Achieving RGB-D level Segmentation Performance from a Single ToF Camera
This addresses the cost and complexity of RGB-D cameras for semantic segmentation in applications like automotive systems, though it is incremental as it builds on existing multi-task learning methods.
The paper tackled the problem of achieving RGB-D level semantic segmentation accuracy using only a single Time-of-Flight (ToF) camera, and the result showed competitiveness against more costly RGB-D approaches on an in-car segmentation dataset.
Depth is a very important modality in computer vision, typically used as complementary information to RGB, provided by RGB-D cameras. In this work, we show that it is possible to obtain the same level of accuracy as RGB-D cameras on a semantic segmentation task using infrared (IR) and depth images from a single Time-of-Flight (ToF) camera. In order to fuse the IR and depth modalities of the ToF camera, we introduce a method utilizing depth-specific convolutions in a multi-task learning framework. In our evaluation on an in-car segmentation dataset, we demonstrate the competitiveness of our method against the more costly RGB-D approaches.