Object Detection and Recognition System using Tensor Flow

Date
2020
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
We are presenting the design and implementation of a real-time approach to detect and track features in a structured context using TensorFlow. Object detection and recognition are essential and challenging tasks in many computer vision applications such as vehicle navigation, surveillance and monitoring, self-driving cars, home automation, and autonomous robot navigation. Object detection requires placing objects in the framework of a video or camera. Every tracking method entails an object detection mechanism either in every frame or when something first surfaces in the camera view. The advanced computers, high-quality camera, and economical video cameras, and the growing need for automated video analysis have produced a great deal of investment in object tracking algorithms. There are three key measures in object analysis: detecting objects, recognizing objects from each frame to frame, and interpreting object tracks to identify their behavior. Therefore, object tracking is relevant in the tasks of automatic detection, tracking, motion-based recognition, and many others. This paper discusses a deep learning method for the robust detection of distinctive objects by the object detection model and evaluating the flexibility of the TensorFlow Object Detection Framework to solve real-time problems.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN