Shape Based Object Classification And Sorting Using DC Servo Motors
Automation has led to the growth of industries in recent years. For better performance of industrial process automated machines are used. Image processing has led to advancements in applications of embedded systems. Sorting of objects are usually done by humans which takes a lot of time and effort.
2025-06-28 16:34:59 - Adil Khan
Shape Based Object Classification And Sorting Using DC Servo Motors
Project Area of Specialization Electrical/Electronic EngineeringProject SummaryAutomation has led to the growth of industries in recent years. For better performance of industrial process automated machines are used. Image processing has led to advancements in applications of embedded systems. Sorting of objects are usually done by humans which takes a lot of time and effort. Using Computer Vision techniques, a conveyor belt system is developed using servo motors and mechanical structures, which can identify and sort various objects. This reduces human effort, time consumed and also improves the time to market the products.
This design uses a low cost hardware and open source programming language and image processing libraries for achieving the goal of sorting objects. Raspberry Pi 3 with Linux operating system is used to process images and as the controlling unit to drive various hardware devices.
The goal of object recognition is to automatically detect the objects in the screen and classify them according to their properties. This process repeats for all the frames of the captured images. The region of interest is determined by training a model from object samples.
The system has a conveyor belt which is driven by DC servo motors and pulley arrangement. Object is fed from one end of the belt. The pulley that drives the conveyor belt is called drive pulley and the end pulley is called as the idler pulley. Pi camera is used to continuously monitor the objects and identify them. The recognized objects are sorted by the sorting mechanism installed at end of conveyor belt.
The system can be used:
1. In food industry to identify rotted fruits and vegetables.
2. In small scale and large scale industries, to sort the products based on the various parameters e.g. color, shape.
3. In production units to scan and identify the defects in raw materials.
4. In malls (to segregate and separate different clothes, toys, bags etc.) and in small shop.
5. In fruits and vegetable farming areas (rural areas) where installation of expensive sorters is very difficult.
Project ObjectivesThe main objective of our project is to design the mechanism of Object Classification by using image processing based on shape and Sorting using DC Servo Motors
Project Implementation MethodThis system has a conveyor belt which runs with the help of servo motors and corresponding pulleys which constantly run at a desirable speed. The servo motors are initialized to run the conveyor belt. Different objects are fed on the feed-side of the belt and landed on the rotating conveyor belt, and they rely on the conveyor belt friction to be delivered to discharge end. Pi camera is used to continuously monitor the objects and identify them. The objects are classified by camera using the template matching technique. Once the objects are recognized or classified into a particular group, the actuators are activated to sort the objects.
Block Diagram:
Benifits of this industrial project are :
1) Man power is condensed
2) Economical technology
3) A broad scope for future advancement
4) Can be programmed to detect irregular shapes
5) High efficiency.
6) High speed of operation.
7) High precision: margin of error can be reduced to great extent.
8) Low failure rate with long life.
9) Reliable operation and maintenance.
10) Fully automatic operation.
Technical Details of Final DeliverableObject recognition is done in real time using a Pi camera by training various images.The training process is implemented using Python 2.7 and OpenCV library in Raspberry Pi model with quad core processor, 1 GB RAM, CPU at 1.20 GHz. The frame rate was found to be less than 10 fps at low resolution of 320*240. The training process produces a classifier which is later used for testing. Also the conveyor belt is tested by driving the servo motors. Later, Commands are sent to the Raspberry Pi using server and client model as the objects are detected using Pi camera. The client process will be running continuously on the Raspberry Pi. Whenever a particular set of objects are detected in the server computer, a code is sent to the client python script running in Raspberry Pi using socket communication. The client runs the corresponding thread and activates the actuator. The frame rate in the computer was found to be around 10 fps even at a higher resolution of 800*600. Thus, the real time recognition is improved using this approach
1. Conveyor Belt:
Belt Width: 1.2 feet
Belt Length: 7.5 feet
2. Raspberry Pi 3
1.2GHz 64-bit quad-core CPU 1GB RAM
3. Pi Camera:
5MP Omni vision 5647 Camera module
Still Picture Resolution: 2592 x 1944
Video: Supports 1080p
4. IR Sensor:
Detection distance: 2 ~ 30cm
Final Deliverable of the Project HW/SW integrated systemCore Industry ManufacturingOther IndustriesCore Technology OthersOther TechnologiesSustainable Development Goals Decent Work and Economic Growth, Industry, Innovation and InfrastructureRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 55690 | |||
| Raspberry Pi 3 | Equipment | 1 | 10000 | 10000 |
| Pi Camera | Equipment | 1 | 2500 | 2500 |
| SD Card 32 GB | Equipment | 1 | 1200 | 1200 |
| Conveyor Belt Structure | Equipment | 1 | 20000 | 20000 |
| DC Motor | Equipment | 1 | 3000 | 3000 |
| Actuator Motors | Equipment | 3 | 2500 | 7500 |
| IR sensor | Equipment | 3 | 250 | 750 |
| Power Supply | Equipment | 1 | 1500 | 1500 |
| Travel Expenses | Miscellaneous | 12 | 120 | 1440 |
| Report Printing | Miscellaneous | 5 | 1200 | 6000 |
| Panaflex Printing | Miscellaneous | 2 | 500 | 1000 |
| Brochure Printing | Miscellaneous | 40 | 20 | 800 |