The main aim of this project is to build a mobile device for blind persons which uses to detect the object along with obstacles via camera using raspberry pi3 and openCV image processing. This system to detect the object using machine learning algorithm which is written in embedded Linux platform. All images like table, chair, bottle…..we will prepared dataset and stored into the raspberry pi and trained for preprocessing. This system uses Ultrasonic sensor to detect the nearest obstacle and announce the voice through speaker. OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library. The library has more than 2500 optimized algorithms, which includes a comprehensive set of both classic and state-of-the-art computer vision and machine learning algorithms. It mainly focuses on image processing; video capture and analysis including features like face detection and object detection. In this project we are using python language to write the program. Python is an interpreter, object-oriented, high-level programming language with dynamic semantics. Python's simple, easy to learn syntax emphasizes readability and therefore reduces the cost of program maintenance. Python supports modules and packages, which encourages program modularity and code reuse. The controlling device of the whole unit is a Raspberrypi3 processor to which input and output modules are interfaced. Raspberrypi3 has Broadcom BCM2837B0, Cortex-A53 (ARMv8) 1GB LPDDR2 SDRAM 1.4GHz 64-bit quad-core processor, dual-band wireless LAN, Bluetooth 4.2/BLE, faster Ethernet, and Power-over-Ethernet support (with separate PoE HAT). The processor is programmed in PYTHON language which intelligently performs the specific task. Here, the processor gets input from the sensor and pi camera attached to the raspberry pi. This input is processed by processor and announce the voice appropriately.  

The major features of this project are:

• 1. Automatic obstacle sensing.
  2. Automatic object detection and classification.
  3. Using Raspberrypi3 processor to achieve this task.
  4. Using pi camera and openCV machine learning to detect the objects
  5. Using Ultrasonic sensor to detect the obstacle.
  6. Voice alerts for obstacle detection.
  7. Voice announce for object detection.

     

The major building blocks of this project:  

• Battery power supply.
• Raspberry Pi3 Processor.
• SD Card.
• Ultrasonic sensor.
• Pi camera.
• LED indicators.

       

Software’s used in the project:

 

1. Python Programming.
2. OpenCV MACHINE LEARNING Image processing.
3. Embedded Linux operating system.
4. Express SCH for Circuit design.

   

Block Diagram:

video: