Obstacle Avoidance using Stereo Camera
The main aim of our project is to develop an anti-collision system for a quadrotor which can be used for real time application. An approach for obstacle detection and collision avoidance of a quad copter both autonomous and remote control using a stereo camera and Single Board Computer.
2025-06-28 16:34:18 - Adil Khan
Obstacle Avoidance using Stereo Camera
Project Area of Specialization RoboticsProject SummaryThe main aim of our project is to develop an anti-collision system for a quadrotor which can be used for real time application. An approach for obstacle detection and collision avoidance of a quad copter both autonomous and remote control using a stereo camera and Single Board Computer.
Project ObjectivesThe main objective of our pproject is to develop a collision avoidance system for quadrotor (UAV) using stereo vision sensor. The project is to develop an unmanned aerial vehicle to fly autonomously in indoor or cluttered environments like houses or urban canyons. The collision with obstacles is a major problem while flying under these environments and hence a collision avoidance system has to be installed. In this project obstacles are avoided using stereo camera.
Project Implementation Method- Point cloud generation
- Object Detection in Point Cloud
- Disparity Map Generation
Object Detection: The sensor system generates a depth map in which each pixel represents a distance to the sensor. As a result, it can detect not only the presence of objects in the danger zone, but also their relative size and position.
Cost Advantages: Because of its simple design, a stereo camera has considerable cost advantages over currently approved technologies. Two standard industrial cameras are fixed at a defined angle to one another. The adjustable lenses can be quickly adapted to fit the required scenario. Moreover, the sensors can be mounted on existing posts near the level crossing.
Reliability:Thanks to its system properties, a stereo camera can provide a higher reliability than is currently required. The sensor system has no moving parts, thus reducing wear and tear and making it less prone to errors.
Technical Details of Final Deliverable- Autonoumous Quadcopter
- Obstacle Detection through stereo camera images.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 77240 | |||
| Odroid Xu4 | Equipment | 1 | 16000 | 16000 |
| Pixhawk 2.4.8 with 4GB SD card Led switch & buzzer | Equipment | 1 | 8500 | 8500 |
| Gps M8n with compass for APM 2.6 Apm 2.8 | Equipment | 1 | 4000 | 4000 |
| Frame with legs | Miscellaneous | 1 | 4200 | 4200 |
| Props | Equipment | 4 | 335 | 1340 |
| Motor | Equipment | 4 | 600 | 2400 |
| Electronic Speed Controls | Equipment | 4 | 375 | 1500 |
| Battery 8000mah | Equipment | 1 | 18500 | 18500 |
| Gimbal | Miscellaneous | 1 | 5800 | 5800 |
| Stereo Camera | Equipment | 1 | 15000 | 15000 |