New Multiple-Target Tracking Strategy Using Domain Knowledge and Optimization

Ding, Runxiao; Yu, Miao; Oh, Hyondong; Chen, Wenhua

doi:10.1109/tsmc.2016.2615188

Cited by 35 publications

(21 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Given component number k = 1, · · · , M for GMM(i) with i = 1, · · · , k * , establish a series of GMMs using EM algorithm for parameter optimization along with k-mean++ initialization; (2) Determine the optimal component number for GMM(i) with i = 1, · · · , k * by maximizing the VRC; (3) Perform classification using the formula in (3).…”

Section: Algorithm 3: Steps For Gmm Classifier With Optimal Componentmentioning

confidence: 99%

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

Liu

2019

IEEE Trans. Syst. Man Cybern, Syst.

Self Cite

View full text Add to dashboard Cite

Adapting in-vehicle systems (e.g., advanced driver assistance systems and in-vehicle information systems) to individual drivers' workload can enhance both safety and convenience. To make this possible, it is a prerequisite to infer driver workload so that adaptive aiding can be provided to the driver at the right time and in an appropriate manner. Rather than developing an average model for all drivers, a personalized driver workload inference (PDWI) system considering individual drivers driving characteristics is developed using machine learning techniques via easily accessed vehicle related measurements (VRMs). The proposed PDWI system comprises two stages. In offline training, individual drivers workload is first automatically splitted into different categories according to its inherent data characteristics using fuzzy C-means (FCM) clustering. Then an implicit mapping between VRMs and different levels of workload is constructed via classification algorithms. In online implementation, VRMs samples are classified into different clusters, consequently driver workload type can be successfully inferred. A recently collected dataset from real-world naturalistic driving experiments is drawn to validate the proposed PDWI system. Comparative experimental results indicate that the proposed framework integrating FCM clustering and support vector machine classifier provides a promising workload recognition performance in terms of accuracy, precision, recall, F 1 -score, and prediction time. The interindividual differences in term of workload are also identified and can be accommodated by the proposed framework due to its adaptiveness.Index Terms-Fuzzy C-means (FCM) clustering, personalized aiding, support vector machine (SVM), workload recognition.

show abstract

Section: Algorithm 3: Steps For Gmm Classifier With Optimal Componentmentioning

confidence: 99%

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

Liu

2019

IEEE Trans. Syst. Man Cybern, Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…When n ik ≤ n max and node i meets other targets at time t, the evaluation results of node i on those targets (including its currently tracking target) are normalized as (14). The normalized results w ik become the transition probabilities P ik for node i in tracking mode to reselect a target k to track.…”

Section: Mode Switching Mechanismmentioning

confidence: 99%

“…To facilitate target tracking, Xu et al [11] and Deshpande et al [12] considered to combine autonomous navigation with target tracking. Others have studied the problem of tracking multiple targets in a given AoI [13], [14].…”

Section: Introductionmentioning

confidence: 99%

Semi-Flocking-Controlled Mobile Sensor Networks for Dynamic Area Coverage and Multiple Target Tracking

et al. 2018

View full text Add to dashboard Cite

Mobile sensor networks (MSNs) can provide sensing coverage to large areas of interest (AoIs). Area coverage and target tracking capabilities of MSNs are heavily depending on their motion control and coordination mechanisms. Many existing MSN motion control algorithms ignore or poorly utilize available information from their operating environment, thus lead to unsatisfactory monitoring performances. This paper proposes a fully distributed semi-flocking algorithm which enables mobile nodes to self-organize themselves based on mobility and sensing information via information exchanges among nearby nodes. A distributed mechanism is designed to maximize area coverage and target tracking performances of MSNs. Mobile nodes perform evaluations based on received information and switch between searching and tracking modes. Behaviors of MSNs controlled by the proposed algorithm are studied under different levels of information exchanges. Our study shows that the proposed semi-flocking algorithm is capable of delivering desirable area coverage and target tracking performances in MSNs.

show abstract

“…Currently, the main methods for video-based vehicle tracking can be divided into generative method and discriminative method [19]. Sparse Coding was the mainstream of generative tracking [20] methods such as ALSA and L1APG [21] in previous years. Currently, as a representative of the discriminative tracking method, the correlation filtering method has gradually occupied the mainstream position and achieved satisfactory results, such as Kalman filter [22] and Kernel Correlation Filter (KCF) [23].…”

Section: Introductionmentioning

confidence: 99%

Video-Based Vehicle Counting for Expressway: A Novel Approach Based on Vehicle Detection and Correlation-Matched Tracking Using Image Data from PTZ Cameras

Meng

Song

Zhang

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Vehicle counting plays a significant role in vehicle behavior analysis and traffic incident detection for established video surveillance systems on expressway. Since the existing sensor method and the traditional image processing method have the problems of difficulty in installation, high cost, and low precision, a novel vehicle counting method is proposed, which realizes efficient counting based on multivehicle detection and multivehicle tracking. For multivehicle detection tasks, a construction of the new expressway dataset consists of a large number of sample images with a high resolution (1920 × 1080) captured from real-world expressway scenes (including the diversity climatic conditions and visual angles) by Pan-Tilt-Zoom (PTZ) cameras, in which vehicle categories and annotation rules are defined. Moreover, a correlation-matched algorithm for multivehicle tracking is proposed, which solves the problem of occlusion and vehicle scale change in the tracking process. Due to the discontinuity and unsmooth of the trajectories that occurred during the tracking process, we designed a trajectory optimization algorithm based on least square method. Finally, a new vehicle counting method is designed based on the tracking results, in which the driving direction information of the vehicle is added in the counting process. The experimental results show that the proposed counting method in this research can achieve more than 93% accuracy and an average speed of 25 frames per second in expressway video sequence.

show abstract

New Multiple-Target Tracking Strategy Using Domain Knowledge and Optimization

Cited by 35 publications

References 29 publications

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

Semi-Flocking-Controlled Mobile Sensor Networks for Dynamic Area Coverage and Multiple Target Tracking

Video-Based Vehicle Counting for Expressway: A Novel Approach Based on Vehicle Detection and Correlation-Matched Tracking Using Image Data from PTZ Cameras

Contact Info

Product

Resources

About