Object Tracking in Video Sequence based on Kalman filter

Li, Hongmei; Huang, Lin; Zhang, Ruiqiang; Lv, Lei; Diangang, Wang; Jiazhou, Li

doi:10.1109/icceic51584.2020.00029

Cited by 5 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, outside the field of transport, there are studies focusing on people detection and counting that employ similar approaches based on overhead video cameras. Some authors have used Kalman filtering for tracking purposes [ 45 ] and to improve a YOLO-based object detection and tracking algorithm [ 46 ]. Others have used only object detection algorithms for counting [ 47 , 48 ].…”

Section: Introductionmentioning

confidence: 99%

Evaluating the Performance of Video-Based Automated Passenger Counting Systems in Real-World Conditions: A Comparative Study

Pronello,

Garzón Ruiz

2023

Sensors

View full text Add to dashboard Cite

Automatic passenger counting (APC) systems in public transport are useful in collecting information that can help improve the efficiency of transport networks. Focusing on video-based passenger counting, the aim of this study was to evaluate and compare an existing APC system, claimed by its manufacturer to be highly accurate (98%), with a newly developed low-cost APC system operating under the same real-world conditions. For this comparison, a low-cost APC system using a Raspberry Pi with a camera and a YOLOv5 object detection algorithm was developed, and an in-field experiment was performed in collaboration with the public transport companies operating in the cities of Turin and Asti in Italy. The experiment shows that the low-cost system was able to achieve an accuracy of 72.27% and 74.59%, respectively, for boarding and alighting, while the tested commercial APC system had an accuracy, respectively, of 53.11% and 55.29%. These findings suggest that current APC systems might not meet expectations under real-world conditions, while low-cost systems could potentially perform at the same level of accuracy or even better than very expensive commercial systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluating the Performance of Video-Based Automated Passenger Counting Systems in Real-World Conditions: A Comparative Study

Pronello,

Garzón Ruiz

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Object tracking has always been a focus of research in the field of computer vision. With the in-depth study of visual tracking algorithms by researchers, their scientific and theoretical basis has continued to improve, which has greatly promoted the development of surveillance systems, perceptual user interface, intelligent robotics, vehicle navigation, and intelligent transportation systems [1][2][3]. Two important factors to consider when for the performance of embedded hardware, algorithm selection, and algorithm-based improvement.…”

Section: Introductionmentioning

confidence: 99%

Real-time embedded object detection and tracking system in Zynq SoC

Dai

Hou

et al. 2021

J Image Video Proc.

View full text Add to dashboard Cite

With the increasing application of computer vision technology in autonomous driving, robot, and other mobile devices, more and more attention has been paid to the implementation of target detection and tracking algorithms on embedded platforms. The real-time performance and robustness of algorithms are two hot research topics and challenges in this field. In order to solve the problems of poor real-time tracking performance of embedded systems using convolutional neural networks and low robustness of tracking algorithms for complex scenes, this paper proposes a fast and accurate real-time video detection and tracking algorithm suitable for embedded systems. The algorithm combines the object detection model of single-shot multibox detection in deep convolution networks and the kernel correlation filters tracking algorithm, what is more, it accelerates the single-shot multibox detection model using field-programmable gate arrays, which satisfies the real-time performance of the algorithm on the embedded platform. To solve the problem of model contamination after the kernel correlation filters algorithm fails to track in complex scenes, an improvement in the validity detection mechanism of tracking results is proposed that solves the problem of the traditional kernel correlation filters algorithm not being able to robustly track for a long time. In order to solve the problem that the missed rate of the single-shot multibox detection model is high under the conditions of motion blur or illumination variation, a strategy to reduce missed rate is proposed that effectively reduces the missed detection. The experimental results on the embedded platform show that the algorithm can achieve real-time tracking of the object in the video and can automatically reposition the object to continue tracking after the object tracking fails.

show abstract