Self-supervised monocular depth estimation with direct methods

Wang, Haixia; Sun, Yehao; Wu, Q. M. Jonathan; Lu, Xiao; Wang, Xiuling; Zhang, Zhiguo

doi:10.1016/j.neucom.2020.10.025

Cited by 13 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, learning strategies utilize relatively larger and highly varied datasets of images. In "Self-supervised monocular depth estimation with direct methods" [120], the use of ground-truth or binocular stereo depth is replaced with unlabeled data of monocular video sequences. No assumptions about scene geometry or pre-trained information are required.…”

Section: Self-supervised Monocular Modelsmentioning

confidence: 99%

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Lahiri,

Ren,

Lin

2024

Vehicles

View full text Add to dashboard Cite

A lot of research has been conducted in recent years on stereo depth estimation techniques, taking the traditional approach to a new level such that it is in an appreciably good form for competing in the depth estimation market with other methods, despite its few demerits. Sufficient progress in accuracy and depth computation speed has manifested during the period. Over the years, stereo depth estimation has been provided with various training modes, such as supervised, self-supervised, and unsupervised, before deploying it for real-time performance. These modes are to be used depending on the application and/or the availability of datasets for training. Deep learning, on the other hand, has provided the stereo depth estimation methods with a new life to breathe in the form of enhanced accuracy and quality of images, attempting to successfully reduce the residual errors in stages in some of the methods. Furthermore, depth estimation from a single RGB image has been intricate since it is an ill-posed problem with a lack of geometric constraints and ambiguities. However, this monocular depth estimation has gained popularity in recent years due to the development in the field, with appreciable improvements in the accuracy of depth maps and optimization of computational time. The help is mostly due to the usage of CNNs (Convolutional Neural Networks) and other deep learning methods, which help augment the feature-extraction phenomenon for the process and enhance the quality of depth maps/accuracy of MDE (monocular depth estimation). Monocular depth estimation has seen improvements in many algorithms that can be deployed to give depth maps with better clarity and details around the edges and fine boundaries, which thus helps in delineating between thin structures. This paper reviews various recent deep learning-based stereo and monocular depth prediction techniques emphasizing the successes achieved so far, the challenges acquainted with them, and those that can be expected shortly.

show abstract

Section: Self-supervised Monocular Modelsmentioning

confidence: 99%

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Lahiri,

Ren,

Lin

2024

Vehicles

View full text Add to dashboard Cite

show abstract

“…Then, the angle α between the camera coordinate system and the world coordinate system can be obtained by using the two vectors, as shown in Formula (17).…”

Section: Visual Localization Processmentioning

confidence: 99%

“…Visual guidance is typically based on monocular vision models or multi-vision models for the positioning of the target, and on using the obtained position and posture of the target to guide its movement [15]. Multi-vision requires multiple cameras for shooting, resulting in higher costs, and also requires addressing the feature matching issue from different cameras, which leads to complex operations [16,17]. In contrast, monocular vision only requires a single camera, enabling implementation through the pinhole imaging principle, resulting in lower costs and convenient operation [18,19].…”

Section: Introductionmentioning

confidence: 99%

Monocular Vision Guidance for Unmanned Surface Vehicle Recovery

Li,

Xi,

Shi

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The positioning error of the GPS method at close distances is relatively large, rendering it incapable of accurately guiding unmanned surface vehicles (USVs) back to the mother ship. Therefore, this study proposes a near-distance recovery method for USVs based on monocular vision. By deploying a monocular camera on the USV to identify artificial markers on the mother ship and subsequently leveraging the geometric relationships among these markers, precise distance and angle information can be extracted. This enables effective guidance for the USVs to return to the mother ship. The experimental results validate the effectiveness of this approach, with positioning distance errors of less than 40 mm within a 10 m range and positioning angle errors of less than 5 degrees within a range of ±60 degrees.

show abstract

“…Research has shown that the pixels of the moving DC objects that are visible in the target frame but not visible in the adjacent frames ultimately affect pose prediction. Inspired by [48], we not only combine the dynamic mask with per-pixel minimum reprojection loss but also employ the dynamic semantic masking to the DDVO method to improve the accuracy of pose prediction.…”

Section: Joint Learningmentioning

confidence: 99%

Semantically guided self‐supervised monocular depth estimation

Sun

Wang

et al. 2022

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Depth information plays an important role in the vision‐related activities of robots and autonomous vehicles. An effective method to obtain 3D scene information is self‐supervised monocular depth estimation, which utilizes large and diverse monocular video datasets during the training process without the need for ground‐truth data. A novel multi‐task learning strategy that uses semantic information to guide the monocular depth estimation method while maintaining self‐supervision is proposed. An improved differential direct visual odometer (DDVO) combined with Pose‐Net is applied for achieving better pose prediction. Minimum reprojection loss with auto‐masking and semantic masking is used to remove the effects of low‐texture areas and moving dynamic‐class objects within scenes. Concurrently, the semantic masking is introduced into the DDVO pose predictor to filter moving objects and reduce the matching error between monocular sequence frames. In addition, PackNet is employed as the backbone of multi‐task learning to further improve the accuracy of deep prediction. The proposed method produces state‐of‐the‐art results for monocular depth estimation on the KITTI Eigen split benchmark, even outperforming supervised methods that have been trained using ground‐truth depth.

show abstract

Self-supervised monocular depth estimation with direct methods

Cited by 13 publications

References 25 publications

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Monocular Vision Guidance for Unmanned Surface Vehicle Recovery

Semantically guided self‐supervised monocular depth estimation

Contact Info

Product

Resources

About