本文關(guān)鍵詞： 目標(biāo)群 航母戰(zhàn)斗群 行為分析 行為識別 人群場景 多觀察點(diǎn)上下文 多觀察點(diǎn)統(tǒng)計(jì)直方圖 視頻描述子 從屬關(guān)系　出處：《華中科技大學(xué)》2016年博士論文　論文類型：學(xué)位論文

【摘要】：群體行為識別與分析是模式識別和計(jì)算機(jī)視覺領(lǐng)域的前沿課題,為公共場所視頻監(jiān)控、戰(zhàn)場實(shí)時(shí)分析等提供有效的技術(shù)手段。隨著計(jì)算機(jī)視覺技術(shù)的快速發(fā)展,基于圖像的目標(biāo)檢測、識別等技術(shù)日趨成熟。然而,基于視頻的技術(shù)仍需進(jìn)一步提高,特別是行為識別。群體行為識別是行為識別的一種,其場景比一般行為復(fù)雜。到目前為止,不同的目標(biāo)群體很難利用固定的算法進(jìn)行分析。相對單個(gè)目標(biāo)或多個(gè)目標(biāo),群體行為是整體行為,目標(biāo)與目標(biāo)之間的上下文關(guān)系密切。通常具有以下特點(diǎn):目標(biāo)數(shù)量較多,運(yùn)動環(huán)境復(fù)雜,速度快慢不一,密度高或相互之間遮擋嚴(yán)重等。目前,國內(nèi)外學(xué)者對該課題研究不多。雖然近幾年取得了一些階段性的成果,出現(xiàn)了一些大型數(shù)據(jù)庫,但是不同課題組研究的切入點(diǎn)不同,整體研究處于比較分散的階段。本文的研究主要集中在兩類目標(biāo)群。一是稀疏目標(biāo)群(例如航母戰(zhàn)斗群);二是稠密目標(biāo)群(例如人群)。本文以航母戰(zhàn)斗群為例研究了稀疏目標(biāo)群;以人群為例研究了稠密目標(biāo)群。針對群體目標(biāo)的特點(diǎn),本文的研究內(nèi)容如下:首先,模擬了衛(wèi)星監(jiān)視中的航母戰(zhàn)斗群航行視頻。航母戰(zhàn)斗群的數(shù)據(jù)非常寶貴,模擬航母戰(zhàn)斗群隊(duì)形變化航行的意義重大。雖然目前的衛(wèi)星技術(shù)很難支持大范圍的視頻拍攝,但是模擬視頻可以驗(yàn)證識別算法在任意時(shí)刻的有效性。為了盡可能真實(shí)模擬航母戰(zhàn)斗群的航行,本文分析了雷達(dá)偵察衛(wèi)星和光學(xué)偵察衛(wèi)星監(jiān)視航母戰(zhàn)斗群的可行性。提出利用三次Hermite插值函數(shù)規(guī)劃軍艦的軌跡,既可以保證規(guī)劃的軌跡函數(shù)二次可導(dǎo),也能很好控制隊(duì)形變化過程中艦船之間的距離,防止發(fā)生碰船事件。最后,為了增強(qiáng)模擬航行的視頻真實(shí)性,采用“谷歌地球”中的航母和軍艦照片作為軍艦?zāi)０?動態(tài)海面作為背景,沿著設(shè)置好的軌跡生成航母戰(zhàn)斗群的模擬航行視頻。其次,在假設(shè)艦船目標(biāo)已經(jīng)檢測出來的基礎(chǔ)上研究了航母戰(zhàn)斗群的隊(duì)形識別和行為分析。提出在阿基米德螺線上選取一系列觀察點(diǎn),計(jì)算每個(gè)觀察點(diǎn)與航母戰(zhàn)斗群的上下文信息,形成了多觀察點(diǎn)上下文描述子,成功解決了旋轉(zhuǎn)和尺度不變性問題。建立了概率密度函數(shù)模型,將隊(duì)形的局部信息與全局信息有效融合,增強(qiáng)了算子的描述能力。該描述子的維度與軍艦數(shù)量無關(guān),其識別性能對航母戰(zhàn)斗群的中心區(qū)域軍艦數(shù)量不敏感,符合航母戰(zhàn)斗群編隊(duì)的實(shí)際情況。提出了基于隱馬爾科夫模型的行為識別方法,并在不同的模擬視頻中驗(yàn)證了算法的有效性。針對人群檢測,本文提出了一種新的局部區(qū)域描述子——多觀察點(diǎn)統(tǒng)計(jì)直方圖。在多個(gè)觀察點(diǎn)上進(jìn)行徑向梯度變換,形成了一種局部區(qū)域的整體描述子。在不需要?dú)w一化圖像尺度大小的情況下,能統(tǒng)一描述不同尺度的人群圖像塊。最后結(jié)合了快速目標(biāo)框的方法進(jìn)行人群檢測�；谀繕�(biāo)框的方法人群檢測不需要高斯金字塔,但卻可以利用少數(shù)目標(biāo)框覆蓋大部分目標(biāo)。針對形態(tài)變化較大的人群場景,提出了一種多標(biāo)簽的分類器模型。人群行為種類繁多,類別之間關(guān)系復(fù)雜,傳統(tǒng)的分類器效率不高、效果不好。充分利用不同類別之間的從屬關(guān)系,提出了一種高效分類器模型。相比傳統(tǒng)分離器,本文的分類器具有完美的閉合解,可以同時(shí)高效處理多個(gè)類別。人群場景分類是一個(gè)多實(shí)例的問題,本文結(jié)合了深度卷積網(wǎng)絡(luò)和Fisher Vector(FV)編碼,構(gòu)建了具有時(shí)空信息的視頻描述子,高效處理了多實(shí)例問題。以上方法均在充足的數(shù)據(jù)集和實(shí)驗(yàn)下進(jìn)行了驗(yàn)證。實(shí)驗(yàn)結(jié)果表明,本文提出方法大部分結(jié)果優(yōu)于主流方法。大部分?jǐn)?shù)據(jù)集是實(shí)際拍攝的視頻數(shù)據(jù),提出的方法具有很強(qiáng)的實(shí)際應(yīng)用價(jià)值。本文的方法可以視為一些基本的技術(shù),具有相關(guān)領(lǐng)域潛在的實(shí)際應(yīng)用價(jià)值,例如,事件檢測、行為識別等。
[Abstract]:Behavior recognition and analysis of the group is a leading research field of pattern recognition and computer vision, video surveillance for public places, provide effective technical means real-time battlefield analysis. With the rapid development of computer vision technology, image target detection based on recognition technology is becoming more and more mature. However, the video technology needs to be further improved based on the special is the behavior recognition. Group behavior recognition is a kind of behavior recognition, the scene is more complex than the general behavior. So far, different target groups are difficult to analyze using the fixed algorithm. Compared with single target or multiple targets, group behavior is the overall behavior context between the target and the target is usually close. The following characteristics: a large number of target motion in complex environment, the speed of a high density or mutual occlusion seriously. At present, domestic and foreign scholars on the subject. There is not much. Although in recent years has made some achievements, there are some large databases, but the starting point of different research group, the overall research in a relatively dispersed phase. This study focused on two types of target groups. One is the sparse target groups (e.g. carrier battle group); two is the dense target group (e.g. population). The aircraft carrier battle group as an example to study the sparse target group; population as an example to study the dense target group. According to the characteristics of the target groups, the research contents of this paper are as follows: firstly, the simulation of satellite surveillance of aircraft carrier battle groups sailing video carrier battle group data. Very valuable, simulation of the aircraft carrier battle group formation changes sailing of great significance. Although the satellite technology is difficult to support a wide range of video capture, but analog video recognition algorithm can be verified at any time for effectiveness. As far as possible to simulate navigation aircraft carrier battle group, this paper analyzes the radar reconnaissance satellite and optical reconnaissance satellite surveillance aircraft carrier battle group. The feasibility of proposed using three Hermite interpolation function planning ship trajectory, which can not only ensure the planning path function can guide two times, can well control the ship formation changes in the process of distance the ship, to prevent the occurrence of touch events. Finally, in order to enhance the authenticity of the video simulation of navigation, the "Google earth" in the aircraft and warships warship photos as template, dynamic sea as background, set up along the trajectory generation of aircraft carrier battle groups sailing simulation video. Secondly, based on the ship target detection has been assumed on the study on the analysis of formation recognition and behavior. The carrier battle group selected a series of observation points in Archimedes spiral, calculated for each observation point and the aircraft carrier battle group The context information, the formation of multi observation point context descriptor is solved successfully, rotation and scale invariance. A probability density function model, local information and global information formation and effective integration, enhance the operator description ability. The number of dimensions and warships the descriptor is independent of the recognition performance is not sensitive to the number of regional center Navy aircraft carrier battle group, in accordance with the actual situation of the aircraft carrier battle group formation. Put forward the behavior recognition method based on Hidden Markov model, and verify the effectiveness of the algorithm in the analog video. According to different crowd detection, this paper proposes a new local descriptor, multiple observation points of radial histogram. The gradient transform in a plurality of observation points, forming a whole a local descriptor. Without the need of normalized image size under the condition of uniform People describe image blocks at different scales. Finally the method of fast target frame for crowd detection. Detection method of target population box does not need Gauss in Pyramid based on, but can use a box cover most of the target object. According to the morphological changes of large crowd scenes, proposed a multi label classifier model. The crowd behavior types there are categories of the relationship between the complexity of the traditional classifier, the efficiency is not high, the effect is not good. Make full use of the dependencies between different categories, this paper presents an efficient classifier model. Compared with the traditional separator, the classifier has the perfect solution, at the same time, can handle multiple categories. The crowd scene classification is a multi examples of problems, combining the convolutional network and Fisher Vector (FV) encoding, construct the video descriptors with spatial and temporal information, efficient handling of multiple instances All the above problems. The method was validated in sufficient data sets and experiments. The experimental results show that this method is better than most of the results of mainstream method. Most of the data set is the actual shooting video data, the proposed method has strong practical application value. This method can be regarded as some of the basic technology, practical related areas of potential application value, for example, event detection, behavior recognition.

【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前5條

1 孟憲民;祝利;張波;;航母戰(zhàn)斗群電子防空初探[J];艦船電子對抗;2006年01期

2 王劍飛,武文軍,彭小龍,熊平;美軍航母戰(zhàn)斗群空襲火力及其效能分析[J];情報(bào)指揮控制系統(tǒng)與仿真技術(shù);2005年01期

3 朱澤生;孫玲;;電子戰(zhàn)對遠(yuǎn)程火力突襲航母戰(zhàn)斗群戰(zhàn)法性能影響[J];艦船電子對抗;2008年06期

4 朱澤生;孫玲;;網(wǎng)絡(luò)中心聯(lián)合潛艇與遠(yuǎn)程導(dǎo)彈突襲航母戰(zhàn)法[J];指揮控制與仿真;2008年06期

5 楊繼何;許抗;王亞飛;;對航母戰(zhàn)斗群的電子進(jìn)攻方法[J];艦船電子對抗;2009年04期

相關(guān)重要報(bào)紙文章 前10條

1 時(shí)雨;美再向海灣增派兩航母戰(zhàn)斗群[N];工人日報(bào);2007年

2 早報(bào)首席評論員 魯寧;融入“海洋文明”,中國應(yīng)當(dāng)擁有航母戰(zhàn)斗群[N];東方早報(bào);2009年

3 本報(bào)特約編譯 柴志廷;中國需要三支航母戰(zhàn)斗群[N];世界報(bào);2010年

4 王雯;俄加速打造未來航母戰(zhàn)斗群[N];中國國防報(bào);2012年

5 王雯;俄新航母戰(zhàn)斗群計(jì)劃提速[N];北京日報(bào);2012年

6 本報(bào)駐馬尼拉記者 王傳軍;美航母戰(zhàn)斗群赴菲災(zāi)區(qū)意欲何為[N];光明日報(bào);2008年

7 張嶺;印度計(jì)劃建五支航母戰(zhàn)斗群[N];世界報(bào);2006年

8 本報(bào)特約撰稿 侯亞銘;航母戰(zhàn)斗群威力是這樣形成的[N];中國國防報(bào);2011年

9 張希元　倪文鑫;“夏季脈動”凸顯美軍戰(zhàn)略新動向[N];解放軍報(bào);2004年

10 新華社記者 胥金章;后勤難保障 航母先退場[N];新華每日電訊;2003年

相關(guān)博士學(xué)位論文 前1條

1 鄧春華;群體目標(biāo)識別與分析技術(shù)研究[D];華中科技大學(xué);2016年

，

本文編號：1506947