【摘要】：隨著深度學習技術(shù)在計算機視覺領(lǐng)域取得的廣泛成功,當前基于卷積神經(jīng)網(wǎng)絡(luò)(CNN)的目標檢測技術(shù)發(fā)展迅速。作為計算機視覺領(lǐng)域的研究熱點之一,目標檢測在視頻監(jiān)控、工業(yè)機器人自動化抓取等方向中擁有廣泛的應(yīng)用前景。在自動化抓取應(yīng)用中,實際場景通常包含大量的小目標物體,同時機器人抓取需要具備準確的目標姿態(tài)估計�，F(xiàn)有基于CNN的目標檢測算法通常針對大目標物體設(shè)計,對小目標的定位能力不足,同時無法估計目標的姿態(tài)變化。針對上述問題,本文從機器人抓取的實際應(yīng)用出發(fā),分別引入二階的多層深度特征融合結(jié)構(gòu)提升小目標的檢測性能,以及在CNN架構(gòu)中加入角度預(yù)測層,通過多任務(wù)學習的方法同時提升目標定位和姿態(tài)估計的準確性。針對小目標檢測問題,本文首先基于Hyper-Column特征融合算法,將圖像分類中常用的二階特征引入到目標檢測框架中,并實現(xiàn)了兩種包含位置信息的二階特征融合方案:一種是基于特征非線性變換的二階響應(yīng)變換模型(SORT),一種是基于特征核方法的二階核融合的模型(HIHCA)。VOC數(shù)據(jù)集上的實驗結(jié)果表明,兩種基于Hyper-Column的二階特征融合方法均可以有效提升系統(tǒng)的性能;為了進一步利用底層CNN特征更好的定位能力,我們將最新的特征分層表征TDM模型和二階信息相結(jié)合,提出了基于二階TDM特征融合的目標檢測模型。在VOC數(shù)據(jù)集上的結(jié)果驗證了本文提出模型的有效性。針對目標的姿態(tài)估計問題,我們通過引入角度預(yù)測層,將剛性物體的姿態(tài)估計子任務(wù)加入到目標檢測中,通過多任務(wù)學習的方式實現(xiàn)端對端的模型訓練。在PASCAL 3D數(shù)據(jù)集上的實驗結(jié)果表明,本文提出的多任務(wù)學習策略可以有效提升姿態(tài)估計和目標檢測的性能。最后,本文將提出的兩種模型組成一個完整的目標檢測系統(tǒng),并通過機器人目標抓取應(yīng)用驗證算法在實際場景中的性能。
[Abstract]:With the success of deep learning technology in the field of computer vision, the target detection technology based on convolutional neural network (CNN) is developing rapidly. As one of the research hotspots in the field of computer vision, target detection has a wide application prospect in video surveillance, automatic capture of industrial robots and so on. In the application of automatic capture, the actual scene usually contains a large number of small target objects, and robot capture needs accurate target attitude estimation. The existing target detection algorithms based on CNN are usually designed for large target objects, but the localization ability of small targets is insufficient, and the attitude change of the target can not be estimated at the same time. Aiming at the above problems, this paper introduces a second-order multi-layer depth feature fusion structure to improve the detection performance of small targets, and adds an angle prediction layer to the CNN architecture, starting from the practical application of robot capture. The accuracy of target location and attitude estimation is improved by multitask learning. Aiming at the problem of small target detection, based on the Hyper-Column feature fusion algorithm, the second order features commonly used in image classification are introduced into the target detection framework. Two second-order feature fusion schemes are implemented: one is the second-order response transformation model based on the feature nonlinear transformation (SORT),) and the other is the second-order kernel fusion model (HIHCA). VOC) based on the feature kernel method. Two second-order feature fusion methods based on Hyper-Column can effectively improve the performance of the system. In order to further utilize the lower CNN features and better localization ability, we combine the latest feature stratified representation TDM model with second-order information. A target detection model based on second order TDM feature fusion is proposed. The results on the VOC dataset verify the validity of the proposed model. In order to solve the problem of target attitude estimation, the attitude estimation subtask of rigid object is added to the target detection by introducing the angle prediction layer, and the end-to-end model training is realized by multi-task learning. Experimental results on PASCAL 3D dataset show that the proposed multi-task learning strategy can effectively improve the performance of attitude estimation and target detection. Finally, the two models proposed in this paper constitute a complete target detection system, and verify the performance of the algorithm in the actual scene by robot target capture.
【學位授予單位】：哈爾濱工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前1條

1 羅霄,任勇,山秀明;基于Python的混合語言編程及其實現(xiàn)[J];計算機應(yīng)用與軟件;2004年12期

，

本文編號：2147976