Object Detection Learning Techniques for Autonomous Vehicle Applications

Masmoudi, Mehdi; Ghazzai, Hakim; Frikha, Mounir; Massoud, Yehia

doi:10.1109/icves.2019.8906437

Cited by 48 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2D object detection, the use of single-stage and double-stage detectors is very popular due to their high accuracy and speed, including models like YOLO, SSD, RetinaNet, R-CNN, and R-FCN. [19][20][21][22][23][24][25][26][27][28]. e double-stage detectors were able to perform better in object detection; however, the single-stage detector performed faster.…”

Section: Object Detectionmentioning

confidence: 99%

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions

Walambe

Marathe

Kotecha

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The computer vision systems driving autonomous vehicles are judged by their ability to detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing this ability of a self-driving car to distinguish between the elements of its environment under adverse conditions is an important challenge in computer vision. For example, poor weather conditions like fog and rain lead to image corruption which can cause a drastic drop in object detection (OD) performance. The primary navigation of autonomous vehicles depends on the effectiveness of the image processing techniques applied to the data collected from various visual sensors. Therefore, it is essential to develop the capability to detect objects like vehicles and pedestrians under challenging conditions such as like unpleasant weather. Ensembling multiple baseline deep learning models under different voting strategies for object detection and utilizing data augmentation to boost the models’ performance is proposed to solve this problem. The data augmentation technique is particularly useful and works with limited training data for OD applications. Furthermore, using the baseline models significantly speeds up the OD process as compared to the custom models due to transfer learning. Therefore, the ensembling approach can be highly effective in resource-constrained devices deployed for autonomous vehicles in uncertain weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and were able to identify objects from the images captured in the adverse foggy and rainy weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and reached 32.75% mean average precision (mAP) and 52.56% average precision (AP) in detecting cars in the adverse fog and rain weather conditions present in the dataset. The effectiveness of multiple voting strategies for bounding box predictions on the dataset is also demonstrated. These strategies help increase the explainability of object detection in autonomous systems and improve the performance of the ensemble techniques over the baseline models.

show abstract

Section: Object Detectionmentioning

confidence: 99%

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions

Walambe

Marathe

Kotecha

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In this section, we overview the main object detection learning techniques using image processing for AV applications. The purpose is to briefly investigate the performance of machine learning models such as the Support Vector Machine (SVM) model as well as deep learning algorithms like the You Only Look Once (YOLO) algorithm and the Single Shot Detector (SSD) in terms of accuracy and the timing-process [27]. SVM is a supervised learning model that analyzes data for both regression and classification.…”

Section: A Object Detection Learning Techniquesmentioning

confidence: 99%

A Reinforcement Learning Framework for Video Frame-Based Autonomous Car-Following

Masmoudi

Friji

Ghazzai

et al. 2021

IEEE Open J. Intell. Transp. Syst.

Self Cite

View full text Add to dashboard Cite

Car-following theory has received considerable attention as a core component of Intelligent Transportation Systems. However, its application to the emerging autonomous vehicles (AVs) remains an unexplored research area. AVs are designed to provide convenient and safe driving by avoiding accidents caused by human errors. They require advanced levels of recognition of other drivers' driving-style. With car-following models, AVs can use their built-in technology to understand the environment surrounding them and make real-time decisions to follow other vehicles. In this paper, we design an end-to-end carfollowing framework for AVs using automated object detection and navigation decision modules. The objective is to allow an AV to follow another vehicle based on Red Green Blue Depth (RGB-D) frames. We propose to employ a joint solution involving the You Look Once version 3 (YOLOv3) object detector to identify the leader vehicle and other obstacles and a reinforcement learning (RL) algorithm to navigate the self-driving vehicle. Two RL algorithms, namely Q-learning and Deep Q-learning have been investigated. Simulation results show the convergence of the developed models and investigate their efficiency in following the leader. It is shown that, with video frames only, promising results are achieved and that AVs can adopt a reasonable car-following behavior.

show abstract

“…VANETs can be realized in two gorgeous ways: ordinary IP in particular primarily based definitely networking and Information-Centric Networking [ICN] [48]. For vehicular applications, a lot of archives have to be disbursed amongst sellers with intermittent and in lots a great deal much less than nice connections whilst preserving excessive mobility [50].…”

Section: Pedestrian Detectionmentioning

confidence: 99%

“…direct supervised networks can be expert offline with human the use of data, and as soon as the teaching is done, the machine is no longer envisioned to fail in the course of operation. There is no operational related ADS in use yet, however, some researchers trust about this rising science will be the future of the use of automation [48]- [50]. With the use of Vehicular Ad hoc Network [VAN ETs], the handy operations of computerized the use of can be disbursed amongst agents.…”

Section: Pedestrian Detectionmentioning

confidence: 99%

SLAM – DATMO Method for an Autonomous Vehicles

Vasudevan

2021

Preprint

View full text Add to dashboard Cite

Automated automobiles navigate US highways and many different countries round the world. Current question is about AVs revolve round whether or not such applied sciences have to or need to be implemented; they are already with us. Rather, such questions are more and more established on how such utilized sciences will have an impact on evolving transportation systems. More importantly, how will mobility itself exchange as these impartial operational automobiles first share and then dominate our roadways? How will the public be saved apprised of their evolving capacities? We seem right here to tackle these problems and to furnish some recommendations for the issues that are presently emerging.

show abstract

Object Detection Learning Techniques for Autonomous Vehicle Applications

Cited by 48 publications

References 7 publications

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions

A Reinforcement Learning Framework for Video Frame-Based Autonomous Car-Following

SLAM – DATMO Method for an Autonomous Vehicles

Contact Info

Product

Resources

About