Automatic vehicle identification system using machine learning and robot operating system (ROS)

Rokonuzzaman, Md.; Amin, M. Abdullah Al; Ahmed, Kazi Main Uddin; Rahman, Md. Ashib

doi:10.1109/icaee.2017.8255362

Cited by 7 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It consists of libraries, tools, and conventions which greatly simplify the task of building a complex robotic system. Due to the open source nature of the framework, ROS has an increasing number of different tools which make interfacing with different sensors and devices much easier [18]. In our experiments, the publish-subscribe model in ROS was used to support communication between UAVs.…”

Section: Communication Systemmentioning

confidence: 99%

Live-fly experimentation for pigeon-inspired obstacle avoidance of quadrotor unmanned aerial vehicles

Huo

Duan

Qing

et al. 2019

Sci. China Inf. Sci.

View full text Add to dashboard Cite

In this paper, we applied a pigeon-inspired obstacle-avoidance model to the flight of quadrotor UAVs through environments with obstacles. Pigeons bias their flight direction by considering the largest gap and minimum required steering. Owing to the similarities between pigeon flocks and UAV swarms in terms of mission requirements, the pigeon-inspired obstacle-avoidance model is used to control a UAV swarm so that it can fly through a complex environment with multiple obstacles. The simulation and flight results illustrate the viability and superiority of pigeon-inspired obstacle avoidance for quadrotor UAVs.

show abstract

Section: Communication Systemmentioning

confidence: 99%

Live-fly experimentation for pigeon-inspired obstacle avoidance of quadrotor unmanned aerial vehicles

Huo

Duan

Qing

et al. 2019

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…There exist a fast and trainable method for object recognition, The Haar Cascade Classifier [10] this method also used by [11] with the detector trained by BIT-Dataset and conclude that Haar Cascade Classifier is a good candidate for object detector. Research by [12] combines the Haar detector with the K-nearest neighbour technique to identify the license plate of vehicles that claimed to offer great efficiency for practical use. According to [13], the classifier superior performance over image-intensity based algorithm encourages the use of Haar Cascade in this work.…”

Section: A Haar-cascade Classifiermentioning

confidence: 99%

Vehicular networking and computer vision-based distance estimation for VANET application using Raspberry Pi 3

Pratama

Gruosso

Santoso

et al. 2019

J. Mechatron. Electr. Power Veh. Technol.

View full text Add to dashboard Cite

This research was implementing vehicle networking using WIFI connection and computer vision to measure the distance of vehicles in front of a driver. In particular, this works aimed to improve a safe driving environment thus supporting the current technology concept being developed for inter-vehicular networking, VANET, especially in its safety application such as Overtaking Assistance System. Moreover, it can wirelessly share useful visual information such as hazard area of a road accident. In accordance with Vehicle-to-Vehicle (V2V) concept, a vehicle required to be able to conduct networking via a wireless connection. Useful data and video were the objects to be sent over the network established. The distance of a vehicle to other vehicles towards it is measured and sent via WIFI together with a video stream of the scenery experienced by the front vehicle. Haar Cascade Classifier is chosen to perform the detection. For distance estimation, at least three methods have been compared in this research and found evidence that, for measuring 5 meters, the iterative methods shows 5.80. This method performs well up to 15 meters. For measuring 20 meters, P3P method shows a better result with only 0.71 meters to the ground truth. To provide a physical implementation for both the detection and distance estimation mechanism, those methods were applied in a compact small-sized vehicle-friendly computer device the Raspberry Pi. The performance of the built system then analyzed in terms of streaming latency and accuracy of distance estimation and shows a good result in measuring distance up to 20 meters.

show abstract

“…With the rapid growth of the number of vehicles, the demand of vehicle production line supervision, traffic video surveillance is increasing [1,2]. As a result, the accuracy in vehicle identification is required to be getting higher.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Identification Using Wavelet Entropy and Particle Swarm Optimization Support Vector Machine

Bao¹,

Nakamura²

2018

Proceedings of the 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 201

View full text Add to dashboard Cite

Abstract:In order to identify Ford vehicles from non-Ford vehicles, this paper proposed a novel method based on the combination of wavelet entropy, particle swarm optimization, and support vector machine. We collect a 100-image dataset, 50 are Ford vehicles and the rest 50 are non-Ford vehicles. The results show that our method obtained a sensitivity of 82.20± 3.94%, a specificity of 81.60± 3.50%, and an accuracy of 81.90± 0.74%. In all, this method is promising in vehicle identification.

show abstract

Automatic vehicle identification system using machine learning and robot operating system (ROS)

Cited by 7 publications

References 13 publications

Live-fly experimentation for pigeon-inspired obstacle avoidance of quadrotor unmanned aerial vehicles

Live-fly experimentation for pigeon-inspired obstacle avoidance of quadrotor unmanned aerial vehicles

Vehicular networking and computer vision-based distance estimation for VANET application using Raspberry Pi 3

Vehicle Identification Using Wavelet Entropy and Particle Swarm Optimization Support Vector Machine

Contact Info

Product

Resources

About