Suppr超能文献

基于区块链和稳健特征定位的视频目标跟踪与校正模型。

A Video Target Tracking and Correction Model with Blockchain and Robust Feature Location.

机构信息

College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China.

Hangzhou Anheng Information Technology Co., Ltd., Hangzhou 310051, China.

出版信息

Sensors (Basel). 2023 Feb 22;23(5):2408. doi: 10.3390/s23052408.

Abstract

In this paper, a cutting-edge video target tracking system is proposed, combining feature location and blockchain technology. The location method makes full use of feature registration and received trajectory correction signals to achieve high accuracy in tracking targets. The system leverages the power of blockchain technology to address the challenge of insufficient accuracy in tracking occluded targets, by organizing the video target tracking tasks in a secure and decentralized manner. To further enhance the accuracy of small target tracking, the system uses adaptive clustering to guide the target location process across different nodes. In addition, the paper also presents an unmentioned trajectory optimization post-processing approach, which is based on result stabilization, effectively reducing inter-frame jitter. This post-processing step plays a crucial role in maintaining a smooth and stable track of the target, even in challenging scenarios such as fast movements or significant occlusions. Experimental results on CarChase2 (TLP) and basketball stand advertisements (BSA) datasets show that the proposed feature location method is better than the existing methods, achieving a recall of 51% (27.96+) and a precision of 66.5% (40.04+) in the CarChase2 dataset and recall of 85.52 (11.75+)% and precision of 47.48 (39.2+)% in the BSA dataset. Moreover, the proposed video target tracking and correction model performs better than the existing tracking model, showing a recall of 97.1% and a precision of 92.6% in the CarChase2 dataset and an average recall of 75.9% and mAP of 82.87% in the BSA dataset, respectively. The proposed system presents a comprehensive solution for video target tracking, offering high accuracy, robustness, and stability. The combination of robust feature location, blockchain technology, and trajectory optimization post-processing makes it a promising approach for a wide range of video analytics applications, such as surveillance, autonomous driving, and sports analysis.

摘要

本文提出了一种融合特征定位和区块链技术的前沿视频目标跟踪系统。该定位方法充分利用特征注册和接收的轨迹校正信号,实现了对目标的高精度跟踪。系统利用区块链技术的力量,通过安全和去中心化的方式组织视频目标跟踪任务,解决了跟踪被遮挡目标时精度不足的挑战。为了进一步提高小目标跟踪的准确性,系统使用自适应聚类来指导不同节点的目标定位过程。此外,本文还提出了一种未提及的轨迹优化后处理方法,该方法基于结果稳定化,有效减少了帧间抖动。该后处理步骤在保持目标平滑稳定的跟踪方面起着至关重要的作用,即使在快速运动或显著遮挡等具有挑战性的场景下也是如此。在 CarChase2(TLP)和篮球架广告(BSA)数据集上的实验结果表明,所提出的特征定位方法优于现有方法,在 CarChase2 数据集上的召回率为 51%(27.96+)和精度为 66.5%(40.04+),在 BSA 数据集上的召回率为 85.52%(11.75+)和精度为 47.48%(39.2+)。此外,所提出的视频目标跟踪和校正模型优于现有的跟踪模型,在 CarChase2 数据集上的召回率为 97.1%和精度为 92.6%,在 BSA 数据集上的平均召回率为 75.9%和 mAP 为 82.87%。该系统为视频目标跟踪提供了一个全面的解决方案,具有高精度、鲁棒性和稳定性。强大的特征定位、区块链技术和轨迹优化后处理的结合使其成为广泛的视频分析应用的一种有前途的方法,例如监控、自动驾驶和运动分析。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/f317/10007279/d5fd395d7362/sensors-23-02408-g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验