scholarly journals Efficient Deep Network Architecture for Vision-Based Vehicle Detection Keyvan Kasiri,

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
Keyvan Kasiri ◽  
Mohammad Javad Shafiee ◽  
Francis Li ◽  
Alexander Wong ◽  
Justin Eichel
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Vehicle Detection ◽  
Transportation Systems ◽  
Surveillance Systems ◽  
Performance Accuracy ◽  
Sparse Set

With the progress in intelligent transportation systems in smartcities, vision-based vehicle detection is becoming an important issuein the vision-based surveillance systems. With the advent ofthe big data era, deep learning methods have been increasinglyemployed in the detection, classification, and recognition applicationsdue to their performance accuracy, however, there are stillmajor concerns regarding deployment of such methods in embeddedapplications. This paper offers an efficient process leveragingthe idea of evolutionary deep intelligence on a state-of-the-art deepneural network. Using this approach, the deep neural network isevolved towards a highly sparse set of synaptic weights and clusters.Experimental results for the task of vehicle detection demonstratethat the evolved deep neural network can achieve a substantialimprovement in architecture efficiency adapting for GPUacceleratedapplications without significant sacrifices in detectionaccuracy. The architectural efficiency of ~4X-fold and ~2X-folddecrease is obtained in synaptic weights and clusters, respectively,while the accuracy of 92.8% (drop of less than 4% compared to theoriginal network model) is achieved. Detection results and networkefficiency for the vehicular application are promising, and opensthe door to a wider range of applications in deep learning.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals Spectral deep learning for prediction and prospective validation of functional groups

2020 ◽  
Vol 11 (18) ◽  
pp. 4618-4630 ◽  
Author(s):  
Jonathan A. Fine ◽  
Anand A. Rajasekar ◽  
Krupal P. Jethava ◽  
Gaurav Chopra
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Functional Groups ◽  
Network Architecture ◽  
Mass Spectra ◽  
Deep Neural Network ◽  
Complex Mixtures ◽  
Neural Network Architecture

A new multi-label deep neural network architecture is used to combine Infrared and mass spectra, trained on single compounds to predict functional groups, and experimentally validated on complex mixtures.

scholarly journals FGSC: Fuzzy Guided Scale Choice SSD Model for Edge AI Design on Real-Time Vehicle Detection and Class Counting

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7399
Author(s):  
Ming-Hwa Sheu ◽  
S M Salahuddin Morsalin ◽  
Jia-Xiang Zheng ◽  
Shih-Chang Hsia ◽  
Cheng-Jian Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Vehicle Detection ◽  
Traffic Monitoring ◽  
Sigmoid Function ◽  
Real Time Processing ◽  
Scale Choice ◽  
Training Stage

The aim of this paper is to distinguish the vehicle detection and count the class number in each classification from the inputs. We proposed the use of Fuzzy Guided Scale Choice (FGSC)-based SSD deep neural network architecture for vehicle detection and class counting with parameter optimization. The 'FGSC' blocks are integrated into the convolutional layers of the model, which emphasize essential features while ignoring less important ones that are not significant for the operation. We created the passing detection lines and class counting windows and connected them with the proposed FGSC-SSD deep neural network model. The 'FGSC' blocks in the convolution layer emphasize essential features and find out unnecessary features by using the scale choice method at the training stage and eliminate that significant speedup of the model. In addition, FGSC blocks avoided many unusable parameters in the saturation interval and improved the performance efficiency. In addition, the Fuzzy Sigmoid Function (FSF) increases the activation interval through fuzzy logic. While performing operations, the FGSC-SSD model reduces the computational complexity of convolutional layers and their parameters. As a result, the model tested Frames Per Second (FPS) on edge artificial intelligence (AI) and reached a real-time processing speed of 38.4 and an accuracy rate of more than 94%. Therefore, this work might be considered an improvement to the traffic monitoring approach by using edge AI applications.

scholarly journals Deep Neural Network Architecture Search for Wearable Heart Rate Estimations

2021 ◽  
Author(s):  
Daniel Ray ◽  
Tim Collins ◽  
Prasad Ponnapalli
Keyword(s):  
Neural Network ◽  
Heart Rate ◽  
Deep Learning ◽  
Network Architecture ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Data Driven ◽  
Network Architectures ◽  
Learning Approaches ◽  
Neural Network Architecture

Extracting accurate heart rate estimations from wrist-worn photoplethysmography (PPG) devices is challenging due to the signal containing artifacts from several sources. Deep Learning approaches have shown very promising results outperforming classical methods with improvements of 21% and 31% on two state-of-the-art datasets. This paper provides an analysis of several data-driven methods for creating deep neural network architectures with hopes of further improvements.

scholarly journals A NOVEL DEEP LEARNING BASED METHOD FOR DETECTION AND COUNTING OF VEHICLES IN URBAN TRAFFIC SURVEILLANCE SYSTEMS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 793-800
Author(s):  
J. J. Majin ◽  
Y. M. Valencia ◽  
M. E. Stivanello ◽  
M. R. Stemmer ◽  
J. D. Salazar
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Management Strategies ◽  
Transportation Systems ◽  
Urban Traffic ◽  
Surveillance Systems ◽  
Real Time Processing ◽  
Detection Model

Abstract. In intelligent transportation systems (ITS), it is essential to obtain reliable statistics of the vehicular flow in order to create urban traffic management strategies. These systems have benefited from the increase in computational resources and the improvement of image processing methods, especially in object detection based on deep learning. This paper proposes a method for vehicle counting composed of three stages: object detection, tracking and trajectory processing. In order to select the detection model with the best trade-off between accuracy and speed, the following one-stage detection models were compared: SSD512, CenterNet, Efficiedet-D0 and YOLO family models (v2, v3 and v4). Experimental results conducted on the benchmark dataset show that the best rates among the detection models were obtained using YOLOv4 with mAP = 87% and a processing speed of 18 FPS. On the other hand, the accuracy obtained in the proposed counting method was 94% with a real-time processing rate lower than 1.9.

scholarly journals Vehicle Classification and Detection using Deep Learning

2019 ◽  
Vol 9 (1S5) ◽  
pp. 24-28
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Convolution Neural Network ◽  
Vehicle Classification ◽  
Hard Problem ◽  
Bounding Box ◽  
Probability Estimates

Intelligent transportation systems have acknowledged a ration of attention in the last decades. In this area vehicle classification and localization is the key task. In this task the biggest challenge is to discriminate the features of different vehicles. Further, vehicle classification and detection is a hard problem to identify and locate because wide variety of vehicles don’t follow the lane discipline. In this article, to identify and locate, we have created a convolution neural network from scratch to classify and detect objects using a modern convolution neural network based on fast regions. In this work we have considered three types of vehicles like bus, car and bike for classification and detection. Our approach will use the entire image as input and create a bounding box with probability estimates of the feature classes as output. The results of the experiment have shown that the projected system can considerably improve the accuracy of the detection.

scholarly journals Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

2021 ◽  
Vol 11 (7) ◽  
pp. 3059
Author(s):  
Myeong-Hun Jeong ◽  
Tae-Young Lee ◽  
Seung-Bae Jeon ◽  
Minkyo Youm
Keyword(s):  
Neural Network ◽  
Intelligent Transportation Systems ◽  
Moving Average ◽  
Computational Cost ◽  
Nonlinear Problems ◽  
Transportation Systems ◽  
Mobility Data ◽  
Challenges And Opportunities ◽  
Moving Average Model ◽  
Gated Recurrent Unit

Movement analytics and mobility insights play a crucial role in urban planning and transportation management. The plethora of mobility data sources, such as GPS trajectories, poses new challenges and opportunities for understanding and predicting movement patterns. In this study, we predict highway speed using a gated recurrent unit (GRU) neural network. Based on statistical models, previous approaches suffer from the inherited features of traffic data, such as nonlinear problems. The proposed method predicts highway speed based on the GRU method after training on digital tachograph data (DTG). The DTG data were recorded in one month, giving approximately 300 million records. These data included the velocity and locations of vehicles on the highway. Experimental results demonstrate that the GRU-based deep learning approach outperformed the state-of-the-art alternatives, the autoregressive integrated moving average model, and the long short-term neural network (LSTM) model, in terms of prediction accuracy. Further, the computational cost of the GRU model was lower than that of the LSTM. The proposed method can be applied to traffic prediction and intelligent transportation systems.

Sign in / Sign up

Export Citation Format

Share Document