几个未建成作品及启示

笔者从回顾未建成博物馆和文化中心工程案例入手,分析当代中国建筑师所面临的复杂市场环境,进而提出思考和启示。     

基于纯几何学线特征匹配的点线结合匹配算法

为了解决传统匹配算法在强光照变化或者高动态范围(HDR)环境下的匹配不准确,在欠点环境下提取特征过少的问题,引入基于纯几何学的线特征匹配算法并融合性能优越的点特征匹配算法。在保证算法实时性与拥有足够数量匹配对的前提下,使得算法对于光照变化有较好的鲁棒性,同时提高匹配的准确率,满足诸如视觉里程计(VO)之类的实时应用。实验表明,该算法在满足实时应用要求的前提下,匹配精度以及对于光照变换的鲁棒性都有了明显的提升。     

A new distortion measure for motion estimation in motion-compensated hybrid video coding

In the video coding standards MPEG-x and H.26x, a motion-compensated prediction technique is used for enhancing the coding performance of bitrate reduction or peak signal to noise ratio (PSNR) improvement. This technique takes advantage of the correlation between consecutive frames in the time domain, which is relatively higher than that between adjacent blocks in the spatial domain. In order to utilize the correlation between consecutive frames, the conventional video coding standards have used the motion estimation (ME) and compensation technique, where the Sum of the Absolute Differences (SAD) is usually used as the distortion measure. The ME estimates the reference block that could minimize the residual signal between the current and reference blocks. However, the SAD is not appropriate to the specific sequences that have global or local illumination changes. In addition, the high-resolution video sequences have higher spatial correlation than the low-resolution video sequences in general. Therefore, a new distortion measure that can consider spatial and temporal correlation simultaneously may be helpful to enhance the coding performance. The proposed distortion measure searches for a reference block that minimizes the motion-compensated residual signal when the DC-component is predicted. In our proposed algorithm, the maximum BD-rate improvement is up to 13.6% for illumination-changed video sequences, and the average BD-rate improvement is 6.6% for various high-resolution video sequences in the baseline profile.     

PIAFusion: A progressive infrared and visible image fusion network based on illumination aware

Infrared and visible image fusion aims to synthesize a single fused image containing salient targets and abundant texture details even under extreme illumination conditions. However, existing image fusion algorithms fail to take the illumination factor into account in the modeling process. In this paper, we propose a progressive image fusion network based on illumination-aware, termed as PIAFusion, which adaptively maintains the intensity distribution of salient targets and preserves texture information in the background. Specifically, we design an illumination-aware sub-network to estimate the illumination distribution and calculate the illumination probability. Moreover, we utilize the illumination probability to construct an illumination-aware loss to guide the training of the fusion network. The cross-modality differential aware fusion module and halfway fusion strategy completely integrate common and complementary information under the constraint of illumination-aware loss. In addition, a new benchmark dataset for infrared and visible image fusion, i.e., Multi-Spectral Road Scenarios (available at https://github.com/Linfeng-Tang/MSRS), is released to support network training and comprehensive evaluation. Extensive experiments demonstrate the superiority of our method over state-of-the-art alternatives in terms of target maintenance and texture preservation. Particularly, our progressive fusion framework could round-the-clock integrate meaningful information from source images according to illumination conditions. Furthermore, the application to semantic segmentation demonstrates the potential of our PIAFusion for high-level vision tasks. Our codes will be available at https://github.com/Linfeng-Tang/PIAFusion.     

An illumination,expression, and noise invariant gender classifier using two-directional 2DPCA on real Gabor space

This work investigates a framework for gender classification which is invariant to illumination, expression, and noise. It utilizes 2D Gabor filter along with two-directional 2DPCA. Gabor filter gives the real Gabor space which contains crucial face information and prohibits the illumination, expression, and deformation to a certain extent. The real Gabor space is high dimensional to represent face images. To select the most discriminate feature set from the real Gabor space, 2DPCA in horizontal and vertical directions is used. The proposed scheme is evaluated through a number of well-known face image databases. The system yields classification rate of 98.18%, 96.61%, 96.15%, 93.33%, and 88.34% for FERET, FIE A, AR, Indian Face, and LFW, respectively. In the presence of illumination, expression, and noise, the system gives more than 90% accuracy for all databases except LFW. The system does so with reduced features which make it suitable for real life applications.     

Degradation by ultra-violet light and its mechanism in organic solar cells

We experimentally investigate the optimum illumination wavelength range and the degradation mechanism by the ultra-violet (UV) light for small-molecule organic solar cells (OSCs) using various long-pass filters with different cutoff wavelengths λ_c. The OSC structure consists of an indium–tin–oxide (ITO, anode)/copper phthalocyanine (CuPc, donor)/fullerene (acceptor)/bathocuproine (buffer)/Ag (cathode). The initial power conversion efficiency η_p is not affected by the use of the long-pass filter with λ_c < 400 nm. As λ_c increases above 400 nm, the initial η_p decreases significantly accompanied by a significant decrease in the short-circuit current, since the total amount of light energy absorbed in the OSC is decreased. The degradation of the OSC is investigated by repeating 30 s cycles, each consisting of 3 s of illumination followed by 27 s in the dark. The curve of the current J_L vs voltage V under illumination becomes strongly S-shaped at the 100th illumination cycle for λ_c < 400 nm, showing degradation. In contrast, for λ_c > 400 nm, no distinct degradation appears. Thus, the origin of the degradation is revealed to be UV light with wavelengths less than 400 nm. The degradation mechanism is attributed to the decrease in carrier transport efficiency at the interface between ITO and CuPc film. Reorganization of the CuPc crystal structure occurs in the near-surface region on ITO due probably to the heat generated by the UV light. This would deteriorate the electrical contact at the interface, resulting in an increase in series resistance there.     

Face recognition across illumination

Illumination variation on images of faces is one of the most difficult problems in face recognition systems. The performance of a self-organizing map-based face recognition system is highly degraded when the illumination in test images differs from that of the training images. Illumination normalization is a way to solve this problem. Both global and local image enhancement methods are studied in this article. A local histogram equalization method strongly improves the recognition accuracy of the CMU-PIE face database. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007     

A new segmentation method for phase change thermography sequence

A new segmentation method for image sequence is proposed in order to get the isotherm from phase change thermography sequence (PCTS). Firstly, the PCTS is transformed into a series of synthesized images by compression and conversion, so the isotherm extraction can be transformed into the segmentation of a series of synthesized images. Secondly, a virtual illumination model is constructed to eliminate the glisten of the aerocraft model. In order to get the parameters of virtual illumination model, a coordination-optimization method is employed and all parameters are obtained according to the similarity constraint. Finally, the proving isotherms are gained after the threshold coefficients are compensated. The eventual results demonstrate the efficiency of the proposed segmentation method.     

环球网图象搜索引擎研究综述

提出了建立一个ＷＷＷ图象搜索引擎的方案，搜索引擎在Ｉｎｔｅｒｎｅｔ上浏览主页，对遇到的图象进行特征计算，抽取出索引信息，存储索引向量，根据图象内容进行相似图象的查找。分析了颜色直方图、边缘方向直方图、纹理分析和形状不变性等基于图象内容查询的技术，并对ＷＷＷ图象搜索引擎的发展作出了预测。     

Spatial Directional Radiance Caching

We present a new approach for accelerated global illumination computation in scenes with glossy surfaces. Our algorithm combines sparse illumination computation used in the radiance caching algorithm with BRDF importance sampling. To make this approach feasible, we extend the idea of lazy illumination evaluation, used in the caching approaches, from the spatial to the directional domain. Using importance sampling allows us to apply caching not only on low-gloss but also on shiny materials with high-frequency BRDFs, for which the radiance caching algorithm breaks down.