Semantic Scene Segmentation for Robotics Applications

08/25/2021
by   Maria Tzelepi, et al.
0

Semantic scene segmentation plays a critical role in a wide range of robotics applications, e.g., autonomous navigation. These applications are accompanied by specific computational restrictions, e.g., operation on low-power GPUs, at sufficient speed, and also for high-resolution input. Existing state-of-the-art segmentation models provide evaluation results under different setups and mainly considering high-power GPUs. In this paper, we investigate the behavior of the most successful semantic scene segmentation models, in terms of deployment (inference) speed, under various setups (GPUs, input sizes, etc.) in the context of robotics applications. The target of this work is to provide a comparative study of current state-of-the-art segmentation models so as to select the most compliant with the robotics applications requirements.

READ FULL TEXT
research
10/01/2019

Real-Time Semantic Stereo Matching

Scene understanding is paramount in robotics, self-navigation, augmented...
research
11/02/2020

CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation

With the increasing demand of autonomous machines, pixel-wise semantic s...
research
09/23/2021

Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

Outdoor scene completion is a challenging issue in 3D scene understandin...
research
07/16/2021

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference

Semantic segmentation for scene understanding is nowadays widely demande...
research
02/25/2018

Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs

The ability to interpret a scene is an important capability for a robot ...
research
08/01/2018

Energy-based Tuning of Convolutional Neural Networks on Multi-GPUs

Deep Learning (DL) applications are gaining momentum in the realm of Art...
research
08/24/2020

LMSCNet: Lightweight Multiscale 3D Semantic Completion

We introduce a new approach for multiscale 3D semantic scene completion ...

Please sign up or login with your details

Forgot password? Click here to reset