A fast instance segmentation with one-stage multi-task deep neural network for autonomous driving

2021 ◽  
Vol 93 ◽  
pp. 107194
Author(s):  
Kuo-Kun Tseng ◽  
Jiangrui Lin ◽  
Chien-Ming Chen ◽  
Mohammad Mehedi Hassan
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Autonomous Driving ◽  
One Stage ◽  
Instance Segmentation

Deep Neural Network Model based on One-Stage Detector for Identifying Fundus Lesions

2021 ◽  
Author(s):  
Carlos Santos ◽  
Marilton Sanchotene De Aguiar ◽  
Daniel Welfer ◽  
Bruno Belloni
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
Model Based ◽  
One Stage

scholarly journals Design and Optimization of a Deep Neural Network Architecture for Traffic Light Detection

2020 ◽  
Vol 77 ◽  
pp. 01002
Author(s):  
Tomohide Fukuchi ◽  
Mark Ogbodo Ikechukwu ◽  
Abderazek Ben Abdallah
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Autonomous Driving ◽  
Research Trend ◽  
Traffic Light ◽  
Light Detection ◽  
Driving System ◽  
Design And Optimization ◽  
Autonomous Driving System

Autonomous Driving has recently become a research trend and efficient autonomous driving system is difficult to achieve due to safety concerns, Applying traffic light recognition to autonomous driving system is one of the factors to prevent accidents that occur as a result of traffic light violation. To realize safe autonomous driving system, we propose in this work a design and optimization of a traffic light detection system based on deep neural network. We designed a lightweight convolution neural network with parameters less than 10000 and implemented in software. We achieved 98.3% inference accuracy with 2.5 fps response time. Also we optimized the input image pixel values with normalization and optimized convolution layer with pipeline on FPGA with 5% resource consumption.

scholarly journals AutoRemover: Automatic Object Removal for Autonomous Driving Videos

2020 ◽  
Vol 34 (07) ◽  
pp. 12853-12861
Author(s):  
Rong Zhang ◽  
Wei Li ◽  
Peng Wang ◽  
Chenye Guan ◽  
Jin Fang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Moving Objects ◽  
State Of The Art ◽  
Autonomous Driving ◽  
Object Removal ◽  
3D Data ◽  
Source Data ◽  
Tightly Coupled ◽  
Geometric Relationship

Motivated by the need for photo-realistic simulation in autonomous driving, in this paper we present a video inpainting algorithm AutoRemover, designed specifically for generating street-view videos without any moving objects. In our setup we have two challenges: the first is the shadow, shadows are usually unlabeled but tightly coupled with the moving objects. The second is the large ego-motion in the videos. To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically. To deal with large ego-motion, we take advantage of the multi-source data, in particular the 3D data, in autonomous driving. More specifically, the geometric relationship between frames is incorporated into an inpainting deep neural network to produce high-quality structurally consistent video output. Experiments show that our method outperforms other state-of-the-art (SOTA) object removal algorithms, reducing the RMSE by over 19%.

Deep Neural Network Perception Models and Robust Autonomous Driving Systems: Practical Solutions for Mitigation and Improvement

2021 ◽  
Vol 38 (1) ◽  
pp. 22-30
Author(s):  
Mohammad Javad Shafiee ◽  
Ahmadreza Jeddi ◽  
Amir Nazemi ◽  
Paul Fieguth ◽  
Alexander Wong
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Autonomous Driving

scholarly journals Path Planning for Autonomous Driving of Mobile Robots using Deep Neural Network based Model Predictive Control

2021 ◽  
Vol 11 (11) ◽  
pp. 31-38
Author(s):  
Kiwon Yeom ◽  
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Model Predictive Control ◽  
Mobile Robot ◽  
Predictive Control ◽  
Deep Neural Network ◽  
Optimal Solution ◽  
Autonomous Driving ◽  
Physical Constraints ◽  
Predictive Controller

A car-like mobile robot is a nonlinear affine system, and the mobile robot has physical constraints such as velocity and acceleration. Thus, no satisfactory solution may not be provided during self-driving under unknown environments. Although Model Predictive Control (MPC) has provided good performance in terms of control strategy, it is difficult to optimize the control parameters due to the uncertainty and non-linearity of a process. In this paper, the Deep Neural Networks (DNN) based Model Predictive Controller (MPC) is derived for tracking the given path during self-driving. The proposed DNN MPC produces the global optimal solution which has better performance than traditional MPC in terms of the errors of position and orientation. This paper verifies that the proposed DNN MPC based controller can track the desired path with high precision for the car-like mobile robot. Keywords—Path planning, autonomous driving, mobile robot, deep neural network, model predictive control.

scholarly journals An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2064 ◽  
Author(s):  
Jelena Kocić ◽  
Nenad Jovičić ◽  
Vujo Drndarević
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
Autonomous Driving ◽  
Frame Rate ◽  
Power Cost ◽  
End To End

In this paper, one solution for an end-to-end deep neural network for autonomous driving is presented. The main objective of our work was to achieve autonomous driving with a light deep neural network suitable for deployment on embedded automotive platforms. There are several end-to-end deep neural networks used for autonomous driving, where the input to the machine learning algorithm are camera images and the output is the steering angle prediction, but those convolutional neural networks are significantly more complex than the network architecture we are proposing. The network architecture, computational complexity, and performance evaluation during autonomous driving using our network are compared with two other convolutional neural networks that we re-implemented with the aim to have an objective evaluation of the proposed network. The trained model of the proposed network is four times smaller than the PilotNet model and about 250 times smaller than AlexNet model. While complexity and size of the novel network are reduced in comparison to other models, which leads to lower latency and higher frame rate during inference, our network maintained the performance, achieving successful autonomous driving with similar efficiency compared to autonomous driving using two other models. Moreover, the proposed deep neural network downsized the needs for real-time inference hardware in terms of computational power, cost, and size.

Sign in / Sign up

Export Citation Format

Share Document