Results of a Precrash Application Based on Laser Scanner and Short-Range Radars

Pietzsch, Sylvia; Vu, Trung; Burlet, J.; Aycard, Olivier; Hackbarth, T.; Appenrodt, Nils; Dickmann, Jürgen; Radig, Bernd

doi:10.1109/tits.2009.2032300

Cited by 32 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our architecture has been validated in complex crash and non-crash scenarios and compared with Daimler architecture [4]. To conduct the experiments, we built up a comprehensive database that consists of short sequences of measurements recorded during predefined driving maneuvers.…”

Section: Resultsmentioning

confidence: 99%

An Occupancy Grid Based Architecture for ADAS

Aycard

Baig

2010

Advanced Microsystems for Automotive Applications 2010

View full text Add to dashboard Cite

Perceiving or understanding the environment surrounding a vehicle is a very important step in advanced driving assistance systems (ADAS). The task involves both Simultaneous Localization And Mapping (SLAM) and Detection And Tracking of Moving Objects (DATMO). In this context, we have developed a generic architecture based on occupancy grid to solve SLAM and DATMO in dynamic outdoor environments. In this paper, we give an overview of this architecture and results obtained in different european projects: PReVENT-ProFusion2, INTERSAFE2 & Interactive.

show abstract

Section: Resultsmentioning

confidence: 99%

An Occupancy Grid Based Architecture for ADAS

Aycard

Baig

2010

Advanced Microsystems for Automotive Applications 2010

View full text Add to dashboard Cite

show abstract

“…The region-growing method searches OT (occlusion threshold) points beyond a boundary for a continuation of the current object that it is attempting to grow. This method first attempts to grow the region on one side (see lines [10][11][12][13][14] and then the other side (see lines [15][16][17][18][19].…”

Section: Background-foreground Object Segmentation and Classificmentioning

confidence: 99%

“…Because classification is performed at the point level, this technique does not consider the likelihood that neighboring points will be of the same class. Pietzsch et al [11] also proposes a strategy that performs static/dynamic classification at the point level. Zhao et al [12] proposed a light detection and ranging (LIDAR) background-foreground segmentation algorithm.…”

Section: Introductionmentioning

confidence: 99%

Background Foreground Segmentation for SLAM

Corcoran

Winstanley

Mooney

et al. 2011

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Abstract-To perform simultaneous localization and mapping (SLAM) in dynamic environments, static background objects must first be determined. This condition can be achieved using a priori information in the form of a map of background objects. Such an approach exhibits a causality dilemma, because such a priori information is the ultimate goal of SLAM. In this paper, we propose a background foreground segmentation method that overcomes this issue. Localization is achieved using a robust iterative closest point implementation and vehicle odometry. Background objects are modeled as objects that are consistently located at a given spatial location. To improve robustness, classification is performed at the object level through the integration of a new segmentation method that is robust to partial object occlusion.Index Terms-Background-Foreground segmentation, light detection and ranging (LIDAR).

show abstract

“…Ambient motion estimation also plays important roles in assistive driving where relative motion between cars is the most useful index to predict potential environmental collision. The available assistive driving systems generally depend on range finders such as 3D lasers [7], [8], which are cumbersome and require additional hardware supports. The problem of motion estimation using wearable lightweight sensors has not been fully addressed either in theory or in practical products.…”

Section: Introductionmentioning

confidence: 99%

Ambient motion estimation in dynamic scenes using wearable visual-inertial sensors

Tan

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

This paper proposes a method to estimate the motion of ambient objects including translational and rotational velocities by moving observers with hybrid visual-inertial sensors. Ambient motion is recovered from visual optical flows that represent ego and ambient dynamics. In this paper, each moving object is considered as a rigid body that has been segmented from the background using computer vision algorithms. In motion recovery, the fundamental challenge is to resolve the coupling between scene depths and translational velocities. Ambient rotational velocities are obtained following a depthindependent bilinear constrain. The scales of ambient translational velocities is computed using the proposed dynamics constraint with an assumption that ambient accelerations are negligible. A fix-point optimization scheme is further introduced to iteratively refine the recoveries of translational and rotational ambient motion until an expected precision is achieved or the maximal iteration is reached. During the optimization, translational ambient motion is precisely recovered and translational ambient motion is rescaled to the canonical amplitude. The results of the simulation study show the effectiveness of the proposed method in motion analysis and prediction.

show abstract

Results of a Precrash Application Based on Laser Scanner and Short-Range Radars

Cited by 32 publications

References 15 publications

An Occupancy Grid Based Architecture for ADAS

An Occupancy Grid Based Architecture for ADAS

Background Foreground Segmentation for SLAM

Ambient motion estimation in dynamic scenes using wearable visual-inertial sensors

Contact Info

Product

Resources

About