High Accuracy Monocular SFM and Scale Correction for Autonomous Driving

Song, Shiyu; Chandraker, Manmohan; Guest, Clark C.

doi:10.1109/tpami.2015.2469274

Cited by 76 publications

(53 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) KITTI odometry benchmark: Most existing monocular SLAMs use a constant ground plane height assumption on the benchmark to reduce monocular scale drift [49,50]. Recently, there are also some object based scale recovery approaches [21,22].…”

Section: Kitti Datasetmentioning

confidence: 99%

CubeSLAM: Monocular 3-D Object SLAM

2019

View full text Add to dashboard Cite

We present a method for single image 3D cuboid object detection and multi-view object SLAM in both static and dynamic environments, and demonstrate that the two parts can improve each other. Firstly for single image object detection, we generate high-quality cuboid proposals from 2D bounding boxes and vanishing points sampling. The proposals are further scored and selected based on the alignment with image edges. Secondly, multi-view bundle adjustment with new object measurements is proposed to jointly optimize poses of cameras, objects and points. Objects can provide long-range geometric and scale constraints to improve camera pose estimation and reduce monocular drift. Instead of treating dynamic regions as outliers, we utilize object representation and motion model constraints to improve the camera pose estimation. The 3D detection experiments on SUN RGBD and KITTI show better accuracy and robustness over existing approaches. On the public TUM, KITTI odometry and our own collected datasets, our SLAM method achieves the stateof-the-art monocular camera pose estimation and at the same time, improves the 3D object detection accuracy.

show abstract

Section: Kitti Datasetmentioning

confidence: 99%

CubeSLAM: Monocular 3-D Object SLAM

2019

View full text Add to dashboard Cite

show abstract

“…(Clipp et al, 2008) present an approach to obtain the metric scale for a multi-camera system with non-overlapping fields-of-view. For a mono camera, (Song et al, 2016) present an approach to obtain the scale if the height of the camera above the ground plane is known. In a vehicle driving on an uneven road, there might be rotations around the pitch axis, causing height changes of the camera relative to the ground.…”

Section: Methods For Camera Localization and Mappingmentioning

confidence: 99%

Metric Scale Calculation for Visual Mapping Algorithms

Hanel

Mitschke

Boerner

et al. 2018

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Visual SLAM algorithms allow localizing the camera by mapping its environment by a point cloud based on visual cues. To obtain the camera locations in a metric coordinate system, the metric scale of the point cloud has to be known. This contribution describes a method to calculate the metric scale for a point cloud of an indoor environment, like a parking garage, by fusing multiple individual scale values. The individual scale values are calculated from structures and objects with a-priori known metric extension, which can be identified in the unscaled point cloud. Extensions of building structures, like the driving lane or the room height, are derived from density peaks in the point distribution. The extension of objects, like traffic signs with a known metric size, are derived using projections of their detections in images onto the point cloud. The method is tested with synthetic image sequences of a drive with a front-looking mono camera through a virtual 3D model of a parking garage. It has been shown, that each individual scale value improves either the robustness of the fused scale value or reduces its error. The error of the fused scale is comparable to other recent works.

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%

“…In summary, the sparse and dense optimization based methods give better results compared with Figure 10: Scale estimation evaluation on the KITTI VO benchmark training sequences. Blue, greed, and black lines represent the estimation results by using 3D points based method [27], sparse [50] and dense [39] optimization based methods and direct homography decomposition [51] based method.…”

Section: A Scale Estimation Evaluationmentioning

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

High Accuracy Monocular SFM and Scale Correction for Autonomous Driving

Cited by 76 publications

References 41 publications

CubeSLAM: Monocular 3-D Object SLAM

CubeSLAM: Monocular 3-D Object SLAM

Metric Scale Calculation for Visual Mapping Algorithms

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

Contact Info

Product

Resources

About