Robust Matching of Occupancy Maps for Odometry in Autonomous Vehicles

Dimitrievski, Martin; Hamme, David Van; Veelaert, Peter; Philips, Wilfried

doi:10.5220/0005719006260633

Cited by 15 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensor constellation is as depicted on Figure 3 with the area of interest defined by the intersection of the camera and radar fields of view ∼

. Vehicle odometry is estimated at run-time using the lidar data and the algorithm from our previous work [ 56 ] allowing tracking to be performed accurately in global coordinates.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Dimitrievski

Hamme

Veelaert

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents a vulnerable road user (VRU) tracking algorithm capable of handling noisy and missing detections from heterogeneous sensors. We propose a cooperative fusion algorithm for matching and reinforcing of radar and camera detections using their proximity and positional uncertainty. The belief in the existence and position of objects is then maximized by temporal integration of fused detections by a multi-object tracker. By switching between observation models, the tracker adapts to the detection noise characteristics making it robust to individual sensor failures. The main novelty of this paper is an improved imputation sampling function for updating the state when detections are missing. The proposed function uses a likelihood without association that is conditioned on the sensor information instead of the sensor model. The benefits of the proposed solution are two-fold: firstly, particle updates become computationally tractable and secondly, the problem of imputing samples from a state which is predicted without an associated detection is bypassed. Experimental evaluation shows a significant improvement in both detection and tracking performance over multiple control algorithms. In low light situations, the cooperative fusion outperforms intermediate fusion by as much as 30%, while increases in tracking performance are most significant in complex traffic scenes.

show abstract

“…The sensor constellation is as depicted on Figure 3 with the area of interest defined by the intersection of the camera and radar fields of view ∼

. Vehicle odometry is estimated at run-time using the lidar data and the algorithm from our previous work [ 56 ] allowing tracking to be performed accurately in global coordinates.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Dimitrievski

Hamme

Veelaert

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In all experiments, accurate odometry was obtained by applying the LiDAR odometry algorithm of [16]. The tracker [10] solves the association problem, and decides whether to update an existing track, spawn a new track or merge tracks.…”

Section: Resultsmentioning

confidence: 99%

People Tracking by Cooperative Fusion of RADAR and Camera Sensors

Dimitrievski

Jacobs

Veelaert

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

Accurate 3D tracking of objects from monocular camera poses challenges due to the loss of depth during projection. Although ranging by RADAR has proven effective in highway environments, people tracking remains beyond the capability of single sensor systems. In this paper, we propose a cooperative RADAR-camera fusion method for people tracking on the ground plane. Using average person height, joint detection likelihood is calculated by back-projecting detections from the camera onto the RADAR Range-Azimuth data. Peaks in the joint likelihood, representing candidate targets, are fed into a Particle Filter tracker. Depending on the association outcome, particles are updated using the associated detections (Tracking by Detection), or by sampling the raw likelihood itself (Tracking Before Detection). Utilizing the raw likelihood data has the advantage that lost targets are continuously tracked even if the camera or RADAR signal is below the detection threshold. We show that in single target, uncluttered environments, the proposed method entirely outperforms camera-only tracking. Experiments in a real-world urban environment also confirm that the cooperative fusion tracker produces significantly better estimates, even in difficult and ambiguous situations.

show abstract

“…However, depending on the spatial extent of the two input datasets, there can be some significant translations in the x-and y-axis and a rotation about the z-axis. Coarse registration is enhanced using a phase correlation transformation (one rotation along the z-axis and two translations) (Dimitrievski et al 2016). Approximate cropping of the two input datasets to the same spatial extent can facilitate the coarse registration performed in this step.…”

Section: Methodsmentioning

confidence: 99%

A Novel Approach to Register Multi-Platform Point Clouds for Rockfall Monitoring

Bolkas

Walton

Kromer

et al. 2021

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Point cloud produced from technologies such as terrestrial laser scanning (TLS) and photogrammetry (terrestrial and aerial) are widely used in rockfall monitoring applications due to the wealth of data they provide. In such applications, the acquisition and registration of multi-epoch point clouds is necessary. In addition, point clouds can be derived from different sensors (e.g., lasers versus digital cameras) and different platforms (terrestrial versus aerial). Therefore, registration methods should be able to support multi-platform datasets. Currently, registration of multi-platform datasets is done with manual intervention, and automatic registration is difficult. While registration of TLS point clouds can be achieved by targets that are not on the rock surface, this is not the case for photogrammetric methods, as ground control points (GCPs) should be located on the rock surface. Such GCPs can be lost or destroyed with time, and re-establishing them is difficult. Automated registration often relies on feature-based algorithms with refinement using the iterative closest point (ICP) algorithm. This paper presents a novel registration approach of multi-epoch and multi-platform point clouds to support rockfall monitoring applications. The registration method is based on edges that are detected in the different datasets using α-molecules. The paper shows application examples of the novel approach at different rock slopes in Colorado. Results demonstrate that the developed method in many cases performs better than the well-known ICP method and can be used to register point clouds and support rockfall monitoring.

show abstract

Robust Matching of Occupancy Maps for Odometry in Autonomous Vehicles

Cited by 15 publications

References 5 publications

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

People Tracking by Cooperative Fusion of RADAR and Camera Sensors

A Novel Approach to Register Multi-Platform Point Clouds for Rockfall Monitoring

Contact Info

Product

Resources

About