A new algorithm is proposed that treats both the estimation of the trajectory of a sensor and the detection and tracking of moving objects jointly and has applicability to any type of environment since specific object models are not used at any algorithm stage.
Abstract:
Both, the estimation of the trajectory of a sensor and the detection and tracking of moving objects are essential tasks for autonomous robots. This work proposes a new algorithm that treats both problems jointly. The sole input is a sequence of dense 3D measurements as returned by multi-layer laser scanners or time-of-flight cameras. A major characteristic of the proposed approach is its applicability to any type of environment since specific object models are not used at any algorithm stage. More specifically, precise localization in non-flat environments is possible as well as the detection and tracking of e.g. trams or recumbent bicycles. Moreover, 3D shape estimation of moving objects is inherent to the proposed method. Thorough evaluation is conducted on a vehicular platform with a mounted Velodyne HDL-64E laser scanner.
TL;DR: A novel, dense approach to laserbased mapping that operates on three-dimensional point clouds obtained from rotating laser sensors is proposed that is efficient and enables real-time capable registration and is able to detect loop closures and to perform map updates in an online fashion.
TL;DR: A review of state-of-the-art automotive lidar technologies and the perception algorithms used with them and the limitations, challenges, and trends for automotive lidars and perception systems.
TL;DR: This paper presents a novel model-free approach for detecting and tracking dynamic objects in 3D LiDAR scans obtained by a moving sensor that outperforms the state of the art.
TL;DR: A review of state-of-the-art automotive LiDAR technologies and the perception algorithms used with those technologies can be found in this paper, where the main components from laser transmitter to its beam scanning mechanism are analyzed and compared.
TL;DR: This paper proposes a novel method for estimating dense rigid scene flow in 3D LiDAR scans as an energy minimization problem, where it assumes local geometric constancy and incorporate regularization for smooth motion fields.
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
TL;DR: The authors propose an approach that works on range data directly and registers successive views with enough overlapping area to get an accurate transformation between views and performs a functional that does not require point-to-point matches.
TL;DR: Based on the SLAM with DATMO framework, practical algorithms are proposed which deal with issues of perception modeling, data association, and moving object detection.
Since object models were kept generic and tracking is performed in full 3D, the approach is applicable to other sensors and in other application areas, too.
Q2. What is the way to evaluate the localization accuracy of a track?
Since in static scenes the proposed algorithm for localization equals the algorithm presented in [16], the results are transferable.
Q3. What is the average flatness value of the tracklet?
In case the average flatness value of the tracklet exceeds some threshold, the pointto-plane ICP [6] is used, otherwise the point-to-point variant [2].
Q4. What is the definition of a multi target tracking problem?
moosmann at kit.eduThe problem of multi target tracking is usually understood as the task to detect a set of objects in the environment and to characterize them by their position, orientation, extent, and velocity.
Q5. Why is the car continuously tracked during the overtaking maneuver?
Especially during the overtaking maneuver, the car is continuously tracked because the appearance smoothly adapts to the new viewpoints.
Q6. What is the ICP energy of the tracklet?
The ICP energy eg( tρ′′g,h) is calculated using both the Euclidean point-to-point distance [2] and the projective point-to-plane distance [6].
Q7. What is the special treatment for the static scene track?
One special treatment is made for the static scene track: instead of registering the track appearance against the input data, the input data is registered against the track appearance as in [16].
Q8. How is the ttt algorithm applied to 3D environments?
Experiments conducted in a vehicular environment show the applicability to 3D environments with both tracking and self-localization performed with full 6 degrees of freedom.
Q9. How is the registration and update performed?
Registration and update is performed as in [14] by aligning the track’s appearance point cloud with the full input point cloud by means of the ICP algorithm.