• 한국실내디자인학회논문집
• /
• 제24권6호
• /
• pp.145-153
• /
• 2015

For this research with the objects of spaces in two department stores which can be referred to as representative facility of commercial space, observation test has carried out to estimate how much visitors rivet their eyes to the display of shops. In addition, to find out what effect the difference among the department types has on the selective attention to space element, the observation time was applied as a medium for estimation. The followings are the result from analyzing the observation frequency and the observation intensity feature of each section where the characteristics of design could be found at attention. First, both images of A and B had concentrative dominant-observation at left shops. In case of Image A, Customers began to observe the right shops very attentively after 25 seconds, and with Image B, the attentive observation at right and left took place alternatively after 35 seconds. In other words, regardless of the characteristics of shop displays, the left shops were observed first while in case of the observation after the early and middle time-frame the characteristics of shops were found to have effects on observation. Second, the normal observation showed some difference among attention sections over time while on the whole both images of A and B had the same highly attentive observation at the middle space. Accordingly, it could be concluded that the middle space was playing a faithful role as background for commercial spaces. Third, the ignorant observation, which is the opposite to the attentive observation, was found different between the images of A and B. When the ignorant observation is considered to have intentionality, it will be possible to set up the display which may attract the attention aggressively by the process of figuring out the characteristics of ignored shops.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• 전자공학회논문지SC
• /
• 제44권1호
• /
• pp.50-58
• /
• 2007

본 논문에서는 로봇이 태스크와 관련된 부분에 시각 집중을 하도록 하기 위해서 기존의 상향식 주목 알고리즘을 확장한 질의 기반 시각 집중 알고리즘을 제안한다. 질의 기반 시각 집중 알고리즘은 로봇이 수행 할 태스크와 관련한 물체를 질의하면 그 물체의 속성을 분석하여 여러 종류의 도드라짐(Conspicuity) 영상 지도에 적용될 가중치 값을 작성한다. 그리고 가중치를 이용하여 도드라짐 영상 지도를을 합성한 Saliency 영상 지도를 작성하여 기존의 주목 알고리즘과 비교 평가를 수행하였다. 여기서는 일예로서 질의 물체의 속성을 색으로 사용하였다.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.