scholarly journals Recognize Moving Objects Around an Autonomous Vehicle Considering a Deep-learning Detector Model and Dynamic Bayesian Occupancy

Author(s):  
Andres E. Gomez Hernandez ◽  
Ozgur Erkent ◽  
Christian Laugier
2021 ◽  
Vol 54 (4) ◽  
pp. 1-37
Author(s):  
Azzedine Boukerche ◽  
Xiren Ma

Vision-based Automated Vehicle Recognition (VAVR) has attracted considerable attention recently. Particularly given the reliance on emerging deep learning methods, which have powerful feature extraction and pattern learning abilities, vehicle recognition has made significant progress. VAVR is an essential part of Intelligent Transportation Systems. The VAVR system can fast and accurately locate a target vehicle, which significantly helps improve regional security. A comprehensive VAVR system contains three components: Vehicle Detection (VD), Vehicle Make and Model Recognition (VMMR), and Vehicle Re-identification (VRe-ID). These components perform coarse-to-fine recognition tasks in three steps. In this article, we conduct a thorough review and comparison of the state-of-the-art deep learning--based models proposed for VAVR. We present a detailed introduction to different vehicle recognition datasets used for a comprehensive evaluation of the proposed models. We also critically discuss the major challenges and future research trends involved in each task. Finally, we summarize the characteristics of the methods for each task. Our comprehensive model analysis will help researchers that are interested in VD, VMMR, and VRe-ID and provide them with possible directions to solve current challenges and further improve the performance and robustness of models.


2020 ◽  
Vol 19 (1) ◽  
pp. 85-88
Author(s):  
A. S. J. Cervera ◽  
F. J. Alonso ◽  
F. S. García ◽  
A. D. Alvarez

Roundabouts provide safe and fast circulation as well as many environmental advantages, but drivers adopting unsafe behaviours while circulating through them may cause safety issues, provoking accidents. In this paper we propose a way of training an autonomous vehicle in order to behave in a human and safe way when entering a roundabout. By placing a number of cameras in our vehicle and processing their video feeds through a series of algorithms, including Machine Learning, we can build a representation of the state of the surrounding environment. Then, we use another set of Deep Learning algorithms to analyze the data and determine the safest way of circulating through a roundabout given the current state of the environment, including nearby vehicles with their estimated positions, speeds and accelerations. By watching multiple attempts of a human entering a roundabout with both safe and unsafe behaviours, our second set of algorithms can learn to mimic the human’s good attempts and act in the same way as him, which is key to a safe implementation of autonomous vehicles. This work details the series of steps that we took, from building the representation of our environment to acting according to it in order to attain safe entry into single lane roundabouts.


2018 ◽  
Vol 5 (9 (95)) ◽  
pp. 6-17
Author(s):  
Bassant Mohamed Elbagoury ◽  
Rytis Maskeliunas ◽  
Abdel Badeeh Mohamed M. Salem

2021 ◽  
Vol 336 ◽  
pp. 07004
Author(s):  
Ruoyu Fang ◽  
Cheng Cai

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.


Author(s):  
Can Xu ◽  
Wanzhong Zhao ◽  
Jingqiang Liu ◽  
Feng Chen

To improve the agility and efficiency of the highway decision-making system and overcome the local optimal dilemma of the existing safety field, this paper builds an improved safety field to reflect the advantage of the reachable states and the learning process is further employed to make the decision long-term optimal. Firstly, the improved safety field is prepared by the kinematic model-based prediction of surrounding vehicles and the boundary is determined elaborately to ensure real-time performance. Then, the field is constructed by three individual fields. One is the kinematic field, which is built based the safe-distance model to measure the colliding risk of both moving or no-moving objects accurately. Another is the road field that reflects the lane-marker constraint. The last is the efficiency field, which is introduced creatively to improve efficiency. Furthermore, the learning algorithm is adopted to learn the long-term optimal state-action sequence in the safety field. Finally, the simulations are conducted in Prescan platform to validate the feasibility of the improved safety field in complex scenarios. The results show that the proposed decision algorithm can always drive autonomous vehicle to the state with a long-term optimal payoff and can improve the overall performance compared to the existing pure safety field and the interaction-aware method.


Author(s):  
Jay Rodge ◽  
Swati Jaiswal

Deep learning and Artificial intelligence (AI) have been trending these days due to the capability and state-of-the-art results that they provide. They have replaced some highly skilled professionals with neural network-powered AI, also known as deep learning algorithms. Deep learning majorly works on neural networks. This chapter discusses about the working of a neuron, which is a unit component of neural network. There are numerous techniques that can be incorporated while designing a neural network, such as activation functions, training, etc. to improve its features, which will be explained in detail. It has some challenges such as overfitting, which are difficult to neglect but can be overcome using proper techniques and steps that have been discussed. The chapter will help the academician, researchers, and practitioners to further investigate the associated area of deep learning and its applications in the autonomous vehicle industry.


2019 ◽  
Vol 489 (3) ◽  
pp. 3582-3590 ◽  
Author(s):  
Dmitry A Duev ◽  
Ashish Mahabal ◽  
Frank J Masci ◽  
Matthew J Graham ◽  
Ben Rusholme ◽  
...  

ABSTRACT Efficient automated detection of flux-transient, re-occurring flux-variable, and moving objects is increasingly important for large-scale astronomical surveys. We present braai, a convolutional-neural-network, deep-learning real/bogus classifier designed to separate genuine astrophysical events and objects from false positive, or bogus, detections in the data of the Zwicky Transient Facility (ZTF), a new robotic time-domain survey currently in operation at the Palomar Observatory in California, USA. Braai demonstrates a state-of-the-art performance as quantified by its low false negative and false positive rates. We describe the open-source software tools used internally at Caltech to archive and access ZTF’s alerts and light curves (kowalski ), and to label the data (zwickyverse). We also report the initial results of the classifier deployment on the Edge Tensor Processing Units that show comparable performance in terms of accuracy, but in a much more (cost-) efficient manner, which has significant implications for current and future surveys.


Sign in / Sign up

Export Citation Format

Share Document