Real-time Object Detection using Haar Cascade Classifier for Robot Cars

Ensuring accurate detection and identification of objects in the environment is crucial for the safe and efficient operation of autonomous vehicles in today's world. The Haar Cascade Classifier, a machine learning algorithm for object detection, has gained significant popularity in recent years...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC) S. 64 - 70
Hauptverfasser: Gharge, Saylee, Patil, Aditi, Patel, Shrutika, Shetty, Vaishnavi, Mundhada, Nidhi
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 06.07.2023
Schlagworte:
Arduino Uno
Autonomous automobiles
Classification algorithms
Feature extraction
Haar cascade classifier
Machine learning algorithms
Object detection
Object recognition
Raspberry Pi
Self-Driving Robot Car
Training
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Ensuring accurate detection and identification of objects in the environment is crucial for the safe and efficient operation of autonomous vehicles in today's world. The Haar Cascade Classifier, a machine learning algorithm for object detection, has gained significant popularity in recent years. This algorithm analyzes specific features of an object and has found diverse applications, including facial recognition. This research aims to investigate the application of the Haar Cascade Classifier in an autonomous robot car. The study encompasses the Haar-like features, which are fundamental building blocks of the algorithm, and the process for training and testing the dataset. The research also explores the actions that the robot car can take based on the type of object detected in its surroundings and delves into the practical implementation of the Haar Cascade Classifier in an autonomous vehicle. Furthermore, this work provides valuable insights into the effectiveness of the algorithm in detecting and identifying objects in an autonomous vehicle's environment.
DOI:10.1109/ICESC57686.2023.10193401