An official website of the United States government
Integral imaging has proven useful for three-dimensional (3D) object visualization in adverse environmental conditions such as partial occlusion and low light. This paper considers the problem of 3D object tracking. Two-dimensional (2D) object tracking within a scene is an active research area. Several recent algorithms use object detection methods to obtain 2D bounding boxes around objects of interest in each frame. Then, one bounding box can be selected out of many for each object of interest using motion prediction algorithms. Many of these algorithms rely on images obtained using traditional 2D imaging systems. A growing literature demonstrates the advantage of using 3D integral imaging instead of traditional 2D imaging for object detection and visualization in adverse environmental conditions. Integral imaging’s depth sectioning ability has also proven beneficial for object detection and visualization. Integral imaging captures an object’s depth in addition to its 2D spatial position in each frame. A recent study uses integral imaging for the 3D reconstruction of the scene for object classification and utilizes the mutual information between the object’s bounding box in this 3D reconstructed scene and the 2D central perspective to achieve passive depth estimation. We build over this method by using Bayesian optimization to track the object’s depth in as few 3D reconstructions as possible. We study the performance of our approach on laboratory scenes with occluded objects moving in 3D and show that the proposed approach outperforms 2D object tracking. In our experimental setup, mutual information-based depth estimation with Bayesian optimization achieves depth tracking with as few as two 3D reconstructions per frame which corresponds to the theoretical minimum number of 3D reconstructions required for depth estimation. To the best of our knowledge, this is the first report on 3D object tracking using the proposed approach.
more »
« less
Multi-Modal Geometric Learning for Grasping and Manipulation
This work provides an architecture that incorporates depth and tactile information to create rich and accurate 3D models useful for robotic manipulation tasks. This is accomplished through the use of a 3D convolutional neural network (CNN). Offline, the network is provided with both depth and tactile information and trained to predict the object’s geometry, thus filling in regions of occlusion. At runtime, the network is provided a partial view of an object. Tactile information is acquired to augment the captured depth information. The network can then reason about the object’s geometry by utilizing both the collected tactile and depth information. We demonstrate that even small amounts of additional tactile information can be incredibly helpful in reasoning about object geometry. This is particularly true when information from depth alone fails to produce an accurate geometric prediction. Our method is benchmarked against and outperforms other visual-tactile approaches to general geometric reasoning. We also provide experimental results comparing grasping success with our method.
more »
« less
- Award ID(s):
- 1734557
- PAR ID:
- 10111003
- Date Published:
- Journal Name:
- 2019 International Conference on Robotics and Automation (ICRA)
- Page Range / eLocation ID:
- 7339 to 7345
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In this work, we propose a novel method to supervise 3D Gaussian Splatting (3DGS) scenes using optical tactile sensors. Optical tactile sensors have become widespread in their use in robotics for manipulation and object representation; however, raw optical tactile sensor data is unsuitable to directly supervise a 3DGS scene. Our representation leverages a Gaussian Process Implicit Surface to implicitly represent the object, combining many touches into a unified representation with uncertainty. We merge this model with a monocular depth estimation network, which is aligned in a two stage process, coarsely aligning with a depth camera and then finely adjusting to match our touch data. For every training image, our method produces a corresponding fused depth and uncertainty map. Utilizing this additional information, we propose a new loss function, variance weighted depth supervised loss, for training the 3DGS scene model. We leverage the DenseTact optical tactile sensor and RealSense RGB-D camera to show that combining touch and vision in this manner leads to quantitatively and qualitatively better results than vision or touch alone in a few-view scene syntheses on opaque as well as on reflective and transparent objects. Please see our project page at armlabstanford.github.io/touch-gsmore » « less
-
We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions, resulting in highly accurate predictions which agree on the underlying scene geometry. Unlike existing depth-prediction techniques, our method uses a volumetric 3D convolutional neural network (CNN) that operates in world space on all depth maps jointly. The network can therefore learn meaningful scene-level priors. Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps. Experimental results show our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics on the ScanNet dataset, as well as a selection of scenes from the TUM-RGBD and ICL-NUIM datasets. This shows that our method is both effective and generalizes to new settings.more » « less
-
An object’s interior material properties, while invisible to the human eye, determine motion observed on its surface. We propose an approach that esti- mates heterogeneous material properties of an object directly from a monoc- ular video of its surface vibrations. Specifically, we estimate Young’s modulus and density throughout a 3D object with known geometry. Knowledge of how these values change across the object is useful for characterizing defects and simulating how the object will interact with different environments. Traditional non-destructive testing approaches, which generally estimate homogenized material properties or the presence of defects, are expensive and use specialized instruments. We propose an approach that leverages monocular video to (1) measure an object’s sub-pixel motion and decompose this motion into image-space modes, and (2) directly infer spatially-varying Young’s modulus and density values from the observed image-space modes. On both simulated and real videos, we demonstrate that our approach is able to image material properties simply by analyzing surface motion. In particular, our method allows us to identify unseen defects on a 2D drum head from real, high-speed video.more » « less
-
We introduce Vysics, a vision-and-physics framework for a robot to build an expressive geometry and dynamics model of a single rigid body, using a seconds-long RGBD video and the robot’s proprioception. While the computer vision community has built powerful visual 3D perception algorithms, cluttered environments with heavy occlusions can limit the visibility of objects of interest. However, observed motion of partially occluded objects can imply physical interactions took place, such as contact with a robot or the environment. These inferred contacts can supplement the visible geometry with "physible geometry," which best explains the observed object motion through physics. Vysics uses a vision-based tracking and reconstruction method, BundleSDF, to estimate the trajectory and the visible geometry from an RGBD video, and an odometry-based model learning method, Physics Learning Library (PLL), to infer the "physible" geometry from the trajectory through implicit contact dynamics optimization. The visible and "physible" geometries jointly factor into optimizing a signed distance function (SDF) to represent the object shape. Vysics does not require pretraining, nor tactile or force sensors. Compared with vision-only methods, Vysics yields object models with higher geometric accuracy and better dynamics prediction in experiments where the object interacts with the robot and the environment under heavy occlusion.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICRA.2019.8794233
