Towards Multi-Object Detection and Tracking in Urban Scenario under Uncertainties

Kampker, Achim; Sefati, Mohsen; Rachman, Arya; Kreisköther, Kai; Campoy, Pascual

doi:10.5220/0006706101560167

Cited by 36 publications

(33 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other works on 3D visual tracking include [59], [166], [194], which used a single camera with a multi-Bernoulli mixture tracking filter. Some works with 3D lidar sensors include [114], [207], [234], which proposed online classification of humans for 3D lidar tracking. In [175], both camera and lidar data are used to improve people tracking.…”

Section: Multiple Pedestrian Trackingmentioning

confidence: 99%

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Camara

Bellotto

Coşar

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them. This narrative review article is Part I of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low-level image detection to high-level psychology models, from the perspective of an AV designer. This self-contained Part I covers the lower levels of this stack, from sensing, through detection and recognition, up to tracking of pedestrians. Technologies at these levels are found to be mature and available as foundations for use in high-level systems, such as behaviour modelling, prediction and interaction control.

show abstract

Section: Multiple Pedestrian Trackingmentioning

confidence: 99%

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Camara

Bellotto

Coşar

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…The uncertainties pertaining to the measurements and state estimations are generally handled by Bayesian probabilistic approaches (e.g, [12]). The unmodeled dynamics of the tracked object contribute in the uncertainties, generally tackled by Kalman filters [15] and particle filters [16], whereas, uncertainties due to measurements are treated by probabilistic data association methods, such as Joint Probabilistic Data Association filters [6] and Multiple Hypothesis Tracking [17]. The maintenance of the tracking information and pruning of the spurious and duplicate tracks is carried out by additional mechanism for track management.…”

Section: Modt Overviewmentioning

confidence: 99%

“…A similar implementation for ground classification is adopted in [6], however with an additional step of consistency check along the channels. This step is not necessary in this implementation because every bin gets relatively precise local ground information.…”

Section: Object Detectionmentioning

confidence: 99%

“…The concept has a diverse application area and so are the methods. In general, clustering algorithms may be divided into: (a) hierarchy-based [6], (b) centroid-based [30], (c) distribution-based [31], and (d) density-based methods [32]. The hierarchy-based or connectivity-based algorithms operate on the distances from the neighboring measurements.…”

Section: Object Detectionmentioning

confidence: 99%

“…To the best of authors’ knowledge, the proposed MODT framework is the first to have been implemented on an embedded computer that is based on multiple LiDARs, performs in real-time, and considers the existence of non-planar ground and elevated structures. A somewhat similar work was proposed in [6], however there a 2D clustering scheme is deployed for detection that suffers when attempting to detect objects under elevated structures, unless highly restricted dimension filters are used. Moreover, the Joint Probabilistic Data Association scheme is adopted without explicit consideration of the combinatorial explosion phenomenon, a major bottleneck in cluttered environments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Multi-LiDAR Based Multiple Object Detection and Tracking

Sualeh

Kim

2019

Sensors

View full text Add to dashboard Cite

Environmental perception plays an essential role in autonomous driving tasks and demands robustness in cluttered dynamic environments such as complex urban scenarios. In this paper, a robust Multiple Object Detection and Tracking (MODT) algorithm for a non-stationary base is presented, using multiple 3D LiDARs for perception. The merged LiDAR data is treated with an efficient MODT framework, considering the limitations of the vehicle-embedded computing environment. The ground classification is obtained through a grid-based method while considering a non-planar ground. Furthermore, unlike prior works, 3D grid-based clustering technique is developed to detect objects under elevated structures. The centroid measurements obtained from the object detection are tracked using Interactive Multiple Model-Unscented Kalman Filter-Joint Probabilistic Data Association Filter (IMM-UKF-JPDAF). IMM captures different motion patterns, UKF handles the nonlinearities of motion models, and JPDAF associates the measurements in the presence of clutter. The proposed algorithm is implemented on two slightly dissimilar platforms, giving real-time performance on embedded computers. The performance evaluation metrics by MOT16 and ground truths provided by KITTI Datasets are used for evaluations and comparison with the state-of-the-art. The experimentation on platforms and comparisons with state-of-the-art techniques suggest that the proposed framework is a feasible solution for MODT tasks.

show abstract

Processing Technology of Thematic Identification and Classification of Objects in the Multispectral Remote Sensing Imagery

Hnatushenko

Shedlovska²,

Shedlovsky³

2022

Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making

View full text Add to dashboard Cite

Towards Multi-Object Detection and Tracking in Urban Scenario under Uncertainties

Cited by 36 publications

References 23 publications

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Dynamic Multi-LiDAR Based Multiple Object Detection and Tracking

Processing Technology of Thematic Identification and Classification of Objects in the Multispectral Remote Sensing Imagery

Contact Info

Product

Resources

About