Learning Object Depth from Camera Motion and Video Object Segmentation
This work addresses the need for accurate depth estimation in 3D applications like robotics and autonomous vehicles, but it is incremental as it builds on existing video object segmentation methods.
The paper tackles the problem of estimating object depth from camera motion and video object segmentation by introducing a diverse dataset and a novel deep network that uses only segmentation masks and uncalibrated camera movement, demonstrating applications in robotics and autonomous driving.
Video object segmentation, i.e., the separation of a target object from background in video, has made significant progress on real and challenging videos in recent years. To leverage this progress in 3D applications, this paper addresses the problem of learning to estimate the depth of segmented objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by, first, introducing a diverse, extensible dataset and, second, designing a novel deep network that estimates the depth of objects using only segmentation masks and uncalibrated camera movement. Our data-generation framework creates artificial object segmentations that are scaled for changes in distance between the camera and object, and our network learns to estimate object depth even with segmentation errors. We demonstrate our approach across domains using a robot camera to locate objects from the YCB dataset and a vehicle camera to locate obstacles while driving.