Deep Learning-Based Obstacle Detection and Depth Estimation

Hsieh, Yi-Yu; Lin, Wei‐Yu; Li, Donglin; Chuang, Jen-Hui

doi:10.1109/icip.2019.8803100

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DTN network infers surface normal from depth map via the least square solution and a residual module, while the NTD network refines the depth estimation from the estimated surface normal and initial depth map. Hesieh et al [108] propose a multi-task learning network by adding a depth estimation branch to YOLOv3 [111]. In the process of training, an L 1 distance depth estimation loss (…”

Section: A Depth Estimation With Supervised Learningmentioning

confidence: 99%

Towards Real-Time Monocular Depth Estimation for Robotics: A Survey

Dong¹,

Garratt²,

Anavatti³

et al. 2021

Preprint

View full text Add to dashboard Cite

As an essential component for many autonomous driving and robotic activities such as ego-motion estimation, obstacle avoidance and scene understanding, monocular depth estimation (MDE) has attracted great attention from the computer vision and robotics communities. Over the past decades, a large number of methods have been developed. To the best of our knowledge, however, there is not a comprehensive survey of MDE. This paper aims to bridge this gap by reviewing 197 relevant articles published between 1970 and 2021. In particular, we provide a comprehensive survey of MDE covering various methods, introduce the popular performance evaluation metrics and summarize publically available datasets. We also summarize available open-source implementations of some representative methods and compare their performances. Furthermore, we review the application of MDE in some important robotic tasks. Finally, we conclude this paper by presenting some promising directions for future research. This survey is expected to assist readers to navigate this research field.

show abstract

Section: A Depth Estimation With Supervised Learningmentioning

confidence: 99%

Towards Real-Time Monocular Depth Estimation for Robotics: A Survey

Dong¹,

Garratt²,

Anavatti³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A central problem with LECs in an autonomous system is that the performance is dependent on the training data. When the neural network receives out of distribution data that differs significantly from the distribution of the training data, the precision and recall drops dramatically [ 10 ]. As autonomous vehicles become increasingly complex, it is hard to fully test and validate such systems offline.…”

Section: Introductionmentioning

confidence: 99%

Fault-Adaptive Autonomy in Systems with Learning-Enabled Components

Stojcsics

Boursinos

Mahadevan

et al. 2021

Sensors

View full text Add to dashboard Cite

Autonomous Cyber-Physical Systems (CPS) must be robust against potential failure modes, including physical degradations and software issues, and are required to self-manage contingency actions for these failures. Physical degradations often have a significant impact on the vehicle dynamics causing irregular behavior that can jeopardize system safety and mission objectives. The paper presents a novel Behavior Tree-based autonomy architecture that includes a Fault Detection and Isolation Learning-Enabled Component (FDI LEC) with an Assurance Monitor (AM) designed based on Inductive Conformal Prediction (ICP) techniques. The architecture implements real-time contingency-management functions using fault detection, isolation and reconfiguration subsystems. To improve scalability and reduce the false-positive rate of the FDI LEC, the decision-making logic provides adjustable thresholds for the desired fault coverage and acceptable risk. The paper presents the system architecture with the integrated FDI LEC, as well as the data collection and training approach for the LEC and the AM. Lastly, we demonstrate the effectiveness of the proposed architecture using a simulated autonomous underwater vehicle (AUV) based on the BlueROV2 platform.

show abstract

Mobile robot monocular vision-based obstacle avoidance algorithm using a deep neural network

Rezaei

Darabi

2023

Evol. Intel.

View full text Add to dashboard Cite

Deep Learning-Based Obstacle Detection and Depth Estimation

Cited by 7 publications

References 21 publications

Towards Real-Time Monocular Depth Estimation for Robotics: A Survey

Towards Real-Time Monocular Depth Estimation for Robotics: A Survey

Fault-Adaptive Autonomy in Systems with Learning-Enabled Components

Mobile robot monocular vision-based obstacle avoidance algorithm using a deep neural network

Contact Info

Product

Resources

About