Design of moving object detection embedded experimental platform based on Python

LIANG Nan, LI Sen, ZHANG Chunfei, LIU Pengfei

Integrated Circuits and Embedded Systems ›› 2025, Vol. 25 ›› Issue (9) : 28-35.

PDF(14534 KB)
PDF(14534 KB)
Integrated Circuits and Embedded Systems ›› 2025, Vol. 25 ›› Issue (9) : 28-35. DOI: 10.20193/j.ices2097-4191.2025.0037
Research Paper

Design of moving object detection embedded experimental platform based on Python

Author information +
History +

Abstract

To meet the needs of personalized talent training in Emerging Engineering Education, an experimental platform for moving object detection based on Python and embedded development board is designed. The platform combines advanced technologies such as edge computing, deep learning and image recognition to design experiment module. The experimental platform is configured based on the Linux system of the embedded development board. The moving target detection algorithms based on frame difference method, background subtraction and optical flow are developed using Python language. The deep learning algorithms are deployed based on Tencent ncnn computing framework to recognize and locate moving objects. The platform enables students to choose different experimental projects and methods according to their interest in scientific research to improve the teaching effect.

Key words

experimental platform / Python / embedded development board / moving object detection / deep learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
LIANG Nan , LI Sen , ZHANG Chunfei , et al. Design of moving object detection embedded experimental platform based on Python[J]. Integrated Circuits and Embedded Systems. 2025, 25(9): 28-35 https://doi.org/10.20193/j.ices2097-4191.2025.0037

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis
[1]
窦海波. 考虑遮挡因素的视频人体运动目标自适应跟踪[J]. 吉林大学学报(信息科学版), 2023, 41(3):566-573.
DOU H B. Adaptive Tracking Algorithm for Video Human Moving Objects Considering Occlusion[J]. Journal of Jilin University (Information Science Edition), 2023, 41(3):566-573 (in Chinese).
Cited in this article [1]
[2]
刘明文, 蒋涛, 袁建英, 等. 基于双目稀疏场景流的智能车运动目标检测[J]. 成都信息工程大学学报, 2023, 38(4):381-386.
LIU M W, JIANG T, YUAN J Y, et al. Detection of Moving Objects in Smart Cars based on Binocular Sparse Scene Flow[J]. Journal of Chengdu University of Information Technology, 2023, 38(4):381-386 (in Chinese).
Cited in this article [1]
[3]
JANS C, BOGOSSIAN F, ANDERSEN P, et al. Examining the impact of virtual reality on clinical decision making- An integrative review[J]. Nurse Education Today, 2023,125.
Cited in this article [1]
[4]
杨彬, 毛银, 陈晋, 等. 深度学习的遥感变化检测综述: 文献计量与分析[J]. 遥感学报, 2023, 27(9):1988-2005.
YANG B, MAO Y, CHEN J, et al. Review of remote sensing change detection in deep learning: Bibliometric and analysis[J]. National Remote Sensing Bulletin, 2023, 27(9):1988-2005 (in Chinese).
Cited in this article [1]
[5]
何永琦, 张腾, 邱健. 一种基于边缘计算的野外目标探测器设计与实现[J]. 电子设计工程, 2023, 31(12):174-179,184.
HE Y Q, ZHANG T, QIU J. Design and implementation of a wild object detector based on edge computing[J]. Electronic Design Engineering, 2023, 31(12):174-179,184 (in Chinese).
Cited in this article [1]
[6]
杨焕峥, 崔业梅, 杨贝贝, 等. 嵌入式人工智能与物联网实验开发板教学应用[J]. 实验技术与管理, 2021, 38(7):238-243.
YANG H Z, CUI Y M, YANG B B, et al. Teaching application of experimental development board for embedded artificial intelligence and Internet of Things[J]. Experimental Technology and Management, 2021, 38(7):238-243 (in Chinese).
Cited in this article [1]
[7]
张玥, 张琦, 陈梦丹, 等. 基于树莓派的智能监控系统设计与实现[J]. 计算机测量与控制, 2023, 31(8):122-127,134.
ZHANG Y, ZHANG Q, CHENG M D, et al. Design and Implementation of Intelligent Monitoring System Based on Raspberry PI[J]. Computer Measurement & Control, 2023, 31(8):122-127,134 (in Chinese).
Cited in this article [1]
[8]
徐金鸣, 张龙乐, 孙立辉. 基于树莓派4B的入侵监控系统设计与实现[J]. 长江信息通信, 2024, 37(12):112-115.
XU J M, ZHANG L L, SUN L H. Design and Implementation of an Intrusion Monitoring System Based on Raspberry Pi 4B[J]. Changjiang Information & Communications, 2024, 37(12):112-115 (in Chinese).
Cited in this article [1]
[9]
刘存领, 林青松, 于洪泽. 基于FPGA的运动目标远程监视系统设计[J]. 计算机测量与控制, 2023, 31(5):21-27.
LIU C L, LIN Q S, YU H Z. Design of Remote Monitoring System for Moving Target Based on FPGA[J]. Computer Measurement & Control, 2023, 31(5):21-27 (in Chinese).
Cited in this article [1]
[10]
王德贵, 彭圣哲, 孙小倩, 等. 基于深度学习与嵌入式系统课程结合的教学案例实践探索[J]. 创新创业理论研究与实践, 2024, 7(14):145-149,153.
WANG D G, PENG S Z, SUN X Q, et al. Exploration on Teaching Reform Based on the Combination of Deep Learning and Embedded Curriculum[J]. The Theory and Practice of Innovation and Entrepreneurship, 2024, 7(14):145-149,153 (in Chinese).
Cited in this article [1]
[11]
陆玲霞, 于淼, 彭勇刚. 面向I3型卓越人才培养的嵌入式人工智能实验教学探索[J]. 实验室研究与探索, 2025, 44(1):85-90.
LU L X, YU M, PENG Y G. Exploration of Embedded Artificial Intelligence Experimental Teaching for Cultivating I3-type Outstanding Talents[J]. Research and Exploration in Laboratory, 2025, 44(1):85-90 (in Chinese).
Cited in this article [1]
[12]
刘雪琳, 章钰琪, 董爱国. 基于Python的物理实验数据处理系统设计与实现[J]. 实验技术与管理, 2021, 38(3):74-78.
LIU X L, ZHANG Y Q, DONG A G. Design and realization of python-based physical experimental data processing system[J]. Experimental Technology and Management, 2021, 38(3):74-78 (in Chinese).
Cited in this article [1]
[13]
梁楠, 王成喜, 张春飞, 等. 基于Python的多维度、层次化的综合实验平台[J]. 吉林大学学报(信息科学版), 2023, 41(5):858-865.
LIANG N, WANG C X, ZHANG C F, et al. Design of Multi-Dimensional and Hierarchical Integrated Experimental Platform Based on Python[J]. Journal of Jilin University (Information Science Edition), 2023, 41(5): 858-865 (in Chinese).
Cited in this article [1]
[14]
CHENG Y H, WANG J. A Motion Image Detection Method Based on the Inter-Frame Difference Method[J]. Applied Mechanics & Materials, 2014,490-491:1283-1286.
Cited in this article [1]
[15]
WANG H L, WANG J Q, DING H F, et al. Moving Target Detection Based on the Improved Gaussian Mixture Model Background Difference Method[J]. Advanced Materials Research, 2012,482-484:569-574.
Cited in this article [1]
[16]
廖逍, 张弛, 应国德, 等. 基于背景差分法的电网巡检运动目标检测技术[J]. 沈阳工业大学学报, 2023, 45(1):78-83.
https://doi.org/10.7688/j.issn.1000-1646.2023.01.13
Abstract
针对无人机对电网巡检过程中移动镜头下的目标检测问题,采用背景补偿与背景差分法实现了动态场景下的目标检测.建立了全局运动矢量模型,并利用SIFT特征点提取和匹配技术,完成了视频图像的特征点匹配,实现了移动镜头下的背景补偿.通过降维和局部匹配方式对SIFT特征点提取和匹配技术进行优化.结果表明,优化后的特征向量生成时间是原来的30％～40％,与经典SIFT算法相比,提取特征点的总时间是原来的30％～50％,该方法能准确检测运动目标并排除干扰.
LIAO X, ZHANG C, YING G D, et al. Moving target detection technology based on background difference method for power grid patrol inspection[J]. Journal of Shenyang University of Technology, 2023, 45(1):78-83 (in Chinese).
https://doi.org/10.7688/j.issn.1000-1646.2023.01.13
Cited in this article [1] Abstract
Aiming at the problem of target detection by using the unmanned aerial vehicle (UAV) with moving lens during the power grid patrol inspection, both background compensation and background difference methods were adopted to realize the target detection in dynamic scenes. A global motion vector model was established, and a SIFT feature point extraction and matching technology was used to complete the feature point matching for video images to realize the background compensation under moving lens. The SIFT feature point extraction and matching technology was optimized through dimensional reduction and local matching mode. The results show that the generation time of optimized feature vector is as much as 30％ to 40％ of original time, and the total time for extracting feature points is as much as 30％ to 50％ of original time, compared with the classical SIFT algorithm. Furthermore, the as-proposed method can accurately detect moving targets and eliminate interference as well.
[17]
RAZAVIAN M, OESTGES C, VANHOENACKER D. Synthetic Rain Models and Optical Flow Algorithms for Improving the Resolution of Rain Attenuation Time Series Simulated from Numerical Weather Prediction[J]. Radio Science, 2022, 58(1).
Cited in this article [1]
[18]
刘珂铖, 谢群, 李雁军. 基于深度学习YOLOX算法的混凝土构件裂缝智能化检测方法[J]. 济南大学学报(自然科学版), 2024, 38(3):341-349.
LIU K C, XIE Q, LI Y J. Intelligent Detection Method for Cracks of Concrete Members Based on Deep Learning YOLOX Algorithm[J]. Journal of University of Jinan (Science and Technology), 2024, 38(3):341-349 (in Chinese).
Cited in this article [1]
PDF(14534 KB)

Accesses

Citation

Detail
Sections
Recommended

/

〈 〉