OBJECTION DETECTION USING HISTOGRAM ORIENTED GRADIENT & SUPPORT VECTOR MACHINE

Repetitive tasks and high accuracy became the two contradictory needs of any industrial process. By introducing autonomous robotic applications, easy repetitive tasks will be accomplished keeping the strain of the accuracy in mind. At present during this quick growing industrial age each company nee

Project Title

OBJECTION DETECTION USING HISTOGRAM ORIENTED GRADIENT & SUPPORT VECTOR MACHINE

Project Area of Specialization

Artificial Intelligence

Project Summary

Repetitive tasks and high accuracy became the two contradictory needs of any industrial process. By introducing autonomous robotic applications, easy repetitive tasks will be accomplished keeping the strain of the accuracy in mind. At present during this quick growing industrial age each company needs speed in producing to cope up with the method of sorting objects can be created utterly autonomous by machines which can recognize objects. Technology is increasing day by day and modification advances have become potential for object sorting, for object tracking activity to become smarter and intelligent Requirements of systems are terribly costly and high spec system consumes more electrical power and will be tough to carry if needed. For this we wanted an occasional value and high description system. In this Project we present a system in which a robotic arm sorts object according to their color. Objects are categorized into 3 colors which are red blue and green. The image of the object to be sorted is captured by using digital camera and HOG is used for image processing. For object tracking computing device (processor electronic computer information processing system machine) should equipped with camera that could process images, this requires high specification configuration system.

Project Objectives

Object detection has become one of the most popular tasks when it comes to Deep Learning. Object identification can be utilized to include items in a picture and choose and mark their correct areas, all while precisely naming them. Article discovery is a PC vision method that permits us to distinguish and find objects in a picture or video. In order to achieve project accuracy, a variety of methods can be implemented. Because of its speed and performance, it can be introduced effectively and perfectly for projects, thanks to HOG and SVM, which make it more reliable and perfect for this. HOG breaks pixels into little bits, resulting in a large number of pixels in a picture. Because the size of the picture shrinks and it runs in the system in under a minute, SVM stores unstructured and semi-structured data such as photos, content, and tree. For this type of task, HOG and SVM are more cost-effective and efficient.

Project Implementation Method

This project can assist people in reducing human effort and saving time. The system was created using the Python programming language and the HOG and SVM algorithms. Image processing is done with a Histogram Oriented Gradient, object sorting is done with a Support Vector Machine, and picking and placing objects is done with a robotic arm. The system was created using the Python programming language and the HOG and SVM algorithms. For sorting the objects, we connected the robotic arm with a camera, positioned the objects on a reel, and placed the camera on top. The image is captured by a camera, and HOG processes it before sending it to the robotic arm through serial connection. SVM is then used to position the object at the desired location if it is related; otherwise, robotic arm activity is not necessary. We adapted the framework for object sorting and proposed a fully automated mechanical arranging framework to sort objects in this venture. In the first segment of the framework, all objects to be arranged are placed on a moving reel, these objects are boxes, and then these boxes with different colors are placed on a moving reel, we have an edge line to determine the constraint of camera movement, the camera used for this situation is overhead, and the picture taken by the camera is sent to the computer, where we use HOG and other algorithms. For image processing, a camera was used, and HOG was used to handle the acquired image and determine shading. A robotic arm is used to choose and arrange objects in predetermined locations; this framework can distinguish between three different colors: red, blue, and green.

Benefits of the Project

With the incrementing work on technological furtherance and sustainability the main axis for the engineers to develop smarter way  of doing any task  as we know that the activity of science is usually for the exceeding of world so same goes for this scenario, Object detection is inextricably linked to other computer vision techniques like image segmentation and image recognition, which let us comprehend and evaluate scenes in movies and photos. Several real-world use cases for object detection are now being implemented in the market, and they are having a huge impact on various industries. Through this project we can easily detect the desire object and place it into predefine position.

Technical Details of Final Deliverable

The technical details of the project are as following:

1) The circuit is made through integrated circuits and ICs , the main controlling brain is the Arduino mega.

2) There are a Robotic arm needs to program to execute the specific task or job quickly, effectively and with high accuracy. Industrially robotic arm is used for welding, assembling, packaging, painting etc.

3) The inputs are taken from environment as well as the used parameters in the circuits as well through sensors.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Manufacturing

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com