基于立體視覺與光流融合的運動目標(biāo)檢測
發(fā)布時間：2019-06-01 11:35
【摘要】：針對攝像機與被檢測目標(biāo)同時運動時的目標(biāo)檢測問題,提出一種立體視覺與光流融合的運動目標(biāo)檢測算法。結(jié)合立體視覺技術(shù)設(shè)計了光流與自運動估計模型,運用車輛的運動信息和場景的深度信息估計因攝像機運動產(chǎn)生的自運動光流;采用多分辨率細(xì)化的Horn算法估計場景的混合光流;對混合光流和自運動光流進行差分運算,剔除背景中靜態(tài)目標(biāo)的運動干擾。經(jīng)過一系列形態(tài)學(xué)濾波處理獲得運動目標(biāo)完整區(qū)域,依據(jù)光流的連通性對運動目標(biāo)標(biāo)號,并確定位置信息。以典型的交通場景為對象進行分析,實驗結(jié)果表明該算法能有效地檢測出動態(tài)背景下的運動目標(biāo)。
[Abstract]:In order to solve the problem of target detection when the camera and the detected target move at the same time, a moving target detection algorithm based on stereo vision and optical flow fusion is proposed. Combined with stereo vision technology, the optical flow and self-motion estimation model are designed, and the vehicle motion information and scene depth information are used to estimate the self-moving optical flow caused by camera motion. The multi-resolution thinning Horn algorithm is used to estimate the mixed optical flow of the scene, and the difference operation between the mixed optical flow and the self-moving optical flow is carried out to eliminate the moving interference of the static target in the background. After a series of morphological filtering, the complete region of the moving target is obtained, and the moving target is marked according to the connectivity of the optical flow, and the position information is determined. The typical traffic scene is analyzed. The experimental results show that the algorithm can effectively detect the moving target in dynamic background.
【作者單位】： 上海理工大學(xué)光電信息與計算機工程學(xué)院;
【基金】：國家自然科學(xué)基金(61374197) 上�？莆萍紕�(chuàng)新行動計劃資助項目(13510502600)
【分類號】：TP391.41
[Abstract]:In order to solve the problem of target detection when the camera and the detected target move at the same time, a moving target detection algorithm based on stereo vision and optical flow fusion is proposed. Combined with stereo vision technology, the optical flow and self-motion estimation model are designed, and the vehicle motion information and scene depth information are used to estimate the self-moving optical flow caused by camera motion. The multi-resolution thinning Horn algorithm is used to estimate the mixed optical flow of the scene, and the difference operation between the mixed optical flow and the self-moving optical flow is carried out to eliminate the moving interference of the static target in the background. After a series of morphological filtering, the complete region of the moving target is obtained, and the moving target is marked according to the connectivity of the optical flow, and the position information is determined. The typical traffic scene is analyzed. The experimental results show that the algorithm can effectively detect the moving target in dynamic background.
【作者單位】： 上海理工大學(xué)光電信息與計算機工程學(xué)院;
【基金】：國家自然科學(xué)基金(61374197) 上�？莆萍紕�(chuàng)新行動計劃資助項目(13510502600)
【分類號】：TP391.41
【相似文獻】
相關(guān)期刊論文 前10條
1 韓雷;王洪慶;林隱靜;;光流法在強對流天氣臨近預(yù)報中的應(yīng)用[J];北京大學(xué)學(xué)報(自然科學(xué)版);2008年05期
2 龔大墉;汪治華;楊數(shù)強;劉巖;;基于目標(biāo)的局部約束光流分析[J];重慶工學(xué)院學(xué)報(自然科學(xué)版);2009年07期
3 嚴(yán)強;黃增喜;曹麗萍;黃蓉剛;;光流法在機車安全行駛中的應(yīng)用[J];計算機應(yīng)用研究;2013年04期
4 馬鵬飛;楊金孝;;基于光流法的粒子圖像測速[J];科學(xué)技術(shù)與工程;2012年32期
5 張永亮;盧煥章;賀興華;謝耀華;;基于光流預(yù)測的直線對應(yīng)算法[J];信號處理;2010年05期
6 孫承志;熊田忠;吉順平;張家海;;基于差分的光流法在目標(biāo)檢測跟蹤中的應(yīng)用[J];機床與液壓;2010年14期
7 王，
本文編號：2490243
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2490243.html
最近更新
教材專著
