Created a virtual environment to keep dependencies organized.
+# Implemented Gesture Detection:
-Used Mediapipe’s Pose Estimation to identify shoulder and elbow landmarks.
+#* Used Mediapipe’s Pose Estimation to identify shoulder and elbow landmarks.
-Determined a gesture by comparing y-coordinates of elbows vs. shoulders (e.g., elbow above the shoulder).
+#* Determined a gesture by comparing y-coordinates of elbows vs. shoulders (e.g., elbow above the shoulder).
-Drone Controller
+# Drone Controller:
+#* Developed a separate background thread for drone commands.
-Developed a background thread to send blocking commands (like takeoff()) so the main loop remains responsive.
+#* Stores only one command at a time and executes it before accepting the next.
-Stored only one command at a time (no queue) and executed it before accepting the next.
+# Main Application Loop:
-Main Application Loop
+#* Captures frames from the laptop camera in a separate thread to avoid UI lag.
-Adjusted arm-raise thresholds for better recognition accuracy.
+=== Algorithm overview ===
-Verified drone responsiveness and safe takeoff/landing.
+# Threaded Camera Capture

@@ Line 5: / Line 5: @@
 * Explore computer vision and machine learning for gesture recognition.
 * Demonstrate real-time controls using multithreading to have a smooth video feed.
 === Description ===
@@ Line 14: / Line 15: @@
 * Custom gesture logic to determine gestures (LEFT arm up, RIGHT arm up, both arms up, or none).
 When the user performs a gesture in front of the laptop camera, the system detects it and translates it into a drone command:
@@ Line 23: / Line 25: @@
 * The command has to be held for 1.5 seconds to take effect. This helps prevent accidental commands and ensure safety.
 * While the program is running and a drone is connected pressing "t" makes the drone take off/land. Pressing "q" shuts down the program.

@@ Line 6: / Line 6: @@
 * Demonstrate real-time controls using multithreading to have a smooth video feed.
-=== Tools used ===
+=== Description ===
-* [https://github.com/google-ai-edge/mediapipe MediaPipe] for pose estimation.
+The system uses:
 * [https://opencv.org/ OpenCV] for video processing.
-* [https://github.com/damiafuentes/DJITelloPy DJITelloPy] library for drone communication over wifi.
+* [https://github.com/damiafuentes/DJITelloPy DJITelloPy] library to send commands to the Tello drone over Wi-Fi, handling takeoff, landing, and movement.
+* Holding both arms raised for 4 seconds toggles flight (either takeoff or land).
+* Once in the air, raising both arms makes the drone go up.
-Key features:
+* Raising only the left or right arm makes the drone move left or right.
-* Hand movement recognition for drone directional control
+* Doing neither results in a hover command.
-* First-person view (FPV) video recording
+* The drone moves 30cm for all commands, which can be changed in ''drone_controller.py''.
-* Command queue system for safe operation
+* The command has to be held for 1.5 seconds to take effect. This helps prevent accidental commands and ensure safety.

@@ Line 1: / Line 1: @@
-== Gesture-Controlled Tello Drone Project ==
+== Gesture Controlled Tello Drone Project ==
-=== Abstract ===
+=== Goal of the Project===
-This project implements a real-time gesture control system for DJI Tello drones using:
+The main objective of this project is to control a Tello drone using gesture recognition from a laptop camera. Users can raise their arms in specific poses to make the drone move left, right, up or toggle flight (take off/land) by holding an “UP” pose for four seconds. This project aims to:
-* [https://github.com/google-ai-edge/mediapipe MediaPipe] for pose estimation
+* Provide a way to interact with and control a small drone using hand gestures.
-* [https://opencv.org/ OpenCV] for video processing
+* Explore computer vision and machine learning for gesture recognition.
-* [https://github.com/damiafuentes/DJITelloPy DJITelloPy] library for drone communication
+* Demonstrate real-time controls using multithreading to have a smooth video feed.
 Key features:
-* Hand sign recognition for directional control
+* Hand movement recognition for drone directional control
 * First-person view (FPV) video recording
 * Command queue system for safe operation

@@ Line 2: / Line 2: @@
 === Abstract ===
 This project implements a real-time gesture control system for DJI Tello drones using:
-* [[https://github.com/google-ai-edge/mediapipe|MediaPipe]] for pose estimation
+* [https://github.com/google-ai-edge/mediapipe MediaPipe] for pose estimation
 * [[wikipedia:OpenCV|OpenCV]] for video processing
 * [[DJITelloPy]] library for drone communication

← Older revision		Revision as of 13:22, 29 January 2025
Line 1:		Line 1:
	== Gesture-Controlled Tello Drone Project ==		== Gesture-Controlled Tello Drone Project ==
		+	=== Abstract ===
		+	This project implements a real-time gesture control system for DJI Tello drones using:
		+	* [[wikipedia:MediaPipe\|MediaPipe]] for pose estimation
		+	* [[wikipedia:OpenCV\|OpenCV]] for video processing
		+	* [[DJITelloPy]] library for drone communication
		+
		+	Key features:
		+	* Hand sign recognition for directional control
		+	* First-person view (FPV) video recording
		+	* Command queue system for safe operation