D-Flow: A Real Time Spatial Temporal Model for Target Area Segmentation

TL;DR

This paper introduces D-Flow, a novel real-time spatial-temporal neural network for target area segmentation in robotics and maritime applications, capable of operating efficiently within hardware constraints.

Contribution

The paper presents a new spatial-temporal network architecture designed for real-time target area segmentation under domain-specific constraints.

Findings

Outperforms existing real-time segmentation methods on RoboCup SPL dataset

Successfully generalizes to maritime dataset for ocean region segmentation

Operates efficiently within limited computational resources

Abstract

Semantic segmentation has attracted a large amount of attention in recent years. In robotics, segmentation can be used to identify a region of interest, or \emph{target area}. For example, in the RoboCup Standard Platform League (SPL), segmentation separates the soccer field from the background and from players on the field. For satellite or vehicle applications, it is often necessary to find certain regions such as roads, bodies of water or kinds of terrain. In this paper, we propose a novel approach to real-time target area segmentation based on a newly designed spatial temporal network. The method operates under domain constraints defined by both the robot's hardware and its operating environment . The proposed network is able to run in real-time, working within the constraints of limited run time and computing power. This work is compared against other real time segmentation methods on a dataset generated by a Nao V6 humanoid robot simulating the RoboCup SPL competition. In this case, the target area is defined as the artificial grass field. The method is also tested on a maritime dataset collected by a moving vessel, where the aim is to separate the ocean region from the rest of the image. This dataset demonstrates that the proposed model can generalise to a variety of vision problems.