Filters








597 Hits in 9.0 sec

FAST AND LOW-POWER DEEP LEARNING SYSTEM ON EMBEDDED HARDWARE FOR SELF-DRIVING AUTONOMOUS BICYCLE

Yucheng Yang, Kiran George, Kenneth John Faller II, Pradeep Nair
2022 Zenodo  
Moreover, the proposed soft and hardware co-designed machine learning model is implemented on a development board to obtain greater energy savings and more precise data processing.  ...  To achieve this, we also propose a new implementation based on existing Xilinx software to minimize the development cost, which differs from typical FPGA transplanting technology.  ...  Kenneth John Faller II for serving on the advisory committee and providing valuable comments and suggestions to improve my research.  ... 
doi:10.5281/zenodo.6950722 fatcat:xpz3p7x6s5dszmcohy4zoetfhu

Accurate, Low-Latency Visual Perception for Autonomous Racing:Challenges, Mechanisms, and Practical Solutions [article]

Kieran Strobel, Sibo Zhu, Raphael Chang, Skanda Koppula
2020 arXiv   pre-print
The key components of DUT18D include YOLOv3-based object detection, pose estimation, and time synchronization on its dual stereovision/monovision camera setup.  ...  , a 4WD electric race car with podium finishes at all Formula Driverless competitions for which it raced.  ...  ACKNOWLEDGMENT We thank all the members, advisors, and generous sponsors of DUT/MIT Racing for making this project possible.  ... 
arXiv:2007.13971v1 fatcat:it7epamg75gq7a6drzrydmia4m

Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing [article]

Johannes Betz, Hongrui Zheng, Alexander Liniger, Ugo Rosolia, Phillip Karle, Madhur Behl, Venkat Krovi, Rahul Mangharam
2022 arXiv   pre-print
Researchers are developing software and hardware for high performance race vehicles which aim to operate autonomously on the edge of the vehicles limits: High speeds, high accelerations, low reaction times  ...  The rising popularity of self-driving cars has led to the emergence of a new research field in the recent years: Autonomous racing.  ...  In [45] a case study with different convolutional neural network (CNN) methods (Tiny-YOLO, Proteins) are done in comparison to a YOLO v2 setup [46] to display the best approach for cone detection in  ... 
arXiv:2202.07008v1 fatcat:hwhp43thevd2bighs7y7j7qnam

Composition and Application of Current Advanced Driving Assistance System: A Review [article]

Xinran Li, Kuo-Yi Lin, Min Meng, Xiuxian Li, Li Li, Yiguang Hong, Jie Chen
2021 arXiv   pre-print
This paper makes a general introduction about ADAS by analyzing its hardware support and computation algorithms.  ...  The low resolution leads to the inability of small object detection and precise target feature extraction.  ...  Sensor fusion detection method of [81] is based on CNN and image upsampling theory.  ... 
arXiv:2105.12348v3 fatcat:ymblcizg65e7hhmch5c5mly22q

Comparing MobileNet-SSD and YOLO v3 Learning Architecture for Real-time Driver's Fatigue Detection

Nursuriati Jamil, Mohammad Haziq Mohd Fadhil, Raseeda Hamzah, Muhammad Izzad Ramli
2021 International Journal of Academic Research in Business and Social Sciences  
Even though most CNN-based architectures achieved considerably high accuracy, they are still slow even with high-end hardware.  ...  In our work, we define fatigue based on the rate of eye blinking. We developed a proof of concept systems, and evaluate the systems based on accuracy and detection speed.  ...  To fulfill the aim of this study, a literature search on previous work of object detection using CNN-based models was conducted.  ... 
doi:10.6007/ijarbss/v11-i12/11984 fatcat:rnuuucgbcbcwnkpbr7icmgedoi

A survey of deep learning techniques for autonomous driving

Sorin Grigorescu, Bogdan Trasnea, Tiberiu Cocias, Gigel Macesanu
2019 Journal of Field Robotics  
The objective of this paper is to survey the current state-of-the-art on deep learning technologies used in autonomous driving.  ...  Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources and computational hardware.  ...  A comparison between the object detectors described above is given in Figure 4 , based on the Pascal VOC 2012 dataset and their measured mean Average Precision (mAP) with an Intersection over Union (IoU  ... 
doi:10.1002/rob.21918 fatcat:pjyk4lwjavf63jz4pmc3mnuqe4

Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing

Johannes Betz, Hongrui Zheng, Alexander Liniger, Ugo Rosolia, Phillip Karle, Madhur Behl, Venkat Krovi, Rahul Mangharam
2022 IEEE Open Journal of Intelligent Transportation Systems  
Researchers are developing software and hardware for high-performance race vehicles which aim to operate autonomously on the edge of the vehicle's limits: High speeds, high accelerations, low reaction  ...  The rising popularity of self-driving cars has led to the emergence of a new research field in recent years: Autonomous racing.  ...  Panagiotis Tsiotras (Georgia Institute of Technology) and Sertac Karaman (Massachusetts Institute of Technology) for their talks at 2021 IEEE ICRA 1st Workshop "Opportunities and Challenges with Autonomous Racing  ... 
doi:10.1109/ojits.2022.3181510 fatcat:2uu6aowqrrewfbkfrsrmqxpyei

A Survey of Computer Vision Methods for 2D Object Detection from Unmanned Aerial Vehicles

Dario Cazzato, Claudio Cimarelli, Jose Luis Sanchez-Lopez, Holger Voos, Marco Leo
2020 Journal of Imaging  
on RGB-based object detection.  ...  This survey presents recent advancements in 2D object detection for the case of UAVs, focusing on the differences, strategies, and trade-offs between the generic problem of object detection, and the adaptation  ...  An extensive analysis of UAV object detection basing on these sources of data is out of the scope of this work and it would require a separate study.  ... 
doi:10.3390/jimaging6080078 pmid:34460693 pmcid:PMC8321148 fatcat:ds4kpheadvg6xp2fambrp6nffq

Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing [article]

Izzeddin Teeti, Valentina Musat, Salman Khan, Alexander Rast, Fabio Cuzzolin, Andrew Bradley
2022 arXiv   pre-print
In autonomous racing, high speeds and small margins demand rapid and accurate detection systems.  ...  In order to improve detection in adverse weather, deep-learning-based models typically require extensive datasets captured in such conditions - the collection of which is a tedious, laborious, and costly  ...  CNNs are characterised by multiple feature extraction stages that can automatically learn representations from the data, thus, trained on the right dataset, CNN-based models can detect objects even when  ... 
arXiv:2201.03246v2 fatcat:4qtppnh2nrb5tnhnxmus4vzudq

AMZ Driverless: The Full Autonomous Racing System [article]

Juraj Kabzan, Miguel de la Iglesia Valls, Victor Reijgwart, Hubertus Franciscus Cornelis Hendrikx, Claas Ehmke, Manish Prajapat, Andreas Bühler, Nikhil Gosala, Mehak Gupta, Ramya Sivanesan, Ankit Dhall, Eugenio Chisari, Napat Karnchanachari, Sonja Brits (+7 others)
2019 arXiv   pre-print
Specifically, perception, estimation, and control are incorporated into one high-performance autonomous racecar.  ...  In order to autonomously race around a previously unknown track, the proposed solution combines state of the art techniques from different fields of robotics.  ...  racing applications 3 The paper is organized as follows; Section 1 presents related studies for autonomous racing.  ... 
arXiv:1905.05150v1 fatcat:jztfwaowyzftlgzrlwy3khidnu

A Review on IoT Deep Learning UAV Systems for Autonomous Obstacle Detection and Collision Avoidance

Paula Fraga-Lamas, Lucía Ramos, Víctor Mondéjar-Guerra, Tiago M. Fernández-Caramés
2019 Remote Sensing  
Moreover, the latest DL-UAV communication architectures are studied and their most common hardware is analyzed.  ...  This article reviews the most recent developments on DL Unmanned Aerial Systems (UASs) and provides a detailed explanation on the main DL techniques.  ...  [72] CNN Object detection. Outdoors [73] CNN The network computes feature extraction Outdoors for learning safe trajectories.  ... 
doi:10.3390/rs11182144 fatcat:54xs26xnvzf7rfa5b64tuzkz44

A Review of Recent Developments in Driver Drowsiness Detection Systems

Yaman Albadawi, Maen Takruri, Mohammed Awad
2022 Sensors  
The paper illustrates and reviews recent systems using different measures to track and detect drowsiness. Each system falls under one of four possible categories, based on the information used.  ...  In addition, an evaluation of these systems is presented, in terms of the final classification accuracy, sensitivity, and precision.  ...  Many car manufacturers, such as Toyota and Nissan, have recently installed or upgraded driver assistance devices in their products.  ... 
doi:10.3390/s22052069 pmid:35271215 pmcid:PMC8914892 fatcat:rsdcmzjornarzgcr73nyghhpvi

A review on modern defect detection models using DCNNs – Deep convolutional neural networks

Andrei-Alexandru Tulbure, Adrian-Alexandru Tulbure, Eva-Henrietta Dulf
2021 Journal of Advanced Research  
To offer a structured and analytical overview(stating both advantages and disadvantages) of the existing popular object detection models that can be re-purposed for defect detection: such as Region based  ...  This surge in accuracy and usage is also supported (besides swarms of researchers pouring into the race), by incremental breakthroughs in computing hardware: such as more powerful GPUs(Graphical processing  ...  Several case studies were presented and the result were promising. An apple defect detection method based on a shallow MLP-Neural Networks was presented in [25] .  ... 
doi:10.1016/j.jare.2021.03.015 pmid:35024194 pmcid:PMC8721352 fatcat:qw22r7bqazeypezitxex5f6eve

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications

Deisy Chaves, Eduardo Fidalgo, Enrique Alegre, Rocío Alaiz-Rodríguez, Francisco Jáñez-Martino, George Azzopardi
2020 Sensors  
In this work, we evaluate the speed–accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs.  ...  It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements.  ...  The funders had no role in the design of the study.  ... 
doi:10.3390/s20164491 pmid:32796644 pmcid:PMC7472057 fatcat:kiicnimrt5fylbv6pruws7hwz4

An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots [article]

Marcos V. Conde
2021 arXiv   pre-print
Autonomous robots are currently one of the most popular Artificial Intelligence problems, having experienced significant advances in the last decade, from Self-driving cars and humanoids to delivery robots  ...  We review the state-of-the-art of fundamental problems and demonstrate that many methods employed at small-scale are similar to the ones employed in real Self-driving cars from companies like Tesla or  ...  Study possible solutions to COVID-19 situations in Industry, example use cases: detect and count persons in closed areas like a factory plant, and detect if persons wear facemasks.  ... 
arXiv:2112.05534v2 fatcat:3drhsxelvvdwvpsq5rvfpnukam
« Previous Showing results 1 — 15 out of 597 results