【摘要】：視覺跟蹤中,高效魯棒的特征表達(dá)是解決復(fù)雜環(huán)境下跟蹤漂移問題的關(guān)鍵。該文針對(duì)深層網(wǎng)絡(luò)預(yù)訓(xùn)練復(fù)雜費(fèi)時(shí)及單網(wǎng)絡(luò)跟蹤易漂移的問題,在粒子濾波框架下,提出一種基于自適應(yīng)深度稀疏網(wǎng)絡(luò)的在線跟蹤算法。該算法利用Re LU激活函數(shù),針對(duì)不同類型目標(biāo)構(gòu)建了一種具有自適應(yīng)選擇性的深度稀疏網(wǎng)絡(luò)結(jié)構(gòu),僅通過有限標(biāo)簽樣本的在線訓(xùn)練,就可得到魯棒的跟蹤網(wǎng)絡(luò)。實(shí)驗(yàn)數(shù)據(jù)表明:與當(dāng)前主流的跟蹤算法相比,該算法的平均跟蹤成功率和精度均為最好,且與同樣基于深度學(xué)習(xí)的DLT算法相比分別提高了20.64%和17.72%。在光照變化、相似背景等復(fù)雜環(huán)境下,該算法表現(xiàn)出了良好的魯棒性,能夠有效地解決跟蹤漂移問題。
[Abstract]:In visual tracking, efficient and robust feature representation is the key to solve the problem of tracking drift in complex environment. Aiming at the complex and time-consuming pre-training of deep network and the easy drift of single network tracking, this paper proposes an online tracking algorithm based on adaptive deep sparse network under the framework of particle filter. Using the Re LU activation function, the algorithm constructs a kind of self-adaptive and selective deep sparse network structure for different types of targets. The robust tracking network can be obtained only by the online training of finite tag samples. The experimental data show that the average tracking success rate and accuracy of the algorithm are the best compared with the current mainstream tracking algorithms, and the DLT algorithm based on the same depth learning is increased by 20.64% and 17.72% respectively. In complex environments such as illumination variation and similar background, the proposed algorithm is robust and can effectively solve the drift tracking problem.
【作者單位】： 空軍工程大學(xué)信息與導(dǎo)航學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(61473309) 陜西省自然科學(xué)基礎(chǔ)研究計(jì)劃項(xiàng)目(2015JM6269,2016JM6050)~~
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 程健,曾以亮;IPv6在產(chǎn)品特性在線跟蹤中的應(yīng)用[J];機(jī)械與電子;2004年07期

，

本文編號(hào)：2263851