本文選題：視覺注意 + 自頂向下　； 參考：《華中科技大學》2016年碩士論文

【摘要】：人在看一副圖像時,會不自覺的關注圖像中某些區(qū)域,同時忽略某些區(qū)域。這種視覺感知過程中表現(xiàn)出的選擇性是視覺注意機制作用的結果。在計算機視覺研究中,通過對視覺注意機制進行建模,可以賦予計算機在復雜環(huán)境中自動獲取人的視覺興趣區(qū)的能力。通過模擬人類視覺感知系統(tǒng),研究人員提出了基于特征整合的視覺注意計算框架。在此框架下衍生出了多種視覺注意模型。本文詳細分析Itti和Judd兩種具有較大影響力的顯著性視覺注意模型。其中Itti模型通過整合多種低層次特征生成顯著圖作為圖像區(qū)域受關注程度的預測。該方法忽略視覺注意過程中知識、任務、偏好等因素的影響。Judd模型整合高層次語義特征作為知識的引入方式。雖然取得了較好的效果,但是啟發(fā)式特征的設計和計算較復雜,擴展性不強。本文在現(xiàn)有視覺注意模型基礎上重點研究了兩個問題:(1)如何通過學習方法獲取視覺注意特征。(2)如何在特征整合框架下進行層次特征整合。首先,本文通過訓練卷積神經網獲取像素級、對象級、語義級特征。然后,基于學習獲取的特征,提出了一種整合層次特征的視覺注意模型,重點在于利用對象屬性信息進行高層次特征整合,該方法有效彌補了已有模型在引入先驗知識方面的不足。最后,針對提出的視覺注意模型,設計了一種層次知識引導的注意焦點轉移方法。實驗表明,新模型充分利用了先驗知識,在多個數據集上測試均獲得了較好的實驗結果。
[Abstract]:When you look at an image, you will unconsciously focus on some areas of the image, while ignoring some areas. The selectivity of visual perception is the result of visual attention mechanism. In the research of computer vision, by modeling the visual attention mechanism, the computer can automatically acquire the region of visual interest in complex environment. By simulating human visual perception systems, researchers proposed a visual attention computing framework based on feature integration. Under this framework, several visual attention models are derived. Two significant visual attention models, Itti and Judd, are analyzed in detail. The Itti model uses a variety of low-level features to generate salient maps as a prediction of the attention level of the image region. This method ignores the influence of knowledge, task, preference and other factors in visual attention. Judd model integrates high-level semantic features as a way to introduce knowledge. Although good results have been obtained, the design and calculation of heuristic features are more complicated and less extensible. Based on the existing visual attention models, this paper focuses on two problems: (1) how to acquire visual attention features through learning methods; (2) how to integrate hierarchical features in the framework of feature integration. Firstly, the features of pixel level, object level and semantic level are obtained by training convolution neural network. Then, based on the features acquired by learning, a visual attention model integrating hierarchical features is proposed, which focuses on the high-level feature integration using object attribute information. This method effectively makes up for the deficiency of the existing models in introducing prior knowledge. Finally, aiming at the proposed visual attention model, a method of attention focus shift based on hierarchical knowledge guidance is designed. Experiments show that the new model makes full use of prior knowledge, and good experimental results are obtained by testing on multiple data sets.
【學位授予單位】：華中科技大學
【學位級別】：碩士
【學位授予年份】：2016
【分類號】：TP391.41

【參考文獻】

相關期刊論文 前2條

1 暴林超;蔡超;肖潔;周成平;;一種用于復雜目標感知的視覺注意模型[J];計算機工程;2011年13期

2 肖潔;蔡超;丁明躍;;一種圖斑特征引導的感知分組視覺注意模型[J];航空學報;2010年11期

，

本文編號：2052293