Improved SiamFC Target Tracking Algorithm Based on Anti-Interference Module

Yan, Yejin; Huo, Wenxiao; Ou, Jin Ping; Liu, Zhifeng; Li, Tianping

doi:10.1155/2022/2804114

Cited by 4 publications

(3 citation statements)

References 51 publications

(113 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The flexible target range ensures that the returned tracking bounding box matches the real target range more closely, but it is also more susceptible to interference from surrounding objects with similar features. Therefore, several scholars have attempted to propose a series of anti‐interference modules (Li et al, 2020; Tan & Lai, 2019; Wei et al, 2022; Yan et al, 2022). Current deep learning‐based target‐tracking methods tend to use deeper networks as feature extractors to improve the retrieval of targets in the search area.…”

Section: Related Workmentioning

confidence: 99%

Object tracking in surveillance video based on Siamese network considering geographical spatiotemporal constraints

Lin

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

Identifying and tracking objects in surveillance videos is an important means of mining information during surveillance. Currently, most object‐tracking methods rely only on image features, which cannot accurately express the motion of the tracked object in real geographical scenes and are easily influenced by occlusion and surrounding objects having similar features. However, tracked objects, such as pedestrians and vehicles, usually move in geographical space with fixed patterns of motion, and the motion in a short time is constrained by geographical space and time, the motion trajectory is predictable, and the range of motion is limited. Therefore, based on the SiamFC object tracking framework, this study introduces geographical spatiotemporal constraints into the tracking framework and proposes the GeoSiamFC method. The objective of this is to: (1) construct the mapping relationship between geographical space and image space to solve the problem that the pixel movement within the image after perspective imaging cannot accurately express the motion of the tracked object in a real geographical scene; (2) add candidate search areas according to the predicted trajectory location to correct the tracking errors caused by the occlusion of the object; and (3) focus on the search for the range of motion of the mapped pixel within the image space according to the limited geographical range of motion of the tracked objects in a certain time to reduce the interference of similar objects within the search area. In this study, separate experiments were conducted on a common test dataset using multiple methods to deal with challenges such as occlusion and illumination changes. In addition, a robust test dataset with noise addition and luminance adjustment based on the common test dataset was used. The results show that GeoSiamFC outperforms other object‐tracking methods in the common test dataset with a precision score of 0.995 and a success score of 0.756 compared with most other object‐tracking algorithms under the base condition of using only shallow networks. Moreover, GeoSiamFC maintained the highest precision score (0.970) and high success score (0.734) in the more challenging robust test dataset as well. The tracking speed of 59 frames per second far exceeds the real‐time requirement of 25 FPS. Geographical spatiotemporal constraints were considered to improve tracker performance while providing real‐time feedback on the motion trajectory of the target in geographical space. Thus, the proposed method is suitable for real‐time tracking of the motion trajectory of a target in real geographical scenes in various surveillance videos.

show abstract

Section: Related Workmentioning

confidence: 99%

Object tracking in surveillance video based on Siamese network considering geographical spatiotemporal constraints

Lin

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Network Tracker [43], SiamFC [44] High accuracy, Ability to model complex objects, Robustness to changes in appearance, illumination, and motion, Good performance on large-scale datasets High computational complexity, Requires large amounts of labeled training data, Limited real-time performance on resourceconstrained platforms by…”

Section: Siamesementioning

confidence: 99%

“…However, this type of tracker is more accurate than other types of trackers because of its ability of good decision making. Deep learning-based trackers are mainly of three types, CNN based [43], [44], Recurrent Neural Network(RNN) based [49] and Discriminative deep learning based [50,51].…”

Section: Siamesementioning

confidence: 99%

Real-Time Tracking of Moving Objects through Efficient Scale Space Adaptation and Normalized Correlation Filtering

Ali

Ghosh

Chaudhuri

2023

Preprint

View full text Add to dashboard Cite

The field of real-time mobile object tracking is a crucial aspect of computer vision. Despite numerous algorithms proposed for efficient tracking, the high computational complexity presents challenges in achieving real-time performance. This paper presents a novel approach by introducing an adaptive search region proposal block that works in tandem with Mean Shift and Unscented Kalman Filter. The block efficiently searches the region of the estimated object location. The dynamic changes in the appearance and size of a moving target make tracking difficult, but the proposed Multi-scale Template Matching technique addresses this challenge by utilizing the Normalized Cross-Correlation method in the adaptive search region. This optimization results in a reduced computational complexity and an increased frame rate of 53.4 FPS. Additionally, the approach leads to a 50.3% decrease in error rate and improved precision and success rates of 76% and 79% respectively. Comparisons with various state-of-the-art trackers show that the proposed algorithm achieves the best results in terms of precision, success rate, and object tracking error.

show abstract

Development of a YOLO-KCF Coupling Algorithm for Miniature Fixed-Wing UAVs in Target Detection and Tracking

et al. 2023

View full text Add to dashboard Cite

Target detection and tracking represent key challenges facing miniature fixed-wing unmanned aerial vehicles (UAVs), particularly at high cruising speeds. Therefore, this paper proposes a vision-based target detection and tracking algorithm that systematically couples two mainstream methods, namely, you only look once (YOLO) and kernel correlation filter (KCF) algorithms. This combination enables small fixed-wing UAVs to achieve reliable target detection and rapid target tracking. A customized vision-guidance module is constructed to implement this algorithm, and a dual-thread execution mechanism is developed to ensure that the computational resources are used effectively. A miniature fixed-wing UAV experimental platform is also constructed and evaluated. Flight experiments are performed, and the results demonstrate that the developed algorithm can achieve satisfactory detection and tracking accuracy for stationary and moving ground targets in complex environments.

show abstract

Improved SiamFC Target Tracking Algorithm Based on Anti-Interference Module

Cited by 4 publications

References 51 publications

Object tracking in surveillance video based on Siamese network considering geographical spatiotemporal constraints

Object tracking in surveillance video based on Siamese network considering geographical spatiotemporal constraints

Real-Time Tracking of Moving Objects through Efficient Scale Space Adaptation and Normalized Correlation Filtering

Development of a YOLO-KCF Coupling Algorithm for Miniature Fixed-Wing UAVs in Target Detection and Tracking

Contact Info

Product

Resources

About