Real-Time Tracking of Single and Multiple Objects from Depth-Colour Imagery Using 3D Signed Distance Functions

Ren, Carl Yuheng; Prisacariu, Victor Adrian; Kähler, Olaf; Reid, Ian; Murray, David

doi:10.1007/s11263-016-0978-2

Cited by 25 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3D Object Detection and Segmentation RGB-D images are widely used for 3D object detection and segmentation [20,21,22,23,24]. The geometric embedding method [1] enriches the raw depth channel by three additional features including height above ground, angle with gravity and horizontal disparity.…”

Section: D Object Detection and Segmentationmentioning

confidence: 99%

Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object

2018

TIIS

View full text Add to dashboard Cite

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

show abstract

Section: D Object Detection and Segmentationmentioning

confidence: 99%

Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object

2018

TIIS

View full text Add to dashboard Cite

show abstract

“…Depth data enables the following applications using its surface information. The objects can be detected and tracked by detecting specific surfaces from depth data [1][2][3]. Hand gestures can be recognized by tracking a human hand in depth data [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Efficient Depth Data Coding Method Based on Plane Modeling for Intra Prediction

2021

View full text Add to dashboard Cite

In this paper, we propose a depth data coding method by plane modeling. The plane modeling is a prediction method based on a plane estimation from depth pixels in a block. The plane modeling improves the intra-picture prediction for depth data comparing with intra modes of conventional coding standards. The plane modeling coefficients, which are the information about the estimated plane, are required to be provided during the depth data coding. The plane modeling coefficients are predicted from neighboring depth pixels. A prediction error of the plane modeling coefficients is calculated through the plane modeling for the selected pixels. If the prediction error is below a certain threshold, then the plane modeling coefficients are applied to the plane modeling for the block. From the simulation results, we verify that the proposed method achieves up to 6.76% bit rate saving in the same coding distortion condition compared to VVC test model.

show abstract

“…The pixels of depth video are converted to 3D coordinates by the depth values. Object detection [13][14][15] Appl. Sci.…”

Section: Introductionmentioning

confidence: 99%

Human Height Estimation by Color Deep Learning and Depth 3D Conversion

et al. 2020

View full text Add to dashboard Cite

In this study, an estimation method for human height is proposed using color and depth information. Color images are used for deep learning by mask R-CNN to detect a human body and a human head separately. If color images are not available for extracting the human body region due to low light environment, then the human body region is extracted by comparing between current frame in depth video and a pre-stored background depth image. The topmost point of the human head region is extracted as the top of the head and the bottommost point of the human body region as the bottom of the foot. The depth value of the head top-point is corrected to a pixel value that has high similarity to a neighboring pixel. The position of the body bottom-point is corrected by calculating a depth gradient between vertically adjacent pixels. Two head-top and foot-bottom points are converted into 3D real-world coordinates using depth information. Two real-world coordinates estimate human height by measuring a Euclidean distance. Estimation errors for human height are corrected as the average of accumulated heights. In experiment results, we achieve that the estimated errors of human height with a standing state are 0.7% and 2.2% when the human body region is extracted by mask R-CNN and the background depth image, respectively.

show abstract

Real-Time Tracking of Single and Multiple Objects from Depth-Colour Imagery Using 3D Signed Distance Functions

Cited by 25 publications

References 28 publications

Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object

Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object

Efficient Depth Data Coding Method Based on Plane Modeling for Intra Prediction

Human Height Estimation by Color Deep Learning and Depth 3D Conversion

Contact Info

Product

Resources

About