Target Detection Algorithm of Gaussian Mixture Model Combined with HED Network and Double Threshold Segmentation

Abstract

Abstract: In the process of target detection, the GMM is easily interfered by lighting, the similarity of target color and background color, target shadow and shooting height. Aiming at the above problems, a GMM algorithm is combined with improved HED network and OTSU double threshold segmentation is proposed. First, the improved model divides the background, noise and foreground targets of video frame by double threshold, and reasonably selects the number of GMM. Secondly, HED network is used for edge detection of the input images.The “and” operation of edge result detected by the HED network and the GMM detection result of the double threshold segmentation is completed to obtain the final target detection result. Experimental results show that the improved algorithm has a higher detection rate, a more complete detection profile “and” a better detection effect.

Key words: OTSU double threshold, HED network, edge detection, “and” operation

CLC Number:

TP391.4

LI Rui, WANG De-zhong. Target Detection Algorithm of Gaussian Mixture Model Combined with HED Network and Double Threshold Segmentation[J]. Computer and Modernization, 2020, 0(06): 7-.

References

［1］慈文彦. 运动目标检测方法综述［J］. 信息技术, 2016(12):93-96.
［2］王梦菊,吴小龙,杜海涛. 基于背景差分与帧间差分的目标检测改进算法［J］. 自动化技术与应用, 2018,37(10):89-92.
［3］ WANG Z H, LI C Y, LIU Q P. Improved global optical flow estimation with mean shift algorithm for target detection［J］. International Journal of Wireless and Mobile Computing, 2015,8(4):323-328.
［4］范长军,文凌艳,毛泉涌,等. 结合单高斯与光流法的无人机运动目标检测［J］. 计算机系统应用, 2019,28(2):184-189.
［5］于雯越,安博文,赵明. 基于光流法与RPCA的红外运动目标检测［J］. 现代计算机, 2018(23):66-71.
［6］张应辉,刘养硕. 基于帧差法和背景差法的运动目标检测［J］. 计算机技术与发展, 2017,27(2):25-28.
［7］刘青芳. 基于帧差法的运动目标检测方法研究［J］. 数字通信世界, 2015(11):54.
［8］ LI X X, CHEN L L, ZHU S H. Statistical background model-based target detection［J］. Pattern Analysis and Applications, 2016,19(3):783-791.
［9］乐应英,胡静波. 融合LBP与背景建模的自适应目标检测混合算法［J］. 计算机与数字工程, 2013,41(7):1081-1084.
［10］丁哲,陆文总. 基于Vibe背景建模的运动目标检测算法［J］. 计算机系统应用, 2019,28(4):183-187.
［11］董俊宁,杨词慧. 空间约束混合高斯运动目标检测［J］. 中国图象图形学报, 2016,21(5):588-594.
［12］高海壮,段先华. 基于帧差法和混合高斯的海上运动目标检测［J］. 计算机与数字工程, 2019,47(5):1140-1144.
［13］苏剑臣,李策,杨峰. 基于边缘帧差和高斯混合模型的行人目标检测［J］. 计算机应用研究， 2018,35（4）：292-295.
［14］朱文杰,王广龙,田杰,等. 空时自适应混合高斯模型复杂背景运动目标检测［J］. 北京理工大学学报, 2018,38(2):165-172.
［15］段锁林,严翔,朱方,等. 基于改进混合高斯模型与六帧差分的目标检测算法［J］. 计算机工程, 2017,43(7):234-238.
［16］李睿,盛超. 基于熵和相关接近度的混合高斯目标检测算法［J］. 计算机科学, 2017,44(12):304-309.
［17］KE Z X, JIANG H H， ZHANG C L. Moving objects detection based on three frames differencing and GMM［J］. Advanced Materials Research, 2013,694-697:1974-1977.
［18］XIE S N, TU Z W. Holistically-nested edge detection［J］. International Journal of Computer Vision, 2017,125(1/3):3-18.
［19］焦安波,何淼,罗海波. 一种改进的HED网络及其在边缘检测中的应用［J］. 红外技术, 2019,41(1):72-77.
［20］孙力. 基于ROI与自适应OSTU相结合的图像分割算法［J］. 现代电子技术, 2011,34(6):1-3.
［21］WANG J B, XIONG H D, JIANG N, et al. An improved floc image segmentation algorithm based on Otsu and particle swarm optimisation［J］. International Journal of Computational Science and Engineering, 2017,15(1/2):49-56.
［22］郭永芳,于明,黄凯. 基于细菌趋药性的OSTU双阈值图像分割算法［J］. 计算机工程, 2011,37(22):8-11.
［23］宋森森,贾振红,杨杰,等. 结合OSTU阈值法的最小生成树图像分割算法［J］. 计算机工程与应用, 2019,55(9):178-183.

[1]	ZHAO Qi-wen, XU Kun, XU Yuan. Fast Paper Edge Detection Method Based on HED Network [J]. Computer and Modernization, 2021, 0(05): 1-5.
[2]	ZHOU Hong-yu1, MA Qian-li1, MA Peng-bo2 . Detecting Method for Workpiece Size and Symmetry of Blower Rotor [J]. Computer and Modernization, 2019, 0(11): 55-.
[3]	LIU Bo-ping1,2, MENG Sha-sha1,2, RAO Lan-xiang1,2, FU Kang1,2. Color Image Edge Detection Algorithm Based on K-means and Improved Ant Colony Optimization [J]. Computer and Modernization, 2016, 0(9): 60-63.
[4]	LIU Zhan. Image Edge Detection Algorithm Based on Local Expectation Threshold Segmentation [J]. Computer and Modernization, 2016, 0(8): 52-55.
[5]	DU Mo1,2, WANG Qing-li2. Target Location Based on Double-edge Detection [J]. Computer and Modernization, 2016, 0(8): 56-59.
[6]	DUAN Shan-shan1, LI Xin2. An Adaptive Visual Odometry Algorithm Based on RGBD Sensors [J]. Computer and Modernization, 2016, 0(12): 73-77.
[7]	ZHU Hai-yang1, XU Gen-jiu2, LI Yuan-chen1, ZHANG Meng-qi2. Dynamic Threshold Selection of Local Region Based on Image Partition [J]. Computer and Modernization, 2016, 0(11): 53-57.
[8]	HAO Hongzhuan, ZHANG Weiqiang. Noise Image Edge Detection Algorithm Based on Wavelet Transform [J]. Computer and Modernization, 2015, 0(2): 80-.
[9]	ZHAO Xing-wang, LI Tian-yang, WANG Liang, ZHOU Jing. Second-generation ID Number Recognition System Based on Digital Devices [J]. Computer and Modernization, 2014, 0(6): 132-136.
[10]	ZUO Yu-peng1,2. An Edge Adaptive Up-sampling Scheme Based on Depth Map Compression [J]. Computer and Modernization, 2014, 0(5): 84-88.
[11]	ZHANG Yan-hong;LI Ying;ZHANG Yan-ning;WANG Feng-qin. Research and Realization of Cell Image Segmentation Method Based on Mathematical Morphology [J]. Computer and Modernization, 2013, 1(7): 135-137,.
[12]	ZHAO Boyi;ZHANG Ke. Research on a SAR Image Matching Method Based on Improved SIFT Algorithm [J]. Computer and Modernization, 2013, 1(6): 108-112.
[13]	CHEN Wei-qing;TIAN Pei-yun;ZHENG Bi-bo. Edge Detection of Color Image Based on Quaternion and LOG Operator [J]. Computer and Modernization, 2013, 1(4): 95-98,1.
[14]	GOU Rong. Image Edge Detection Based on GL Fractional Differential [J]. Computer and Modernization, 2013, 1(11): 17-19.
[15]	ZHANG Lan;XU Lei;ZHANG Yang. Mesh Generation Algorithm of Composite Materials Based on Digital Image [J]. Computer and Modernization, 2013, 218(10): 35-37.