Optimal object detection and tracking in occluded video using DNN and gravitational search algorithm

Mahalingam, T. V.; Subramoniam, M.

doi:10.1007/s00500-020-05407-4

Cited by 12 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, he proposed a video sequence with powerful object detection and tracking capabilities. And through experimental analysis, it is proved that the video sequence can effectively improve the accuracy of moving target detection and tracking in complex scenes 5 . The research of Murugan et al.…”

Section: Related Workmentioning

confidence: 99%

“…And through experimental analysis, it is proved that the video sequence can effectively improve the accuracy of moving target detection and tracking in complex scenes. 5 The research of Murugan et al found that the video surveillance system plays an important role in the detection and tracking of moving objects, and proposed a more effective surveillance system deployment method in a wide range of applications. 6 Although the studies are closely related to moving target detection, these studies are relatively complicated and take a long time.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

(Retracted) Detection and tracking of moving targets in martial arts sports arena video based on non-scene target features

Jia

Wang

2022

J. Electron. Imag.

View full text Add to dashboard Cite

.With the vigorous development of contemporary information technology, the field of computer technology is constantly innovating and progressing. Among them, the field of computer vision has achieved more prominent development. Computer vision is a discipline that uses cameras and computers to imitate the structure of human organs, processes and analyzes the collected video sequences, and then makes corresponding behavior judgments. Moving object detection and tracking is an important branch of computer vision. Moving target detection and tracking has broad application space and development scenarios. Here, we aim to study the detection and tracking method of moving targets in a martial arts arena video based on non-scene target features. Based on this research theme, we combine the particle filter moving target tracking algorithm based on non-scene target features to carry out the moving target detection and tracking experiments in the video of the martial arts arena. The experiment concluded: compared with the conventional methods, the particle filter moving target tracking algorithm based on the non-scene target features can perform the following tasks without affecting the detection accuracy. It reduces the time for detecting and tracking the same moving target in the video of the martial arts arena by 1.5 min. It shows that the algorithm can improve the efficiency of non-scene moving target detection and tracking.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

(Retracted) Detection and tracking of moving targets in martial arts sports arena video based on non-scene target features

Jia

Wang

2022

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…The accelerometer is generally composed of the detection mass m and spring in equation (1). The detection quality is fixed and can only move along the input shaft [19].…”

Section: Principle Of Motion Trajectory Tracking Detection Systemmentioning

confidence: 99%

“…Objects generally have the attribute of motion. For a long time, external observation methods have been used to detect the state of object motion, such as global positioning system (GPS) and eagle eye system (real-time playback system) [1]. The space part includes 28 satellites, which are distributed on the orbital plane with 60 degrees apart at 6 intersections, about 20000 kilometers from the ground.…”

Section: Introductionmentioning

confidence: 99%

Motion Tracking and Detection System Based on Motion Sensor

Zhou

2022

Mobile Information Systems

View full text Add to dashboard Cite

To solve the problem of large error of motion MEMS sensor in motion trajectory detection, a motion trajectory tracking and detection system based on motion sensor is proposed. The principle of trajectory tracking is that the three-dimensional velocity and displacement can be obtained by integrating the acceleration. In this paper, acceleration sensor is used to obtain acceleration data of moving object. In order to reduce the data measurement error, a Kalman filter is designed and implemented to eliminate random noise. Aiming at the system nonlinear error, a two speed sampling compensation algorithm is designed and implemented by using the random characteristics of kernel process scheduling algorithm. The system accuracy is significantly improved without increasing the computational burden. According to the characteristics of floating-point instruction system on Advanced RISC Machine (ARM) platform, the algorithms of process core modules such as square root and matrix multiplication are optimized and improved, which greatly improves the computing performance of the system. According to the results of the study, the average error of measurement of X-line displacement measurement of the space control system is 8.06%, the average error of measurement of Y-line displacement measurement is 7.41%, the average error of measurement of Z-line displacement measurement is 9.61%, and the average error of 3D dimensional measurement is 7.6%. The effectiveness and feasibility of the system are verified.

show abstract

“…The model has advantages in terms of accuracy, precision, recall, sensitivity, and specificity. Gravitational search algorithm (GSA) plays an essential role in enhancing the prediction accuracy of DNN models [ 34 ]. The model can more precisely differentiate between benign and malignant nodules in CT scan lung images.…”

Section: Introductionmentioning

confidence: 99%

Multistrategy Improved Sparrow Search Algorithm Optimized Deep Neural Network for Esophageal Cancer

Wang

Liu

Sun

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Deep neural network is a complex pattern recognition network system. It is widely favored by scholars for its strong nonlinear fitting ability. However, training deep neural network models on small datasets typically realizes worse performance than shallow neural network. In this study, a strategy to improve the sparrow search algorithm based on the iterative map, iterative perturbation, and Gaussian mutation is developed. This optimized strategy improved the sparrow search algorithm validated by fourteen benchmark functions, and the algorithm has the best search accuracy and the fastest convergence speed. An algorithm based on the iterative map, iterative perturbation, and Gaussian mutation improved sparrow search algorithm is designed to optimize deep neural networks. The modified sparrow algorithm is exploited to search for the optimal connection weights of deep neural network. This algorithm is implemented for the esophageal cancer dataset along with the other six algorithms. The proposed model is able to achieve 0.92 under all the eight scoring criteria, which is better than the performance of the other six algorithms. Therefore, an optimized deep neural network based on an improved sparrow search algorithm with iterative map, iterative perturbation, and Gaussian mutation is an effective approach to predict the survival rate of esophageal cancer.

show abstract

Optimal object detection and tracking in occluded video using DNN and gravitational search algorithm

Cited by 12 publications

References 19 publications

(Retracted) Detection and tracking of moving targets in martial arts sports arena video based on non-scene target features

(Retracted) Detection and tracking of moving targets in martial arts sports arena video based on non-scene target features

Motion Tracking and Detection System Based on Motion Sensor

Multistrategy Improved Sparrow Search Algorithm Optimized Deep Neural Network for Esophageal Cancer

Contact Info

Product

Resources

About