Sensor Fusion for Depth Estimation, including TOF and Thermal Sensors

This paper describes the computation of depth maps for a high-quality reference camera augmented by a set of satellite sensors. The satellite sensors include support cameras, a TOF (time-of-flight) sensor, and a thermal camera, all rigidly attached to the reference camera. There is extensive previous work on computing depth maps with stereo alone, and high-quality results have been achieved. However it has proved difficult to achieve good results for cases such as texture less areas, or similar fore- and background colors. We show that with our proposed sensor fusion we can achieve high quality results. The paper makes two contributions. The first is a method for combining TOF data with multi-camera data that includes reasoning about occlusions, to produce an improved depth estimate near depth discontinuities. The second contribution is to show the benefit of thermal sensing as a segmentation prior. Thermal cameras were formerly high-cost devices but are now available at the same cost as machine vision cameras. This work demonstrates their advantages, particularly for scenes including humans.