J-MOD${}^2$: Joint Monocular Obstacle Detection and Depth Estimation

Abstract

In this work, we propose an end-to-end deep architecture that jointly learns to detect obstacles and estimate their depth for MAV flight applications. Most of the existing approaches either rely on Visual SLAM systems or on depth estimation models to build 3D maps and detect obstacles. However, for the task of avoiding obstacles this level of complexity is not required. Recent works have proposed multi task architectures to both perform scene understanding and depth estimation. We follow their track and propose a specific architecture to jointly estimate depth and obstacles, without the need to compute a global map, but maintaining compatibility with a global SLAM system if needed. The network architecture is devised to exploit the joint information of the obstacle detection task, that produces more reliable bounding boxes, with the depth estimation one, increasing the robustness of both to scenario changes. We call this architecture J-MOD${}^2$. We test the effectiveness of our approach with experiments on sequences with different appearance and focal lengths and compare it to SotA multi task methods that jointly perform semantic segmentation and depth estimation. In addition, we show the integration in a full system using a set of simulated navigation experiments where a MAV explores an unknown scenario and plans safe trajectories by using our detection model.

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fully Convolutional Networks for Semantic Segmentation
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
• Obstacle Avoidance through Deep Networks based Intermediate Perception

Cited by in corpus (9)

• A Survey on RGB-D Datasets
• Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving
• Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps
• Obstacle Avoidance Using a Monocular Camera
• Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications
• Towards Real-Time Monocular Depth Estimation for Robotics: A Survey
• Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimization
• Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression
• Boundary-induced and scene-aggregated network for monocular depth prediction