Compact Representation of Dynamic Driving Environments for ADAS by Parametric Free Space and Dynamic Object Maps

Schreier, Matthias; Willert, Volker; Adamy, Jürgen

doi:10.1109/tits.2015.2472965

Cited by 59 publications

(35 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed IMM-UKF-JPDAF tracker follows a five-step process: (a) interaction, (b) state prediction and measurement validation, (c) data association and model-based filtering, (d) mode probability update, and (e) combination step. A similar approach for single target is explained in [40], that addresses data association of measurements to a single tracked object. In comparison, a JPDAF is deployed in the proposed framework to perform tracking of multiple objects.…”

Section: Trackingmentioning

confidence: 99%

Visual-LiDAR Based 3D Object Detection and Tracking for Embedded Systems

Sualeh

Kim

2020

IEEE Access

View full text Add to dashboard Cite

In recent years, persistent news updates on autonomous vehicles and the claims of companies entering the space, brace the notion that vehicular autonomy of level 5 is just around the corner. However, the main hindrance in asserting the full autonomy still boils down to environmental perception that affects the autonomous decisions. An efficient perceptual system requires redundancy in sensor modalities capable of performing in varying environmental conditions, and providing a reliable information using limited computational resources. This work addresses the task of 3D object detection and tracking in the vehicles' environment, using camera and 3D LiDAR as primary sensors. The proposed framework is designed to operate in an embedded system that visually classifies the objects using a lightweight neural network, while tracking is performed in 3D space using LiDAR information. The main contribution of this work is 3D LiDAR point cloud classification using visual object detector, and an IMM-UKF-JPDAF based object tracker that jointly performs 3D object detection and tracking. The performance evaluation is carried out using MOT16 metrics and ground truths provided by KITTI Datasets. Furthermore, the proposed tracker is evaluated and compared with state-of-the-art approaches. The experiments suggest that the proposed framework offers a suitable solution for embedded systems to solve 3D object detection and tracking problem, with added benefits. INDEX TERMS Kalman filter, object detection, object tracking, point cloud classification, sensor fusion.

show abstract

Section: Trackingmentioning

confidence: 99%

Visual-LiDAR Based 3D Object Detection and Tracking for Embedded Systems

Sualeh

Kim

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…• Novel metric environment representation for intelligent vehicles by combining dynamic object maps with introduced Parametric Free Space (PFS) maps [223,226].…”

Section: Contributionsmentioning

confidence: 99%

“…Excerpts have already been published by the author in [221,223,226]. as generated by the dynamic mapping approach described in the previous Chapter 4.…”

Section: Generation Of Parametric Free Space Mapsmentioning

confidence: 99%

Bayesian environment representation, prediction, and criticality assessment for driver assistance systems

Schreier

2017

At - Automatisierungstechnik

Self Cite

View full text Add to dashboard Cite

The dissertation approaches the questions i) how to represent the driving environment in an environment model, ii) how to obtain such a representation, and iii) how to predict the traffic scene for criticality assessment. Bayesian inference provides the common framework of all designed methods. First, Parametric Free Space (PFS) maps are introduced, which compactly represent the vehicle environment in form of relevant, drivable free space. They are obtained by a novel method for grid mapping and tracking in dynamic environments. In addition, a maneuver-based, long-term trajectory prediction and criticality assessment system is introduced and the application of all methods within the advanced driver assistance system PRORETA 3 is described.

show abstract

“…However, the resolution of the corresponding grid maps has to be carefully designed, since a small resolution grid consumes a large storage space while a large resolution grid may lead to unfavorable errors near the obstacle surfaces [ 11 ]. With this consideration, an accurate and compact environment representation model without relying on the grid map needs be developed, so as to provide a concise spatial relationship [ 12 , 13 ] and improve the efficiency of navigation [ 14 ], as well as environmental information sharing among the UAVs [ 15 ]. Nonetheless, building an accurate and compact three-dimensional (3D) environment representation model from an onboard sensor is highly non-trivial.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Compact Environment Representation for UAV Navigation

Meng

et al. 2020

Sensors

View full text Add to dashboard Cite

Recently, unmanned aerial vehicles (UAVs) have attracted much attention due to their on-demand deployment, high mobility, and low cost. For UAVs navigating in an unknown environment, efficient environment representation is needed due to the storage limitation of the UAVs. Nonetheless, building an accurate and compact environment representation model is highly non-trivial because of the unknown shape of the obstacles and the time-consuming operations such as finding and eliminating the environmental details. To overcome these challenges, a novel vertical strip extraction algorithm is proposed to analyze the probability density function characteristics of the normalized disparity value and segment the obstacles through an adaptive size sliding window. In addition, a plane adjustment algorithm is proposed to represent the obstacle surfaces as polygonal prism profiles while minimizing the redundant obstacle information. By combining these two proposed algorithms, the depth sensor data can be converted into the multi-layer polygonal prism models in real time. Besides, a drone platform equipped with a depth sensor is developed to build the compact environment representation models in the real world. Experimental results demonstrate that the proposed scheme achieves better performance in terms of precision and storage as compared to the baseline.

show abstract

Compact Representation of Dynamic Driving Environments for ADAS by Parametric Free Space and Dynamic Object Maps

Cited by 59 publications

References 47 publications

Visual-LiDAR Based 3D Object Detection and Tracking for Embedded Systems

Visual-LiDAR Based 3D Object Detection and Tracking for Embedded Systems

Bayesian environment representation, prediction, and criticality assessment for driver assistance systems

Real-Time Compact Environment Representation for UAV Navigation

Contact Info

Product

Resources

About