ZHENG Huifei,WANG Juan,WANG Zuli.Computer Vision-based High-Altitude Object Detection Method[J].Journal of Chengdu University of Information Technology,2025,40(03):322-325.[doi:10.16836/j.cnki.jcuit.2025.03.011]
基于计算机视觉的高空抛物检测方法
- Title:
- Computer Vision-based High-Altitude Object Detection Method
- 文章编号:
- 2096-1618(2025)03-0322-04
- Keywords:
- high-altitude object; target detection; target tracking; encryption
- 分类号:
- TP391.41
- 文献标志码:
- A
- 摘要:
- 针对高层建筑环境下高空抛物检测准确率低的问题,研究影响高空抛物检测准确率的干扰因素,改进传统高空抛物检测方法。基于目标检测和目标跟踪技术,增加抗抖动和形态学去噪,降低复杂环境对检测率的影响。进一步改进高空抛物判定方法,提取目标跟踪过程中高空抛物轨迹数据的特征向量,经由神经网络模型分类,过滤非高空抛物的相似轨迹。并对原始数据和提取数据做加密处理,采用端到端加密的方法,数据在采集、传输和存储的过程中得到可靠保护,确保只有授权用户才能解密和访问数据。实验证明,改进后的高空抛物检出率和误检率优化了32、35.4个百分点,高空抛物轨迹分类准确率达到81%以上。
- Abstract:
- Aiming at the problem of low accuracy of overhead throwing detection in high-rise building environments, we study the interference factors affecting the accuracy of overhead throwing detection and improve the traditional overhead throwing detection method. Based on the target detection and target tracking technology, anti-jitter and morphological denoising are added to reduce the influence of the complex environment on the detection rate. Further, improve the overhead throwing determination method, extract the feature vectors of the overhead throwing trajectory data during the target tracking process, classify them by the neural network model, and filter the similar trajectories of non-overhead throwing objects. The original and extracted data are encrypted, and the end-to-end encryption method is adopted, so that the data are reliably protected during the whole process of being collected, transmitted, and stored, ensuring that only authorized users can decrypt and access the data. The experiments proved that the improved overhead throwing detection rate and false detection rate were optimized by 32% and 35.4%, and the accuracy of overhead throwing trajectory classification reached more than 81%.
参考文献/References:
[1] 季天宇.基于深度学习的高空抛物检测技术研究与应用[D].无锡:江南大学,2023.
[2] 苏崧.基于机器视觉的高空抛物检测技术研究[D].南京:南京理工大学,2022.
[3] 王志芳,代翔.一种端边云结合的高空抛物检测解决方案[J].中国安全防范技术与应用,2021,(4):26-28.
[4] 刘菁琪,冯禧龙,张泊墉,等.基于超声波探测和云物联的高空抛物监测系统[J].科技与创新,2023(5):53-55.
[5] 赵殿国.数据防窜改技术综述及其应用探析[J].内蒙古统计,2023(4):18-20.
[6] 苏鹏飞.基于加密算法的智慧园区视频监控上云系统设计[J].电子产品世界,2023,30(2):21-24.
[7] 葛泉波,王贺彬,杨秦敏,等.基于改进高斯混合模型的机器人运动状态估计[J].自动化学报,2022,48(8):1972-1983.
[8] 李晁铭,苏康友,张黎.一种基于计算机视觉的高空抛物智能识别方法[J].信息与电脑(理论版),2023,35(13):156-159.
相似文献/References:
[1]李 静,鲜 林,王海江.基于YOLOv3的船只检测算法研究[J].成都信息工程大学学报,2023,38(01):37.[doi:10.16836/j.cnki.jcuit.2023.01.006]
LI Jing,XIAN Lin,WANG Haijiang.Research on Ship Detection Algorithm based on YOLOv3[J].Journal of Chengdu University of Information Technology,2023,38(03):37.[doi:10.16836/j.cnki.jcuit.2023.01.006]
[2]魏春梅,马尚昌,卢会国,等.基于视频识别的气象观测场设备监控技术研究[J].成都信息工程大学学报,2023,38(02):129.[doi:10.16836/j.cnki.jcuit.2023.02.001]
WEI Chunmei,MA Shangchang,LU Huiguo,et al.Research on Equipment Monitoring Technology of Meteorological Observation Field based on Video Recognition[J].Journal of Chengdu University of Information Technology,2023,38(03):129.[doi:10.16836/j.cnki.jcuit.2023.02.001]
[3]孙光灵,周云龙.自注意力结合上下文解耦的交通车辆检测[J].成都信息工程大学学报,2024,39(04):422.[doi:10.16836/j.cnki.jcuit.2024.04.005]
SUN Guangling,ZHOU Yunlong.Traffic Vehicle Detection based on Self-Attention Combined with Context Decoupling[J].Journal of Chengdu University of Information Technology,2024,39(03):422.[doi:10.16836/j.cnki.jcuit.2024.04.005]
备注/Memo
收稿日期:2024-01-05