Object Detection for Autonomous Vehicle Using TensorFlow

Howal, Sadanand; Jadhav, Aishwarya; Arthshi, Chandrakirti; Nalavade, Sapana; Shinde, Sonam

doi:10.1007/978-3-030-30465-2_11

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of Autonomous cars is based on Swarm Intelligence which is a natural phenomenon such that the birds which fly in the sky manage their speed to avoid collision with other birds [1]. Autonomous vehicles with advanced driver assistance system with the help of several sensors can easily detect and classify objects on the road which reduces fatal accidents [4]. Object detection and identifying the traffic information is one of the major aspects of autonomous cars.…”

Section: Introductionmentioning

confidence: 99%

An Efficient and Reliable Data Dissemination Among Autonomous Cars Through Cluster Based Relaying in VANETS

Neelima

Sankar²

2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

With a lot of advancement in technology, there is an improvement in transportation so as to make the humans comfortable with driving. The idea behind this is the development of Autonomous cars also called as Self driving cars in which driving is similar to humans. The challenges faced in the Autonomous cars are to provide cooperative driving among themselves and collision avoidance between neighbor cars. The Autonomous cars communicate and gather the road information from the Road Side Units (RSU) that is placed along the road. Hence in this paper an efficient data dissemination model is proposed such that instead of making each and every car to communicate with the RSU’s which increases the travel time the autonomous cars moving on the road are formed as clusters based on certain distance limit and the car which is nearer to the RSU is identified as Cluster head. The Cluster head gathers the information from RSU and relays the information to all the other cars in its cluster. As the road information is broadcasted to all the other cars by the cluster head data dissemination becomes faster and travel time of the vehicles can also be reduced to a greater extent. The Cluster head apart from relaying the information of RSU’s can also transmit the information of object detection and traffic signal information to other cars in the cluster.

show abstract

Section: Introductionmentioning

confidence: 99%

An Efficient and Reliable Data Dissemination Among Autonomous Cars Through Cluster Based Relaying in VANETS

Neelima

Sankar²

2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

show abstract

“…One of the essential components of machine learning is the use of algorithms, among which neural networks are gaining popularity. Inspired by the human brain's structure and function, neural networks are wellsuited for complex pattern and relationship tasks (Howal et al, 2020). TensorFlow, an opensource machine learning framework, has emerged as a popular choice due to its ease of use and flexibility.…”

Section: Introductionmentioning

confidence: 99%

“…TensorFlow is an open-source library for numerical computation and machine learning, making it an ideal choice for building neural networks. It allows users to define the structure of a neural network, including the number of layers, neurons in each layer, and activation functions, and then train it using a large dataset (Heghedus et al, 2019;Howal et al, 2020). Neural networks have a wide range of applications, from predicting customer behavior and stock prices in business, to image recognition and speech recognition in daily life.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Business Operations with TensorFlow and Neural Network-based Data Analysis

Hruška¹

2023

Proceedings of the International Scientific Conference Hradec Economic Days 2023

View full text Add to dashboard Cite

A simplified example of building a neural network using TensorFlow is presented in this article. A single-layer neural network, trained with a small dataset of seven data points and optimized with Stochastic Gradient Descent and a mean squared error loss function, is defined for predicting house prices based on the number of rooms. A prediction for a new value is then made with the trained model. This example serves as a demonstration of the potential for neural networks, in combination with TensorFlow, to bring about increased efficiency, productivity, and improved decision making in business and the economy through automation of tasks and processes. This article demonstrates how the use of neural networks can bring increased efficiency and productivity in business operations through the automation of data processing tasks. The implications and possibilities of using neural networks are also analyzed. This paper will serve as a resource for researchers and practitioners interested in using TensorFlow and neural networks for machine learning and data processing. By automating data analysis and prediction, businesses can make more informed decisions and respond more quickly to market changes, resulting in improved financial performance.

show abstract

“…Object detection has been successfully implemented in many applications, such as autonomous vehicle object avoidance [1]. Although many cases have good test performance, there is potential for further improvements by using an optimised training dataset, which is important to consider as it is one of the fundamental tools used during training.…”

Section: Introductionmentioning

confidence: 99%

Development of an Optimised Dataset for Training a Deep Neural Network

Newman¹,

Petzing²,

Goh³

et al. 2021

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

Artificial intelligence in computer vision has focused on improving test performance using techniques and architectures related to deep neural networks. However, improvements can also be achieved by carefully selecting the training dataset images. Environmental factors, such as light intensity, affect the image’s appearance and by choosing optimal factor levels the neural network’s performance can improve. However, little research into processes which help identify optimal levels is available. This research presents a case study which uses a process for developing an optimised dataset for training an object detection neural network. Images are gathered under controlled conditions using multiple factors to construct various training datasets. Each dataset is used to train the same neural network and the test performance compared to identify the optimal factors. The opportunity to use synthetic images is introduced, which has many advantages including creating images when real-world images are unavailable, and more easily controlled factors.

show abstract

Object Detection for Autonomous Vehicle Using TensorFlow

Cited by 7 publications

References 14 publications

An Efficient and Reliable Data Dissemination Among Autonomous Cars Through Cluster Based Relaying in VANETS

An Efficient and Reliable Data Dissemination Among Autonomous Cars Through Cluster Based Relaying in VANETS

Enhancing Business Operations with TensorFlow and Neural Network-based Data Analysis

Development of an Optimised Dataset for Training a Deep Neural Network

Contact Info

Product

Resources

About