本文選題：超像素分割　切入點(diǎn)：時(shí)空上下文　出處：《甘肅政法學(xué)院》2017年碩士論文

【摘要】：現(xiàn)今,隨著天網(wǎng)全方位的建立,圖像和視頻已成為公安破案的重要依據(jù),計(jì)算機(jī)視覺(jué)中的圖像處理,視頻的動(dòng)態(tài)追蹤也成為世界公安技術(shù)領(lǐng)域相關(guān)專家研究的熱點(diǎn)問(wèn)題,人工智能、機(jī)器學(xué)習(xí)的飛速發(fā)展,也使得計(jì)算機(jī)在針對(duì)圖像、視頻的分析獲取得了快速發(fā)展。在道路監(jiān)控視頻中,往往由于一些樹(shù)木,車輛或其他因素導(dǎo)致追蹤目標(biāo)被遮擋,計(jì)算機(jī)無(wú)法完成連續(xù)追蹤,只能依靠人力去追蹤,這就大大浪費(fèi)了警力和時(shí)間,如何能夠在遮擋或半遮擋的情況下,實(shí)現(xiàn)目標(biāo)的快速動(dòng)態(tài)追蹤,是本文研究的重點(diǎn),也是國(guó)內(nèi)外的一個(gè)研究熱點(diǎn)。同時(shí),為了解決快速追蹤的問(wèn)題,本文采用了圖像處理技術(shù)中的超像素分割技術(shù),將像素級(jí)轉(zhuǎn)化成超像素級(jí)問(wèn)題,實(shí)現(xiàn)了快速追蹤。由于圖像分割的質(zhì)量決定了后續(xù)問(wèn)題的處理,所以在超像素分割算法的選擇上也成為一個(gè)重要因素。本文利用融合了超像素分割技術(shù)的時(shí)空上下文先驗(yàn)?zāi)Ｐ蛠?lái)解決半遮擋問(wèn)題。文章首先介紹現(xiàn)階段國(guó)內(nèi)外對(duì)于視頻目標(biāo)追蹤技術(shù)的發(fā)展情況,提出研究的背景及意義,并提出利用基于熵率的超像素分割算法融合時(shí)空上下文先驗(yàn)?zāi)Ｐ瓦M(jìn)行視頻目標(biāo)的動(dòng)態(tài)追蹤,在實(shí)踐中,通常采用低層特征處理圖像視頻,而很少采用中層視覺(jué)特征,本文則是利用了中層視覺(jué)特征,構(gòu)建上下文模型,求解置信圖,獲得目標(biāo)位置在新一幀的最大概率。首先建立時(shí)空上下文先驗(yàn)?zāi)Ｐ?利用貝葉斯框架來(lái)做目標(biāo)模型構(gòu)建,以及目標(biāo)與背景鄰近的子區(qū)域的關(guān)系,通過(guò)時(shí)空上下文模型確定目標(biāo)位置的置信圖,并在目標(biāo)區(qū)域采用均勻采樣點(diǎn)追蹤器,來(lái)完成當(dāng)前幀的目標(biāo)位置確定。然后,使用超像素分割算法進(jìn)行分割,利用像素位置距離超像素中心點(diǎn)的遠(yuǎn)近,算出所求目標(biāo)在每個(gè)像素位置出現(xiàn)的概率,將置信圖轉(zhuǎn)化成像素級(jí)置信圖,估計(jì)目標(biāo)在所尋求區(qū)域的每個(gè)位置出現(xiàn)的概率問(wèn)題,即概率最大的即為目標(biāo)新一幀所出現(xiàn)的位置。最后,利用捷尚公司的測(cè)試視頻和標(biāo)準(zhǔn)視頻庫(kù)中的視頻,對(duì)本文的算法進(jìn)行實(shí)驗(yàn)驗(yàn)證,驗(yàn)證了算法的正確性和有效性的同時(shí),提出了算法分析及對(duì)運(yùn)算結(jié)果的評(píng)價(jià),最后對(duì)本文涉及的圖像處理及視頻跟蹤技術(shù)的應(yīng)用進(jìn)行了總結(jié)展望。
[Abstract]:Nowadays, with the establishment of Skynet, images and videos have become an important basis for police to solve cases. Image processing and video dynamic tracking in computer vision have also become hot issues in the field of public security technology in the world. With the rapid development of artificial intelligence and machine learning, computer analysis of images and videos has also developed rapidly. In road surveillance videos, tracking targets are often blocked because of trees, vehicles or other factors. The computer can not complete continuous tracking, it can only rely on manpower to track, which greatly wasted the police force and time. How to achieve fast dynamic tracking of targets in occlusion or semi-occlusion, is the focus of this paper. At the same time, in order to solve the problem of fast tracking, this paper adopts the super-pixel segmentation technology in the image processing technology, which transforms the pixel level into the super-pixel level problem. Fast tracking is realized. Because the quality of image segmentation determines the processing of subsequent problems, Therefore, the selection of hyperpixel segmentation algorithm is also an important factor. In this paper, a spatio-temporal contextual priori model combining hyperpixel segmentation technology is used to solve the semi-occlusion problem. The development of video target tracking technology, The background and significance of the research are presented, and a hyper pixel segmentation algorithm based on entropy rate is proposed to fuse the temporal and spatial context prior model for dynamic tracking of video objects. In practice, low level features are usually used to process video images. However, the middle vision feature is seldom used. In this paper, the middle level visual feature is used to construct the context model, to solve the confidence chart, and to obtain the maximum probability of the target position in the new frame. Firstly, the temporal and spatial context priori model is established. The Bayesian framework is used to construct the target model and the relation between the target and the sub-region adjacent to the background. The confidence chart of the target location is determined by the spatio-temporal context model, and the uniform sampling point tracker is used in the target area. To determine the target position of the current frame. Then, using the hyperpixel segmentation algorithm, the probability of the target appearing at each pixel position is calculated by using the distance from the pixel position to the center of the super-pixel. The confidence chart is transformed into a pixel level confidence chart to estimate the probability problem of the target at each location in the region sought, that is, the position where the maximum probability is the occurrence of the new frame of the target. Finally, By using the test video and the video in the standard video library, the algorithm of this paper is verified by experiments, and the correctness and validity of the algorithm are verified. At the same time, the analysis of the algorithm and the evaluation of the operation result are presented. Finally, the application of image processing and video tracking technology in this paper is summarized and prospected.
【學(xué)位授予單位】：甘肅政法學(xué)院
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：D918

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前7條

1 李鐳;基于先驗(yàn)?zāi)Ｐ偷男〔ㄩ撝等ピ胨惴ǖ膽?yīng)用研究[D];電子科技大學(xué);2014年

2 畢述s，

本文編號(hào)：1689156