A Single-Stream Segmentation and Depth Prediction CNN for Autonomous Driving

Aladem, Mohamed; Rawashdeh, Samir A.

doi:10.1109/mis.2020.2993266

Cited by 35 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e results show that the proposed model has better generalization and convergence speed than the original AE network. [79], which has been widely used in computer vision [80,81], speech recognition [82], and other fields [83]. e typical structure of CNN is shown in Figure 13.…”

Section: Output Layermentioning

confidence: 99%

Application of Rotating Machinery Fault Diagnosis Based on Deep Learning

Cui¹,

Meng²,

Wang³

et al. 2021

Shock and Vibration

View full text Add to dashboard Cite

With the continuous progress of modern industry, rotating machinery is gradually developing toward complexity and intelligence. The fault diagnosis technology of rotating machinery is one of the key means to ensure the normal operation of equipment and safe production, which has very important significance. Deep learning is a useful tool for analyzing and processing big data, which has been widely used in various fields. After a brief review of early fault diagnosis methods, this paper focuses on the method models that are widely used in deep learning: deep belief networks (DBN), autoencoders (AE), convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), and transfer learning methods are summarized from the two aspects of principle and application in the field of fault diagnosis of rotating machinery. Then, the commonly used evaluation indicators used to evaluate the performance of rotating machinery fault diagnosis methods are summarized. Finally, according to the current research status in the field of rotating machinery fault diagnosis, the current problems and possible future development and research trends are discussed.

show abstract

Section: Output Layermentioning

confidence: 99%

Application of Rotating Machinery Fault Diagnosis Based on Deep Learning

Cui¹,

Meng²,

Wang³

et al. 2021

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…The driverless vision understanding is realised based on 3D [15]. Aladem and Rawashdeh [16] have used the single‐stream encoding and decoding structure to realise the multi‐task prediction. Atapour‐Abarghouei and Breckon [17] further studied the depth estimation after getting rid of the shackles of 3D.…”

Section: Related Workmentioning

confidence: 99%

Neural network‐based semantic segmentation model for robot perception of driverless vision

Duan

Zhu

2020

IET cyber-systems robotics

View full text Add to dashboard Cite

“…High-quality depth maps are required in a wide variety of tasks in computer vision and graphics, such as RGB-D scene reconstruction [ 1 , 2 ], augmented reality [ 3 , 4 , 5 ] and autonomous driving [ 6 , 7 , 8 ]. Compared to standard RGB-sensors, depth sensors often produce noisy images, which makes depth-reconstruction tasks especially challenging, since every task also has to account for the different task-specific depth uncertainties or deficiencies.…”

Section: Introductionmentioning

confidence: 99%

A Generic Framework for Depth Reconstruction Enhancement

Sommerhoff

Kolb

2022

J. Imaging

View full text Add to dashboard Cite

We propose a generic depth-refinement scheme based on GeoNet, a recent deep-learning approach for predicting depth and normals from a single color image, and extend it to be applied to any depth reconstruction task such as super resolution, denoising and deblurring, as long as the task includes a depth output. Our approach utilizes a tight coupling of the inherent geometric relationship between depth and normal maps to guide a neural network. In contrast to GeoNet, we do not utilize the original input information to the backbone reconstruction task, which leads to a generic application of our network structure. Our approach first learns a high-quality normal map from the depth image generated by the backbone method and then uses this normal map to refine the initial depth image jointly with the learned normal map. This is motivated by the fact that it is hard for neural networks to learn direct mapping between depth and normal maps without explicit geometric constraints. We show the efficiency of our method on the exemplary inverse depth-image reconstruction tasks of denoising, super resolution and removal of motion blur.

show abstract

A Single-Stream Segmentation and Depth Prediction CNN for Autonomous Driving

Cited by 35 publications

References 13 publications

Application of Rotating Machinery Fault Diagnosis Based on Deep Learning

Application of Rotating Machinery Fault Diagnosis Based on Deep Learning

Neural network‐based semantic segmentation model for robot perception of driverless vision

A Generic Framework for Depth Reconstruction Enhancement

Contact Info

Product

Resources

About