本文選題：多目標跟蹤 + 識別輔助的跟蹤��； 參考：《中國圖象圖形學(xué)報》2017年03期

【摘要】：目的目標的長距離跟蹤一直是視頻監(jiān)控中最具挑戰(zhàn)性的任務(wù)之一�，F(xiàn)有的目標跟蹤方法在存在遮擋、目標消失再出現(xiàn)等情況下往往會丟失目標,無法進行持續(xù)有效的跟蹤。一方面目標消失后再次出現(xiàn)時,將其作為新的目標進行跟蹤的做法顯然不符合實際需求;另一方面,在跟蹤過程中當相似的目標出現(xiàn)時,也很容易誤導(dǎo)跟蹤器把該相似對象當成跟蹤目標,從而導(dǎo)致跟蹤失敗。為此,提出一種基于目標識別輔助的跟蹤算法來解決這個問題。方法將跟蹤問題轉(zhuǎn)化為尋找?guī)g檢測到的目標之間對應(yīng)關(guān)系問題,從而在目標消失再現(xiàn)后,采用深度學(xué)習(xí)網(wǎng)絡(luò)實現(xiàn)有效的軌跡恢復(fù),改善長距離跟蹤效果,并在一定程度上避免相似目標的干擾。結(jié)果通過在標準數(shù)據(jù)集上與同類算法進行對比實驗,本文算法在目標受到遮擋、交叉運動、消失再現(xiàn)的情況下能夠有效地恢復(fù)其跟蹤軌跡,改善跟蹤效果,從而可以對多個目標進行持續(xù)有效的跟蹤。結(jié)論本文創(chuàng)新性地提出了一種結(jié)合基于深度學(xué)習(xí)的目標識別輔助的跟蹤算法,實驗結(jié)果證明了該方法對遮擋重現(xiàn)后的目標能夠有效的恢復(fù)跟蹤軌跡,適用在監(jiān)控視頻中對多個目標進行持續(xù)跟蹤。
[Abstract]:Target long-range tracking is one of the most challenging tasks in video surveillance. The existing methods of target tracking often lose the target in the presence of occlusion and disappear and reappear, so they can not be tracked continuously and effectively. On the one hand, tracking a target as a new target when it reappears after disappearing is clearly not in line with actual needs; on the other hand, when a similar target appears in the tracking process, It is also easy to mislead the tracker to treat the similar object as a tracking target, resulting in tracking failure. Therefore, a tracking algorithm based on target recognition assistance is proposed to solve this problem. Methods the tracking problem is transformed into the problem of finding the corresponding relationship between the detected targets between frames. After the target vanishes and reappears, the depth learning network is used to achieve effective trajectory recovery and to improve the effect of long distance tracking. And to a certain extent to avoid the interference of similar targets. Results by comparing with the similar algorithms on the standard data set, the algorithm can recover the tracking track effectively and improve the tracking effect when the target is occluded, cross moving, disappear and reappear. Thus, multiple targets can be tracked continuously and effectively. Conclusion in this paper, a target recognition aided tracking algorithm based on depth learning is proposed. The experimental results show that this method can effectively recover the track of the target after occlusion reconstruction. Suitable for continuous tracking of multiple targets in surveillance video.
【作者單位】： 浙江工商大學(xué)計算機與信息工程學(xué)院;北京正安維視科技股份有限公司;蘭州大學(xué)信息科學(xué)與工程學(xué)院;
【基金】：國家自然科學(xué)基金項目(61472362,61379075) 浙江省自然科學(xué)基金項目(LZ16F020002,LY14F020001) 公益技術(shù)研究社會發(fā)展項目(2015C33081)~~
【分類號】：TP391.41
，

本文編號：1883270