• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.149-151
• /
• 2014

주의(attention)를 어떻게 할당하는가는 정신물리학뿐만 아니라, 컴퓨터 시각과정을 모델링하는데 중요한 주제 중 하나이다. 기존 연구는 saliency와 같은 활성화 값에 의해서 주의탐사 순위가 결정된다. 본 논문에서는 주의탐사과정을 병렬처리를 통한 활성화 값 추출과정과 순차적 처리를 통한 공간적 전략과정으로 구분하였다. 단서패러다임에 기초한 계산모형을 이용하여, 실제 인간의 수행결과를 AUC와 Levenshtein 척도를 이용하여 비교하였다. Fixation point 비교에서는 인간과 활성화를 기반으로 한 계산모형의 수행은 높은 상관성을 가지고 있었다. 주의궤적 혹은 scanpath 분석에서는 활성화기반 전략보다는 공간적 전략 모형이 더 높은 유사성을 보였다. 이는 주의탐사과정이 병렬처리과정을 통해 얻어진 saliency에 의해서만 결정되는 것이 아니라, 목표물간의 근접성 등의 공간적 전략을 통해 순차적 (sequential) 경로가 생성됨을 의미한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4976-4994
• /
• 2018

The diffusion-based salient object detection methods have shown excellent detection results and more efficient computation in recent years. However, the current diffusion-based salient object detection methods still have disadvantage of detecting the object appearing at the image boundaries and different scales. To address the above mentioned issues, this paper proposes a multi-scale diffusion-based salient object detection algorithm with background and objectness seeds. In specific, the image is firstly over-segmented at several scales. Secondly, the background and objectness saliency of each superpixel is then calculated and fused in each scale. Thirdly, manifold ranking method is chosen to propagate the Bayessian fusion of background and objectness saliency to the whole image. Finally, the pixel-level saliency map is constructed by weighted summation of saliency values under different scales. We evaluate our salient object detection algorithm with other 24 state-of-the-art methods on four public benchmark datasets, i.e., ASD, SED1, SED2 and SOD. The results show that the proposed method performs favorably against 24 state-of-the-art salient object detection approaches in term of popular measures of PR curve and F-measure. And the visual comparison results also show that our method highlights the salient objects more effectively.

• Journal of Sensor Science and Technology
• /
• v.10 no.1
• /
• pp.52-61
• /
• 2001

We propose a new saccadic eye movement system with visual selective attention. Saliency map models generate the scan pathways in a natural scene, of which the output makes an attended location. Saccadic eye movement model is used for producing the target trajectories to move the attended locations very rapidly. To categorize human saccadic eye movement, saccadic eye movement model was divided into three parts, each of which was then individually modeled using different neural networks to reflect a principal functionality of brain structures related with the saccadic eye movement in our brain. Based on the proposed saliency map models and the saccadic eye movement model, an active vision system using a CCD type camera and BLDC motor was developed and demonstrated with experimental results.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.137-151
• /
• 2014

This paper proposes a method of detecting object of interest(OOI) in general natural images. OOI is subjectively estimated by human in images. The vision of human, in general, might focus on OOI. As the first step for automatic detection of OOI, candidate regions of OOI are detected by using a saliency map based on the human visual perception. A saliency map locates an approximate OOI, but there is a problem that they are not accurately segmented. In order to address this problem, in the second step, an exact object region is automatically detected by combining graph-based image segmentation and skeletonization. In this paper, we calculate the precision, recall and accuracy to compare the performance of the proposed method to existing methods. In experimental results, the proposed method has achieved better performance than existing methods by reducing the problems such as under detection and over detection.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.306-308
• /
• 2006

We propose an attention based object recognition system, to recognize object fast and robustly. For this we calculate visual stimulus degrees and make saliency maps. Through this map we find a strongly attentive part of image by stimulus degrees, where local features are extracted to recognize objects.

• The Journal of the Korea Contents Association
• /
• v.5 no.6
• /
• pp.87-96
• /
• 2005

In this paper, a selective visual attention module based on motion stimuli is introduced for the purpose of detecting ROI(region of interest) or FOA(focus of attention) in motion pictures. Analysis of motion fields in our approach is in direct contrast to some of the previous studies of selective visual attention module. Motion that presents temporal visual saliency in an aspect between two successive frames is analyzed based on psychological studies in 'DORF(double opponent receptive fields)' and 'NF(noise filtration)' in MT(middle temporal cortex). Analyzed results are integrated based on the theory of 'motion integration' in MT to obtain a single conspicuous region. Experiments through a human subjective evaluation showed generally accepted results.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.217-225
• /
• 2018

Different eye-heights due to individuals' body heights may cause different sensory experiences against the same visual scene, eventually leading to their longer-term psycho-social and developmental individual differences. Accordingly, the present study compared sensory properties of photographs for the same scene taken from two different camera-heights (i.e., eye-heights). Two sets of photographs were taken in parallel from two cameras attached to a different height on the same pedestrian's body. Analysis of the photographs revealed that both the levels of visual saliency and complexity were greater for the photographs taken from the high eye-height than those from the low eye-height. The results indicate a possible difference in sensory properties of visual scenes perceived from two different heights, potentially exposing taller individuals to richer and more diverse sensory experiences than shorter individuals.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.3
• /
• pp.1-6
• /
• 2007

Anticipation effect has been used as a traditional skill to enhance the dynamic motion of the traditional 2D animation. Basically, anticipation means the action of opposite direction which performs before the real action step. In this paper, we propose the perception-based video anticipation method to guide a user's visual attention to the important region. Using the image based attention map, we calculate the visual attention region and then combine this map with temporal saliency of video. We apply the anticipation effect in these saliency regions using the blur kernel. Using our method, we can generate the dynamic video motion which has attentive guidance.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.4
• /
• pp.145-151
• /
• 2021

In this paper, we propose a novel visualization technique to explain the predictions of deep neural networks. We use knowledge distillation (KD) to identify the interior of a black-box model for which we know only inputs and outputs. The information of the black box model will be transferred to a white box model that we aim to create through the KD. The white box model will learn the representation of the black-box model. Second, the white-box model generates attention maps for each of its layers using Grad-CAM. Then we combine the attention maps of different layers using the pixel-wise summation to generate a final saliency map that contains information from all layers of the model. The experiments show that the proposed technique found important layers and explained which part of the input is important. Saliency maps generated by the proposed technique performed better than those of Grad-CAM in deletion game.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.33-34
• /
• 2016

본 논문에서는 HVS(human visual system)의 특성을 고려한 새로운 스케일러블 코딩방법을 제안한다. 제안된 방법은 먼저 영상 내에서 관심영역(saliency map)을 찾고 관심영역을 제외한 부분에 에지 보존 필터를 적용한다. 그 영상은 정해진 양자 파라미터 값으로 인코딩 되어 제안된 코딩 시스템의 베이스 층(base layer)이 된다. 기존 스케일러블 코딩 표준에서의 베이스 층과 다르게 본 논문의 베이스 층은 관심 있는 중요영역(foreground)을 보존하고 또한 배경(background)의 에지 성분도 보존한다. 기본 층이 전송되면 개선층(enhancement layer)은 원 영상과 복원된 베이스 층 영상간의 차분 영상에서 관심영역 순으로 보내진다. 실험은 HEVC 를 바탕으로 수행되었고 스케일러블 코딩 표준인 SHVC 와 관심영역에서 비교를 했을 때 제안된 알고리즘이 더 높은 PSNR 을 가지는 것을 확인하였다. 또한 전체적으로 지각적인 품질(perceptual quality) 또한 향상되었음을 확인하였다.