http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
히스토그램과 가중치 맵을 이용한 배경 영역 움직임 추정에 관한 연구
공경보 Pohang University of Science and Technology 2017 국내석사
This thesis present a compressed-domain global motion estimation (GME) algorithm that detects global motion change without using an iterative process. Conventional GME algorithms based on the gradient descent and least square approaches are usually accurate and powerful, but are inaccurate in various rate of outliers. Also, these algorithms use an iterative approach, which has a high computational load. To robust the rate of outliers and speed up the GME, this thesis proposes a non-iterative algorithm that exploits an outlier rejection mask and wight map. In simulations the proposed algorithm had highest estimation accuracy and had fastest processing time.
공경보 포항공과대학교 일반대학원 2020 국내박사
Recently, deep neural networks have shown exceptional performances in several computer vision applications. However, deep learning has two main limitations for use in the industry: high complexity and vulnerability against noisy labels, also known as erroneous labels. In this dissertation, I study on improving robustness and efficiency of deep neural networks in classification and image enhancement applications. Firstly, a novel criteria is proposed to robustly train deep neural networks with noisy labels. If the labels are dominantly corrupted by some classes (these noisy samples are called dominant noisy labeled samples), the network learns dominant noisy labeled samples rapidly via content-aware optimization and they cause memorization (reduce generalization) in the deep neural network. To mitigate memorization of noisy labels, algorithm with proposed criteria penalizes dominant noisy labeled samples intensively through inner product of class-wise penalty labels and their prediction confidences, which indicate the probability of being assigned to each class. By averaging prediction confidences for the each observed label, I obtain suitable penalty labels that have high values if the labels are largely corrupted by some classes. Additionally, the penalty label is compensated using weight to make it same for learning speed per class, and it is updated using temporal ensembling to enhance the accuracy. The proposed criteria can be easily combined with the algorithms of loss correction and hybrid categories through a simple modification to improve learning performance. Secondly, multi-task learning based deep neural network is proposed to train various image processing operators efficiently. For real-time image processing, the proposed algorithm takes a joint upsampling approach through bilateral guided upsampling. For multi-task learning, the overall network is based on an encoder–decoder architecture, which consists of encoding, processing, and decoding components, in which the encoding and decoding components are shared by all the image processing operators. In the processing component, a semantic guidance map, which contains processing information for each image processing operator, is estimated using simple linear shifts of the shared deep features. Through these components, the proposed algorithm requires an increase of only 5% in the number of parameters to add another image processing operator and achieves faster and higher performance than that of deep-learning-based joint upsampling methods in local image processing as well as global image processing.