Semantic Scene Segmentation for Robotics Applications
This work provides a comparative study to help select segmentation models for robotics, but it is incremental as it focuses on benchmarking existing methods without introducing new techniques.
The paper investigates the deployment speed of state-of-the-art semantic segmentation models under various setups like GPUs and input sizes for robotics applications, aiming to identify the most compliant models, but does not report specific numerical results or improvements.
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.