Influence of AVC and HEVC compression on detection of vehicles through Faster R-CNN
PH Chan, A Huggett, G Souvalioti… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Situational awareness based on the data collected by the vehicle perception sensors (ie
LiDAR, RADAR, camera and ultrasonic sensors) is key for achieving assisted and …
LiDAR, RADAR, camera and ultrasonic sensors) is key for achieving assisted and …
[PDF][PDF] The data conundrum: compression of automotive imaging data and deep neural network based perception
PH Chan, G Souvalioti, A Huggett… - London Imaging …, 2021 - library.imaging.org
Video compression in automated vehicles and advanced driving assistance systems is of
utmost importance to deal with the challenge of transmitting and processing the vast amount …
utmost importance to deal with the challenge of transmitting and processing the vast amount …
Compression of vehicle trajectories with a variational autoencoder
The perception and prediction of the surrounding vehicles' trajectories play a significant role
in designing safe and optimal control strategies for connected and automated vehicles. The …
in designing safe and optimal control strategies for connected and automated vehicles. The …
A survey on compressed sensing in vehicular infotainment systems
Vehicular infotainment systems have attracted great interests from both academia and
industry. A vehicular infotainment system includes two parts: 1) the information part and 2) …
industry. A vehicular infotainment system includes two parts: 1) the information part and 2) …
Robust deep neural object detection and segmentation for automotive driving scenario with compressed image data
K Fischer, C Blum, C Herglotz… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Deep neural object detection or segmentation networks are commonly trained with pristine,
uncompressed data. However, in practical applications the input images are usually …
uncompressed data. However, in practical applications the input images are usually …
Robustness in compressed neural networks for object detection
S Cygert, A Czyżewski - 2021 International Joint Conference …, 2021 - ieeexplore.ieee.org
Model compression techniques allow to significantly reduce the computational cost
associated with data processing by deep neural networks with only a minor decrease in …
associated with data processing by deep neural networks with only a minor decrease in …
Leveraging the edge and cloud for V2X-based real-time object detection in autonomous driving
F Hawlader, F Robinet, R Frank - Computer Communications, 2024 - Elsevier
Environmental perception is a key element of autonomous driving because the information
received from the perception module influences core driving decisions. An outstanding …
received from the perception module influences core driving decisions. An outstanding …
Design and implementation of the vehicular camera system using deep neural network compression
B Kim, Y Jeon, H Park, D Han, Y Baek - Proceedings of the 1st …, 2017 - dl.acm.org
In recent years, there is a growing interest in advanced driver assistance systems, which can
reduce the risk of accidents on various roads. Many vehicular technologies use camera …
reduce the risk of accidents on various roads. Many vehicular technologies use camera …
Real-time and deep learning based vehicle detection and classification using pixel-wise code exposure measurements
C Kwan, D Gribben, B Chou, B Budavari, J Larkin… - Electronics, 2020 - mdpi.com
One key advantage of compressive sensing is that only a small amount of the raw video data
is transmitted or saved. This is extremely important in bandwidth constrained applications …
is transmitted or saved. This is extremely important in bandwidth constrained applications …
Automatic CNN compression system for autonomous driving
D Murata, T Motoya, H Ito - 2019 18th IEEE International …, 2019 - ieeexplore.ieee.org
A system has been developed to realize autonomous driving (AD) with Convolutional Neural
Networks (CNNs). To apply CNNs to AD, the amount of calculations must be compressed …
Networks (CNNs). To apply CNNs to AD, the amount of calculations must be compressed …