Real Time Detection of Speed Hump/Bump and Distance Estimation with Deep Learning using GPU and ZED Stereo Camera

Varma, Vinay; Adarsh, S.; Ramachandran, K. I.; Nair, Binoy B.

doi:10.1016/j.procs.2018.10.335

Cited by 52 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors have utilized NVIDIA GPU and Stereolabs ZED Stereo camera equipment. The vehicle can be controlled to avoid road speed bumps at certain rate even if that vehicle was driven by driver or autodrived where an alert of road speed bumps occurs so as not to make any sort of uneasiness the travelers just as harm to the vehicle [23], [13]. As in this paper we used the feature in the proposed model to permit threshold instated of using a certain rate.…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach for the Detection of Road Speed Bumps using Accelerometer Sensor

Al-Shargabi¹,

Hassan²,

Al-Rousan³

2020

TEM Journal

View full text Add to dashboard Cite

Smart phones and tablets have turned into an indispensable piece in our society. Accordingly, these devices are equipped with many sensors that can be exploited in many applications such as monitoring road surface condition. It becomes important to find an optimal method for detecting road speed bumps and potholes in order to monitor the road conditions and to alert other moving vehicles in order to slow their speed and avoid any damage and experience safe and comfortable driving. Moreover, data collected by smartphones about road conditions can help city authorities to repair and maintain the roads. The aim of this paper is to introduce a model for detecting road speed bumps and potholes using an Android application based on accelerometer sensor. This application uses data gathered by accelerometer sensor that was collected from various roads in order to determine the accuracy of this proposed approach. The proposed model was implemented as an Android application as a proof of concept and it was tested to check its accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Approach for the Detection of Road Speed Bumps using Accelerometer Sensor

Al-Shargabi¹,

Hassan²,

Al-Rousan³

2020

TEM Journal

View full text Add to dashboard Cite

show abstract

“…Results obtained by Devapriya have a detection rate of 30% that is below the average as seen in Figure 1. Another work related to the conditions considered in this research is that carried out by Varma [31] in which a method is proposed to detect and inform drivers in real time about the presence of speed bumps with or without signaling. For this purpose, Deep Learning techniques are applied using a pre-trained convolutional neuronal network.…”

Section: Related Workmentioning

confidence: 99%

“…In this work, speed bumps with and without marks are detected and a convolutional neural network is also applied for detection. However, the difference with the work of Varma [31] is that when the convolutional neural network fails, stereo vision is applied to detect speed bumps by analyzing the 3D surface elevation because it is not restricted only to its signaling pattern. In addition, the methodology proposed in this work, unlike Varma [31] and Devapriya [8], would make it possible to identify the kind of speed bumps as well as some other details regarding their shape and size.…”

Section: Related Workmentioning

confidence: 99%

Speed Bump Detection on Roads using Artificial Vision

Ballinas-Hernández¹,

Olmos-Pineda²,

Olvera-López³

2019

RCS

View full text Add to dashboard Cite

In recent decades, self-driving has been a topic of wide interest for Artificial Intelligence and the Automotive Industry. The irregularities detection on road surfaces is a task with great challenges. In developing countries, it is very common to find un-marked speed bumps on road surfaces which reduce the security and stability of self-driving cars. The existing techniques have not completely solved the speed bump detection without a well-marked signaling. The main contribution of this work is the design of a methodology that use a pre-trained convolutional neural network and supervised automatic classification, by using the analysis of elevations on surfaces through stereo vision, for detect well-marked and no well-marked speed bumps to improve existing techniques.

show abstract

“…In [ 33 ], CNN and SVM classifiers are used for detection and binary classification of potholes' images collected from multiple sources and attained accuracy of 99.80% for CNN and 88.20% for SVM. Vosco Pereira et al, in [ 34 ], applied Tensorflow API and achieved a precision rate of 97.46% for the real-time detection of road bumps from their dataset that is also available publicly. In [ 35 ], Yolov2 is used by Bhanu Prakash et al for potholes detection using a publicly available potholes' dataset.…”

Section: Introductionmentioning

confidence: 99%

Edge AI‐Based Automated Detection and Classification of Road Anomalies in VANET Using Deep Learning

Bibi

Saeed

Zeb

et al. 2021

Computational Intelligence and Neuroscience

142

View full text Add to dashboard Cite

Road surface defects are crucial problems for safe and smooth traffic flow. Due to climate changes, low quality of construction material, large flow of traffic, and heavy vehicles, road surface anomalies are increasing rapidly. Detection and repairing of these defects are necessary for the safety of drivers, passengers, and vehicles from mechanical faults. In this modern era, autonomous vehicles are an active research area that controls itself with the help of in-vehicle sensors without human commands, especially after the emergence of deep learning (DNN) techniques. A combination of sensors and DNN techniques can be useful for unmanned vehicles for the perception of their surroundings for the detection of tracks and obstacles for smooth traveling based on the deployment of artificial intelligence in vehicles. One of the biggest challenges for autonomous vehicles is to avoid the critical road defects that may lead to dangerous situations. To solve the accident issues and share emergency information, the Intelligent Transportation System (ITS) introduced the concept of vehicular network termed as vehicular ad hoc network (VANET) for achieving security and safety in a traffic flow. A novel mechanism is proposed for the automatic detection of road anomalies by autonomous vehicles and providing road information to upcoming vehicles based on Edge AI and VANET. Road images captured via camera and deployment of the trained model for road anomaly detection in a vehicle could help to reduce the accident rate and risk of hazards on poor road conditions. The techniques Residual Convolutional Neural Network (ResNet-18) and Visual Geometry Group (VGG-11) are applied for the automatic detection and classification of the road with anomalies such as a pothole, bump, crack, and plain roads without anomalies using the dataset from different online sources. The results show that the applied models performed well than other techniques used for road anomalies identification.

show abstract

Real Time Detection of Speed Hump/Bump and Distance Estimation with Deep Learning using GPU and ZED Stereo Camera

Cited by 52 publications

References 10 publications

A Novel Approach for the Detection of Road Speed Bumps using Accelerometer Sensor

A Novel Approach for the Detection of Road Speed Bumps using Accelerometer Sensor

Speed Bump Detection on Roads using Artificial Vision

Edge AI‐Based Automated Detection and Classification of Road Anomalies in VANET Using Deep Learning

Contact Info

Product

Resources

About