The multi‐iterative closest point tracker: An online algorithm for tracking multiple interacting targets

Feldman, Adam S.; Hybinette, Maria; Balch, Tucker

doi:10.1002/rob.21402

Cited by 27 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To make use of the full 3D shape of the tracked object, some trackers have attempted to align the object's point clouds using ICP and its variants [5,14]. Such trackers use a local hill-climbing approach to iteratively improve an alignment of two point clouds.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Combining 3D Shape, Color, and Motion for Robust Anytime Tracking

Held

Levinson

Thrun

et al. 2014

Robotics: Science and Systems X

View full text Add to dashboard Cite

Abstract-Although object tracking has been studied for decades, real-time tracking algorithms often suffer from low accuracy and poor robustness when confronted with difficult, realworld data. We present a tracker that combines 3D shape, color (when available), and motion cues to accurately track moving objects in real-time. Our tracker allocates computational effort based on the shape of the posterior distribution. Starting with a coarse approximation to the posterior, the tracker successively refines this distribution, increasing in tracking accuracy over time. The tracker can thus be run for any amount of time, after which the current approximation to the posterior is returned. Even at a minimum runtime of 0.7 milliseconds, our method outperforms all of the baseline methods of similar speed by at least 10%. If our tracker is allowed to run for longer, the accuracy continues to improve, and it continues to outperform all baseline methods. Our tracker is thus anytime, allowing the speed or accuracy to be optimized based on the needs of the application. I. INTRODUCTIONMany robotics applications are limited in what they can achieve due to unreliable tracking estimates. For example, an autonomous vehicle driving past a row of parked cars should know if one of these cars is about to pull out into the lane. Current state-of-the-art trackers give noisy estimates of the velocity of these vehicles, which are difficult to track due to heavy occlusion and viewpoint changes. Additionally, without robust estimates of the velocity of nearby vehicles, merging onto or off of highways or changing lanes become formidable tasks. Similar issues will be encountered by any robot that must act autonomously in crowded, dynamic environments.Our tracker makes use of the full 3D shape of the object being tracked, which allows us to robustly track objects despite occlusions or changes in viewpoint. We place the 3D shape information in a probabilistic framework, in which we combine cues from shape, color, and motion. As we will show, adding color and motion information gives a large benefit to our system compared to using the 3D shape alone. This information is especially useful for distant objects or objects under heavy occlusions, when detailed 3D shape information may not be available.We make use of a grid-based method to sample velocities from the state space. Traditional grid-based approaches are too slow to track multiple objects in real-time. We are able to finely sample from a large grid in real-time through the use of a novel method called annealed dynamic histograms. We start by sampling from the state space at a coarse resolution, using an approximation to the posterior distribution over velocities. As the sampling resolution increases, we anneal this distribution,

show abstract

Section: Related Workmentioning

confidence: 99%

“…First, we compare to the basic point-to-point ICP algorithm, using the implementation from PCL [21]. This basic method is used for tracking by Feldman et al [5]. We initialize ICP by aligning the centroids of the tracked object.…”

Section: B Evaluation: Relative Reference Framementioning

confidence: 99%

Combining 3D Shape, Color, and Motion for Robust Anytime Tracking

Held

Levinson

Thrun

et al. 2014

Robotics: Science and Systems X

View full text Add to dashboard Cite

show abstract

“…3D Tracking and Reconstruction In contrast to methods that track targets in 3D (e.g., [19,11,32]), we have access only to videos and do not use other sensor modalities such as range data. Compared with methods that perform joint 3D reconstruction and tracking (e.g., [16,18]), we are interested mainly in estimating the 3D pose and shape extent of the target in terms of its part layout.…”

Section: Related Workmentioning

confidence: 99%

“…Then the state of the target at time t, i.e., 3D aspect part locations and viewpoint, is predicted as the MAP of the posterior at time t, which is given by the sample with the largest posterior probability in Eq. (11). By sampling new viewpoints, we are able to predict the topological appearance change of the target, so as to apply and update the part templates accordingly.…”

Section: Particle Filtering Trackingmentioning

confidence: 99%

Monocular Multiview Object Tracking with 3D Aspect Parts

Xiang

Song

Mottaghi

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this work, we focus on the problem of tracking objects under significant viewpoint variations, which poses a big challenge to traditional object tracking methods. We propose a novel method to track an object and estimate its continuous pose and part locations under severe viewpoint change. In order to handle the change in topological appearance introduced by viewpoint transformations, we represent objects with 3D aspect parts and model the relationship between viewpoint and 3D aspect parts in a part-based particle filtering framework. Moreover, we show that instance-level online-learned part appearance can be incorporated into our model, which makes it more robust in difficult scenarios with occlusions. Experiments are conducted on a new dataset of challenging YouTube videos and a subset of the KITTI dataset [14] that include significant viewpoint variations, as well as a standard sequence for car tracking. We demonstrate that our method is able to track the 3D aspect parts and the viewpoint of objects accurately despite significant changes in viewpoint.

show abstract

“…But the problem above can be effectively solved if we use several laser range finders based on collaborative perception. Adam et al [12] proposed and evaluated a detection-based algorithm for tracking a variable number of dynamic targets online using multi-laser range finders. In [13], a system to detect and track of moving objects at an intersection using a network of horizontal laser range finders is presented.…”

Section: Introductionmentioning

confidence: 99%