Object-aware bundle adjustment for correcting monocular scale drift

Frost, Duncan; Kähler, Olaf; Murray, David

doi:10.1109/icra.2016.7487680

Cited by 50 publications

(39 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic SLAM With the development of 2D object detection, several joint SLAM with semantic understanding works have sprung up, which we discuss in three categories. The first is semantic-aided localization: [7,8] focus on correcting the global scale of monocular Visual Odometry (VO) by incorporating object metric size of only one dimension into the estimation framework. Indoor with small objects and outdoor experiments are conducted respectively in these two works.…”

Section: Related Workmentioning

confidence: 99%

Stereo Vision-Based Semantic 3D Object and Ego-Motion Tracking for Autonomous Driving

Qin

Shen

2018

Lecture Notes in Computer Science

158

104

View full text Add to dashboard Cite

We propose a stereo vision-based approach for tracking the camera ego-motion and 3D semantic objects in dynamic autonomous driving scenarios. Instead of directly regressing the 3D bounding box using end-to-end approaches, we propose to use the easy-to-labeled 2D detection and discrete viewpoint classification together with a light-weight semantic inference method to obtain rough 3D object measurements. Based on the object-aware-aided camera pose tracking which is robust in dynamic environments, in combination with our novel dynamic object bundle adjustment (BA) approach to fuse temporal sparse feature correspondences and the semantic 3D measurement model, we obtain 3D object pose, velocity and anchored dynamic point cloud estimation with instance accuracy and temporal consistency. The performance of our proposed method is demonstrated in diverse scenarios. Both the ego-motion estimation and object localization are compared with the state-of-of-theart solutions.

show abstract

Section: Related Workmentioning

confidence: 99%

Stereo Vision-Based Semantic 3D Object and Ego-Motion Tracking for Autonomous Driving

Qin

Shen

2018

Lecture Notes in Computer Science

158

104

View full text Add to dashboard Cite

show abstract

“…Another type of scale correction strategy is to detect the scale drift frame by frame by using the prior scene knowledge and trigger the scale correction procedure timely if the scale drift is serious. In [38], [57], [39] the prior size of the object are used for reducing the scale drift when they are detected in the scene. Obviously, these methods cannot work if no object has been detected.…”

Section: Scale Correction For Vomentioning

confidence: 99%

Ground-Plane-Based Absolute Scale Estimation for Monocular Visual Odometry

Zhou

Dai

2020

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Recovering absolute metric scale from a monocular camera is a challenging but highly desirable problem for monocular camera-based systems. By using different kinds of cues, various approaches have been proposed for scale estimation, such as camera height, object size etc. In this paper, firstly, we summarize different kinds of scale estimation approaches. Then, we propose a robust divide and conquer absolute scale estimation method based on the ground plane and camera height by analyzing the advantages and disadvantages of different approaches. By using the estimated scale, an effective scale correction strategy has been proposed to reduce the scale drift during the Monocular Visual Odometry (VO) estimation process. Finally, the effectiveness and robustness of the proposed method have been verified on both public and self-collected image sequences.

show abstract

“…In order to mitigate those issues, different flexible schemes using object detection have been introduced. For example, [9] introduces so-called object bundle adjustment, which optimises 3D landmark positions associated with objects of known size. The work in [30] fuses single detections from a generic object detector within a Bayesian framework.…”

Section: Related Workmentioning

confidence: 99%

Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data

Rukhovich¹

2020

PRIN

View full text Add to dashboard Cite

This paper addresses the problem of scale estimation in monocular SLAM by estimating absolute distances between camera centers of consecutive image frames. These estimates would improve the overall performance of classical (not deep) SLAM systems and allow metric feature locations to be recovered from a single monocular camera. We propose several network architectures that lead to an improvement of scale estimation accuracy over the state of the art. In addition, we exploit a possibility to train the neural network only with synthetic data derived from a computer graphics simulator. Our key insight is that, using only synthetic training inputs, we can achieve similar scale estimation accuracy as that obtained from real data. This fact indicates that fully annotated simulated data is a viable alternative to existing deep-learning-based SLAM systems trained on real (unlabeled) data. Our experiments with unsupervised domain adaptation also show that the difference in visual appearance between simulated and real data does not affect scale estimation results. Our method operates with low-resolution images (0.03 MP), which makes it practical for real-time SLAM applications with a monocular camera.

show abstract

Object-aware bundle adjustment for correcting monocular scale drift

Cited by 50 publications

References 42 publications

Stereo Vision-Based Semantic 3D Object and Ego-Motion Tracking for Autonomous Driving

Stereo Vision-Based Semantic 3D Object and Ego-Motion Tracking for Autonomous Driving

Ground-Plane-Based Absolute Scale Estimation for Monocular Visual Odometry

Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data

Contact Info

Product

Resources

About