Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation

TL;DR

This paper demonstrates that estimated depth from monocular images can significantly enhance object detection and semantic segmentation accuracy by integrating depth features with RGB data.

Contribution

The authors develop a deep depth estimation model from monocular images and incorporate estimated depth features into detection and segmentation tasks, introducing a multi-task training scheme for semantic segmentation.

Findings

Estimated depth improves detection accuracy

Estimated depth enhances segmentation performance

Multi-task training benefits semantic segmentation

Abstract

Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have facilitated easy acquisition of such depth information, the vast majority of images used in vision tasks do not contain depth information. In this paper, we show that augmenting RGB images with estimated depth can also improve the accuracy of both object detection and semantic segmentation. Specifically, we first exploit the recent success of depth estimation from monocular images and learn a deep depth estimation model. Then we learn deep depth features from the estimated depth and combine with RGB features for object detection and semantic segmentation. Additionally, we propose an RGB-D semantic segmentation method which applies a multi-task training scheme: semantic label prediction and depth value regression. We test our methods on several datasets and demonstrate that incorporating information from estimated depth improves the performance of object detection and semantic segmentation remarkably.