基于视觉显著性的毫米波隐匿物品检测算法
2022年电子技术应用第11期
张珂绅,郭文风,王鹤澎,叶学义
杭州电子科技大学 通信工程学院,浙江 杭州310018
摘要: 针对毫米波图像中隐匿物品与人体灰度差异小、形状多变的问题,提出了一种基于视觉显著性的隐匿物品检测算法。该算法在双边滤波后,结合OTSU和形态学运算完成预处理以获得人体区域,再根据频域显著性计算定位前景,经背景抑制后生成显著图完成检测。实验数据表明,所提算法与典型的主动式毫米波成像检测算法相比,检出率分别提高5.87%和9.08%,有更好的检测性能。
中圖分類號(hào): TN928;TP391.41
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.212492
中文引用格式: 張珂紳,郭文風(fēng),王鶴澎,等. 基于視覺(jué)顯著性的毫米波隱匿物品檢測(cè)算法[J].電子技術(shù)應(yīng)用,2022,48(11):99-103,109.
英文引用格式: Zhang Keshen,Guo Wenfeng,Wang Hepeng,et al. Millimeter wave hidden object detection algorithm based on visual saliency[J]. Application of Electronic Technique,2022,48(11):99-103,109.
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.212492
中文引用格式: 張珂紳,郭文風(fēng),王鶴澎,等. 基于視覺(jué)顯著性的毫米波隱匿物品檢測(cè)算法[J].電子技術(shù)應(yīng)用,2022,48(11):99-103,109.
英文引用格式: Zhang Keshen,Guo Wenfeng,Wang Hepeng,et al. Millimeter wave hidden object detection algorithm based on visual saliency[J]. Application of Electronic Technique,2022,48(11):99-103,109.
Millimeter wave hidden object detection algorithm based on visual saliency
Zhang Keshen,Guo Wenfeng,Wang Hepeng,Ye Xueyi
School of Communication Engineering,Hangzhou Dianzi University,Hangzhou 310018,China
Abstract: In order to solve the problem that the gray level difference between hidden objects and human body in millimeter wave image is small and the shape is changeable, a hidden object detection algorithm based on visual saliency is proposed. After bilateral filtering, combined with OTSU and morphological operation,the algorithm completes the pretreatment to obtain the human body region. And then the foreground is located based on the significance calculation in the frequency domain. After background suppression,the significance map is generated,so the detection is completed. Experimental results show that compared with the typical active millimeter wave imaging detection algorithm, the detection rate of the proposed algorithm increases by 5.87% and 9.08%, respectively, and the proposed algorithm has better detection performance.
Key words : hidden object;visual salience;image signature;threshold segmentation
0 引言
近年來(lái),機(jī)場(chǎng)、車站等公共場(chǎng)所的安全問(wèn)題日益得到重視,對(duì)人體攜帶物品的安全檢查必不可少。目前主流的安檢手段如X射線探測(cè)雖然可以清晰成像,但X射線易電離且具有輻射性,不適合于人體安檢[1]。毫米波輻射在電磁頻譜中介于微波和紅外線之間,屬于非電離輻射,可以穿透人體衣物探測(cè)到隱匿物品,且對(duì)人體無(wú)害,有逐步取代傳統(tǒng)安檢手段的趨勢(shì)[2]。
隨著前端成像技術(shù)的不斷成熟,后端毫米波圖像的隱匿物品檢測(cè)成了目前亟待解決的問(wèn)題。目前毫米波成像系統(tǒng)輸出的圖像分辨率較差,信噪比低,對(duì)目標(biāo)檢測(cè)性能有負(fù)面影響,容易造成誤檢和漏檢[3]。這些都給隱匿物品檢測(cè)帶來(lái)了巨大的挑戰(zhàn)。
本文詳細(xì)內(nèi)容請(qǐng)下載:http://www.ihrv.cn/resource/share/2000005013。
作者信息:
張珂紳,郭文風(fēng),王鶴澎,葉學(xué)義
(杭州電子科技大學(xué) 通信工程學(xué)院,浙江 杭州310018)

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。
