High quality reconstruction of dynamic objects using 2D-3D camera fusion

Jiang, Cansen; Christie, Dennis Aprilla; Paudel, Danda Pani; Demonceaux, Cédric

doi:10.1109/icip.2017.8296674

Cited by 7 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thanks to the proposed 3D-SFC, the detected moving objects can be separated according to their specific motion subspace. The detected moving objects are then individually registered with texture mapping to produce photo-realistic 3D modelling [Jiang et al, 2017a]. For more experimental results, readers are recommended to view this video (https://youtu.be/LewA8Lhn5Xo).…”

Section: Static-map and Rigid Object Reconstructionmentioning

confidence: 99%

Moving Object Detection by 3D Flow Field Analysis

Jiang

Paudel

Fofi

et al. 2021

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

Section: Static-map and Rigid Object Reconstructionmentioning

confidence: 99%

Moving Object Detection by 3D Flow Field Analysis

Jiang

Paudel

Fofi

et al. 2021

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

“…Considering the mentioned drawbacks of supervised approaches, completing point cloud by tracking interests us most. [7], [5], [16] jointly use LiDAR and camera for this task. [15], [31] are closest to our objective in using LiDAR only: Held et al [15] aggregates the observed point clouds, while Ushani et al [31] directly optimizes a point cloud model.…”

Section: Point Cloud Completionmentioning

confidence: 99%

Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences

Pang¹,

Li²,

Wang³

2021

Preprint

View full text Add to dashboard Cite

Estimating the states of surrounding traffic participants stays at the core of autonomous driving. In this paper, we study a novel setting of this problem: model-free singleobject tracking (SOT), which takes the object state in the first frame as input, and jointly solves state estimation and tracking in subsequent frames. The main purpose for this new setting is to break the strong limitation of the popular "detection and tracking" scheme in multi-object tracking. Moreover, we notice that shape completion by overlaying the point clouds, which is a by-product of our proposed task, not only improves the performance of state estimation but also has numerous applications. As no benchmark for this task is available so far, we construct a new dataset LiDAR-SOT and corresponding evaluation protocols based on the Waymo Open dataset [28]. We then propose an optimization-based algorithm called SOTracker based on point cloud registration, vehicle shapes, and motion priors. Our quantitative and qualitative results prove the effectiveness of our SOTracker and reveal the challenging cases for SOT in point clouds, including the sparsity of LiDAR data, abrupt motion variation, etc. Finally, we also explore how the proposed task and algorithm may benefit other autonomous driving applications, including simulating LiDAR scans, generating motion data, and annotating optical flow. The code and protocols for our benchmark and algorithm are available at https://github.com/TuSimple/LiDAR_SOT/. A video demonstration is at https://www.youtube.com/watch? v=BpHixKs91i8.

show abstract

“…Point cloud based algorithms: detection algorithms based on Iterative Closest Point (ICP) match current segments of a point cloud to a previous point cloud to reveal their motion [11,23,30]. This approach works best for rigid objects like cars and considerably decreases in performance for deforming objects like humans.…”

Section: Related Workmentioning

confidence: 99%

Leveraging Stereo-Camera Data for Real-Time Dynamic Obstacle Detection and Tracking

Eppenberger¹,

Cesari²,

Dymczyk³

et al. 2020

Preprint

View full text Add to dashboard Cite

Dynamic obstacle avoidance is one crucial component for compliant navigation in crowded environments. In this paper we present a system for accurate and reliable detection and tracking of dynamic objects using noisy point cloud data generated by stereo cameras. Our solution is realtime capable and specifically designed for the deployment on computationally-constrained unmanned ground vehicles. The proposed approach identifies individual objects in the robot's surroundings and classifies them as either static or dynamic. The dynamic objects are labeled as either a person or a generic dynamic object. We then estimate their velocities to generate a 2D occupancy grid that is suitable for performing obstacle avoidance. We evaluate the system in indoor and outdoor scenarios and achieve real-time performance on a consumergrade computer. On our test-dataset, we reach a MOTP of 0.07 ± 0.07m, and a MOTA of 85.3% for the detection and tracking of dynamic objects. We reach a precision of 96.9% for the detection of static objects.

show abstract

High quality reconstruction of dynamic objects using 2D-3D camera fusion

Cited by 7 publications

References 27 publications

Moving Object Detection by 3D Flow Field Analysis

Moving Object Detection by 3D Flow Field Analysis

Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences

Leveraging Stereo-Camera Data for Real-Time Dynamic Obstacle Detection and Tracking

Contact Info

Product

Resources

About