Perception Of Spatial Information Research Articles

B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery

Deep learning (DL) shows remarkable performance in extracting buildings from high resolution remote sensing images. However, how to improve the performance of DL based methods, especially the perception of spatial information, is worth further study. For this purpose, we proposed a building extraction network with feature highlighting, global awareness, and cross level information fusion (B-FGC-Net). The residual learning and spatial attention unit are introduced in the encoder of the B-FGC-Net, which simplifies the training of deep convolutional neural networks and highlights the spatial information representation of features. The global feature information awareness module is added to capture multiscale contextual information and integrate the global semantic information. The cross level feature recalibration module is used to bridge the semantic gap between low and high level features to complete the effective fusion of cross level information. The performance of the proposed method was tested on two public building datasets and compared with classical methods, such as UNet, LinkNet, and SegNet. Experimental results demonstrate that B-FGC-Net exhibits improved profitability of accurate extraction and information integration for both small and large scale buildings. The IoU scores of B-FGC-Net on WHU and INRIA Building datasets are 90.04% and 79.31%, respectively. B-FGC-Net is an effective and recommended method for extracting buildings from high resolution remote sensing images.

Viewing Direction Based LSB Data Hiding in 360° Videos

In this paper, we propose a viewing direction based least significant bit (LSB) data hiding method for 360° videos. The distributions of viewing direction frequency for latitude and longitude are used to control the amount of secret data to be hidden at the latitude, longitude, or both latitude and longitude of 360° videos. Normalized Gaussian mixture models mimicking the viewing behavior of humans are formulated to define data hiding weight functions for latitude, longitude, and both latitude and longitude. On this basis, analytical expressions for the capacity offered by the proposed method to hide secret data in 360° cover videos are derived. Numerical results for the capacity using different numbers of bit planes and popular 360° video resolutions for data hiding are provided. The fidelity of the proposed method is assessed in terms of the peak signal-to-noise ratio (PSNR), weighted-to-spherically uniform PSNR (WS-PSNR), and non-content-based perceptual PSNR (NCP-PSNR). The experimental results illustrate that NCP-PSNR returns the highest fidelity because it gives lower weights to the impact of LSB data hiding on fidelity outside the front regions near the equator. The visual quality of the proposed method as perceived by humans is assessed using the structural similarity (SSIM) index and the non-content-based perceptual SSIM (NCP-SSIM) index. The experimental results show that both SSIM-based metrics are able to account for the spatial perceptual information of different scenes while the PSNR-based fidelity metrics cannot exploit this information. Furthermore, NCP-SSIM reflects much better the impact of the proposed method on visual quality with respect to viewing directions compared to SSIM.

항공관제 전문성 수준에 따른 시각정보 판독과 미래정보 예측 차이

Many studies have shown that having perception of spatial information is important for air traffic control officer (ATCO) since it helps them understand the current situation and predict the situation it leads to. However, little or no research has been done to investigate if there is any difference at the levels of expertise in perceiving spatial information and predicting a prospective situation. This study investigates the difference between expert and novice ATCO groups in how accurately each group of ATCO perceive spatial information such as position, altitude, speed, and flying direction, and predicting such information they will encounter shortly. In completing a task to watch the movement of airplanes displayed on the computer monitor as a blip, the participants were asked to predict the position, speed, and the altitude of the aircraft in a minute by marking on the sector map. The results show that the expert group performed better in accuracy and had tendency to overestimate on position and altitude; however, no significant difference was found between the two groups in terms of reading a flying direction. Therefore reading a flying direction may not be a reliable indicator to judge expertise of ATCO. But the expert group shows better predicting performance by perceiving spatial information such as airplane`s position and altitude with feeling on time. The study suggests that it is important to enhance perceptive skills in ATCO training in improving their expertise in predicting accuracy traffic situation, preventing from air collision, and improving productivity for more efficient air traffic flow. A further study on the relationship between the perception of spatial information and the sense of time in predicting future information and effectiveness as an independent factor would contribute to providing more insights into expertise of ATCOs.

A Method for Evaluating QoE of Live Streaming Services

This paper presents a novel method which can provide accurate real-time evaluation for Quality of Experience (QoE) of live streaming services. First, we use the modified Analytic Hierarchy Process (AHP) to build a QoE model which is mainly based on video quality and network transmission quality in live streaming services. Then, for video quality, we take into account the unique multi-resolution feature of Internet live streaming videos and design a video quality assessment algorithm mainly based on bitrate, temporal perceptual information (TI) and spatial perceptual information (SI). This algorithm removes the interference of multi-resolution and has a good correlation with subjective perception. And for network transmission quality, we design another assessment algorithm based on buffering time and frequency. Finally, by using the QoE model and the assessment algorithms, we can build a real-time QoE monitoring and evaluation system for live streaming services.

Représentations et pratiques du réseau urbain chez des conducteurs professionnels

Road users have to overcome many problems when moving around an unfamiliar environment. In this paper we examine factors that are intrinsic to drivers such as their knowledge of the environment and their related spatial representations. We wish to demonstrate, with the help of experimental studies, how three groups of professional drivers represent their work environment and to describe the strategies used when moving about in it. We also wish to propose a fast and efficient training program to facilitate the insertion of professional drivers into a new urban environment. The analysis of the cognitive processes involved suggested strong similarities in reference points and sequential strategies between the three groups despite varying professional objectives. Each group established a different network. The most efficient drivers had received a theoretical and practical training related to the work network. Those that had not received specific training were equally efficient if they had the possibility of learning about the environment in several ways. We conclude that the network is acquired in two steps : 1) the perception of spatial information (roads, reference points, etc.) and 2) the integration of this acquired information within the network. These two steps must be repeated regularly. Moving slowly while acquiring this information seems to be a determining factor in the elaboration of an efficient mental representation of the environment.