An efficient TO-MHT algorithm for multi-target tracking in cluttered environment

Pan, Shengsen; Bao, Qing; Chen, Zengping

doi:10.1109/iaeac.2017.8054106

Cited by 3 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compare the two methods, we utilize the Poisson distribution to initialize our VRU tracker. We took the same procedure, as in [ 29 ]. This reference gives detail regarding setting the Poisson in a hypothesis tree.…”

Section: Resultsmentioning

confidence: 99%

“…In probability theory and statistics, researchers utilize the Poisson distribution of variables to initialize a hypothesis tree. Pan et al [ 29 ] and Moraffah et al [ 30 ] generate the first track by using the average spatial density of new and false-positive object detections in order to address the initialization with Poisson distribution. They use the Poisson distribution for modeling the number of objects in a fixed interval of space or time.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improved Data Association of Hypothesis-Based Trackers Using Fast and Robust Object Initialization

Dolatabadi

Elfring

Molengraft

2021

Sensors

View full text Add to dashboard Cite

The tracking of Vulnerable Road Users (VRU) is one of the vital tasks of autonomous cars. This includes estimating the positions and velocities of VRUs surrounding a car. To do this, VRU trackers must utilize measurements that are received from sensors. However, even the most accurate VRU trackers are affected by measurement noise, background clutter, and VRUs’ interaction and occlusion. Such uncertainties can cause deviations in sensors’ data association, thereby leading to dangerous situations and potentially even the failure of a tracker. The initialization of a data association depends on various parameters. This paper proposes steps to reveal the trade-offs between stochastic model parameters to improve data association’s accuracy in autonomous cars. The proposed steps can reduce the number of false tracks; besides, it is independent of variations in measurement noise and the number of VRUs. Our initialization can reduce the lag between the first detection and initialization of the VRU trackers. As a proof of concept, the procedure is validated using experiments, simulation data, and the publicly available KITTI dataset. Moreover, we compared our initialization method with the most popular approaches that were found in the literature. The results showed that the tracking precision and accuracy increase to 3.6% with the proposed initialization as compared to the state-of-the-art algorithms in tracking VRU.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Improved Data Association of Hypothesis-Based Trackers Using Fast and Robust Object Initialization

Dolatabadi

Elfring

Molengraft

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…However, the scope of the paper is to track and classify jointly the targets with WSN. In the next section, we present our approach to combine class information provided by sensors and class information obtained from track behavior given by estimated states (27) and its associated covariance (28).…”

Section: B Track Estimation With Geographic Constraints 1) Predictionmentioning

confidence: 99%

“…Algorithm must be adapted to track targets with several sensors. The proposed method is based on the (TO-MHT) framework [27], which takes advantage of the track tree structure to manage and maintain hypotheses sets. Each association between track and measurement generates hypotheses represented by a new branch in the tree of the possible joint association.…”

Section: Data Fusion and Associationmentioning

confidence: 99%