基于目標表觀和幾何建模的物體檢測研究及應用
發(fā)布時間：2018-08-06 08:58
【摘要】：物體檢測是計算機視覺研究領域中一個極富挑戰(zhàn)性的課題,是大量高級視覺任務的基礎。盡管經歷了數十年的研究發(fā)展,但在面對實際復雜變化場景時,物體檢測的表現仍然存在不足。作為兼具分類和定位任務的復雜系統問題,物體檢測始終在模型能力和計算代價的取舍中徘徊前進。針對一般物體檢測,本文依據識別對象的幾何變化,將目標分為結構化和非結構化目標。結構化物體檢測的核心問題是如何表達目標的幾何結構信息,如何建模結構化物體的幾何變化。針對結構化物體檢測,本文假設目標對象的幾何變化是透視變換,使用點特征集合表達目標的幾何結構,使用S-SVM分類器建模結構化物體檢測算法。本文提出預訓練和跟蹤算法進一步提高結構化物體檢測效率。實驗結果表明預訓練能提高分類器對同一類點特征的辨別力,跟蹤算法在不嚴重損失準確度的情況下能大幅提高檢測速度。非結構化物體檢測的核心問題是如何表達目標區(qū)域信息,如何將候選區(qū)域的提取與物體分類統一建模優(yōu)化。針對非結構化物體檢測,本文使用基于特征學習的數據驅動特征來表達目標區(qū)域信息,使用Faster R-CNN建模非結構化物體檢測算法。本文提出基于多層刺激的候選框融合算法進一步提高非結構化物體檢測效率。實驗結果表明多層刺激算法能進一步豐富特征抽象能力,該特征使得學習器學習出更加魯棒的分類規(guī)則。綜上所述,本文分析了結構化與非結構化的物體檢測方法,并提出相應的改進算法,提高了在特定應用場景下的物體檢測效率。
[Abstract]:Object detection is a very challenging task in the field of computer vision. It is the basis of a large number of advanced visual tasks. Despite decades of research and development, the performance of object detection still exists in the face of actual complex change scenes. As a complex system problem with both classification and location tasks, physical examination is a problem. For general object detection, this paper divides the object into structured and unstructured object according to the geometric change of the object. The core problem of structured object detection is how to express the geometric structure of the target and how to model the geometric change of the structured object. In view of structured object detection, this paper assumes that the geometric change of the target object is perspective transformation, uses the point feature set to express the geometric structure of the target, and uses the S-SVM classifier to model the structured object detection algorithm. This paper proposes a pre training and tracking algorithm to further improve the physical examination efficiency of the structuration. The experimental results show that the pre training can be proposed. The recognition ability of the high classifier to the same kind of point features, the tracking algorithm can greatly improve the detection speed when the accuracy of the loss is not serious. The core problem of the unstructured object detection is how to express the target area information, how to model the extraction of the candidate region and the object classification, and to detect the unstructured objects. The data driven feature based on feature learning is used to express the target area information, and the Faster R-CNN is used to model the unstructured object detection algorithm. In this paper, a candidate frame fusion algorithm based on multi-layer stimulation is proposed to further improve the detection efficiency of unstructured objects. The experimental results show that the multi-layer stimulation algorithm can further enrich the feature abstraction energy. This feature makes the learner learn more robust classification rules. In summary, this paper analyzes structural and unstructured object detection methods, and proposes a corresponding improvement algorithm to improve the efficiency of object detection in a specific application scene.
【學位授予單位】：浙江大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
[Abstract]:Object detection is a very challenging task in the field of computer vision. It is the basis of a large number of advanced visual tasks. Despite decades of research and development, the performance of object detection still exists in the face of actual complex change scenes. As a complex system problem with both classification and location tasks, physical examination is a problem. For general object detection, this paper divides the object into structured and unstructured object according to the geometric change of the object. The core problem of structured object detection is how to express the geometric structure of the target and how to model the geometric change of the structured object. In view of structured object detection, this paper assumes that the geometric change of the target object is perspective transformation, uses the point feature set to express the geometric structure of the target, and uses the S-SVM classifier to model the structured object detection algorithm. This paper proposes a pre training and tracking algorithm to further improve the physical examination efficiency of the structuration. The experimental results show that the pre training can be proposed. The recognition ability of the high classifier to the same kind of point features, the tracking algorithm can greatly improve the detection speed when the accuracy of the loss is not serious. The core problem of the unstructured object detection is how to express the target area information, how to model the extraction of the candidate region and the object classification, and to detect the unstructured objects. The data driven feature based on feature learning is used to express the target area information, and the Faster R-CNN is used to model the unstructured object detection algorithm. In this paper, a candidate frame fusion algorithm based on multi-layer stimulation is proposed to further improve the detection efficiency of unstructured objects. The experimental results show that the multi-layer stimulation algorithm can further enrich the feature abstraction energy. This feature makes the learner learn more robust classification rules. In summary, this paper analyzes structural and unstructured object detection methods, and proposes a corresponding improvement algorithm to improve the efficiency of object detection in a specific application scene.
【學位授予單位】：浙江大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
【相似文獻】
相關期刊論文 前10條
1 鮑培明;模糊Petri網在非結構化決策支持中的應用研究[J];計算機工程;2001年12期
2 劉晴;;昆騰創(chuàng)新歸檔解決方案減輕了主存儲上非結構化數據增長的負擔[J];計算機與網絡;2013年23期
3 繆紅;鐘華;龍昕;;元器件企業(yè)保護非結構化大數據的研究[J];電子元件與材料;2014年06期
4 王曉麗;;基于網絡的中學非結構化教育資源建設探析[J];中國教育信息化;2007年08期
5 ToddMatsler;;深耕大數據 助力平安城市智慧轉型[J];中國信息界;2013年12期
6 經有國;但斌;張旭梅;郭鋼;;基于本體的非結構化客戶需求智能解析方法[J];計算機集成制造系統;2010年05期
7 張廣泉;非結構化程序流程圖及其等價變換[J];重慶師范學院學報(自然科學版);1993年03期
8 王曉波;;非結構化數據采集和檢索技術的研究與實現[J];中國內部審計;2014年07期
9 黃遠鳴;;一種非結構化數據的多牽度分配存取實現方法[J];科技通報;2014年08期
10 劉威,武家春,廖建新,丁軼;非結構化補充業(yè)務數據中心的設計與實現[J];計算機工程與應用;2005年10期
相關會議論文 前10條
1 祝世京;陳s，
本文編號：2167206
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2167206.html
