Improving the 3D Perception of the Pepper Robot Using Depth Prediction from Monocular Frames

2018 ◽  
pp. 132-146 ◽  
Author(s):  
Zuria Bauer ◽  
Felix Escalona ◽  
Edmanuel Cruz ◽  
Miguel Cazorla ◽  
Francisco Gomez-Donoso
Keyword(s):  
3D Perception ◽  
Depth Prediction

scholarly journals Task-Aware Monocular Depth Estimation for 3D Object Detection

2020 ◽  
Vol 34 (07) ◽  
pp. 12257-12264 ◽  
Author(s):  
Xinlong Wang ◽  
Wei Yin ◽  
Tao Kong ◽  
Yuning Jiang ◽  
Lei Li ◽  
...  
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Depth Estimation ◽  
3D Perception ◽  
Research Attention ◽  
3D Object ◽  
Depth Prediction ◽  
Monocular Depth ◽  
Almost All ◽  
3D Object Detection

Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions (“things and stuff”) in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyze the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground and background depth using separate optimization objectives and decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.

scholarly journals Research on Improving the Durability of Bridge Pavement Using a High-Modulus Asphalt Mixture

Materials ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 1449
Author(s):  
Wenfeng Wang ◽  
Shaochan Duan ◽  
Haoran Zhu
Keyword(s):  
Construction Industry ◽  
Mechanical Response ◽  
Design Method ◽  
Asphalt Mixture ◽  
Field Tests ◽  
Bottom Layer ◽  
High Modulus ◽  
Practical Applications ◽  
Depth Prediction ◽  
Pavement Structure

In order to improve the durability of the asphalt pavement on a cement concrete bridge, this study investigated the effect of the modulus of the asphalt mixture at the bottom layer on the mechanical response of bridge pavement, along with a type of emerging bridge pavement structure. In addition, the design method and pavement performance of a high-modulus asphalt mixture were investigated using laboratory and field tests, and the life expectancy of the deck pavement structure was predicted based on the rutting deformation. The results showed that the application of a high-modulus asphalt mixture as the bottom asphalt layer decreased the stress level of the pavement structure. The new high-modulus asphalt mixture displayed excellent comprehensive performance, i.e., the dynamic stability reached 9632 times/mm and the fatigue life reached 1.65 million cycles. Based on the rutting depth prediction, using high-modulus mixtures for the bridge pavement prolonged the service life from the original 5 years to 10 years, which significantly enhanced the durability of the pavement structure. These research results could be of potential interest for practical applications in the construction industry.

Sign in / Sign up

Export Citation Format

Share Document