Simulating shadow interactions between real and virtual objects is important for augmented reality (AR), in which accurately and efficiently detecting real shadows from live videos is a crucial step. Most of the existing methods are capable of processing only scenes captured under a fixed viewpoint. In contrast, this article proposes a new framework for shadow detection in live outdoor videos captured under moving viewpoints. The framework splits each frame into a tracked region, which is the region tracked from the previous video frame through optical flow analysis, and an emerging region, which is newly introduced into the scene due to the moving viewpoint. The framework subsequently extracts features based on the intensity profiles surrounding the boundaries of candidate shadow regions. These features are then utilized to both correct erroneous shadow boundaries for the tracked region and to detect shadow boundaries for the emerging region by a Bayesian learning module. To remove spurious shadows, spatial layout constraints are further considered for emerging regions. The experimental results demonstrate that the proposed framework outperforms the state-of-the-art shadow tracking and detection algorithms on a variety of challenging cases in real time, including shadows on backgrounds with complex textures, nonplanar shadows, fast-moving shadows with changing typologies, and shadows cast by nonrigid objects. The quantitative experiments show that our method outperforms the best existing method, achieving a 33.3% increase in the average Fmeasure on a self-collected database. Coupled with an image-based shadow-casting method, the proposed framework generates realistic shadow interaction results. This capability will be particularly beneficial for supporting AR applications.
Augmented Reality , Algorithms , Bayes Theorem , Computer Graphics
BACKGROUND: According to the global cancer burden data released in 2020, breast cancer (BC) has become the most common cancer in the world. Similar to those of other cancers, the present methods used in clinic for diagnosing early BC are invasive, inaccurate, and insensitive. Hence, new non-invasive methods capable of early diagnosis are needed. METHODS: We applied next-generation sequencing and analyzed the messenger RNA (mRNA) profiles of plasma extracellular vesicles (EVs) derived from 14 BC patients and 6 patients with benign breast lesions. We used 3 regression models, namely support vector machine (SVM), linear discriminate analysis (LDA), and logistic regression (LR), to develop classifiers for use in making predictive BC diagnoses; and used 259 plasma samples, including those obtained from 144 patients with BC, 72 patients with benign breast lesions, and 43 healthy women, which were divided into training groups and validation groups to verify their performances as classifiers by quantitative reverse transcription polymerase chain reaction (RT-qPCR). The area under the curve (AUC) and accuracy, sensitivity, and specificity of the classifiers were cross-validated with the leave-1-out cross-validation (LOOCV) method. RESULTS: Among all combinations assessed with the 3 different regression models, an 8-mRNA combination, named EXOBmRNA, exhibited high performance [accuracy =71.9% and AUC =0.718, 95% confidence interval (CI): 0.652 to 0.784] in the training cohort after LOOCV was performed, showing the largest AUC in the SVM model. The mRNAs in EXOBmRNA were HLA-DRB1, HAVCR1, ENPEP, TIMP1, CD36, MARCKS, DAB2, and CXCL14. In the validation cohort, the AUC of EXOBmRNA was 0.737 (95% CI: 0.636 to 0.837). In addition, gene function and pathway analyses revealed that different levels of gene expression were associated with cancer. CONCLUSIONS: We developed a high-performing predictive classifiers including 8 mRNAs from plasma extracellular vesicles for diagnosing breast cancer.
We propose an automatic framework to recover the illumination of indoor scenes based on a single RGB-D image. Unlike previous works, our method can recover spatially varying illumination without using any lighting capturing devices or HDR information. The recovered illumination can produce realistic rendering results. To model the geometry of the visible and invisible parts of scenes corresponding to the input RGB-D image, we assume that all objects shown in the image are located in a box with six faces and build a planar-based geometry model based on the input depth map. We then present a confidence-scoring based strategy to separate the light sources from the highlight areas. The positions of light sources both in and out of the camera's view are calculated based on the classification result and the recovered geometry model. Finally, an iterative procedure is proposed to calculate the colors of light sources and the materials in the scene. In addition, a data-driven method is used to set constraints on the light source intensities. Using the estimated light sources and geometry model, environment maps at different points in the scene are generated that can model the spatial variance of illumination. The experimental results demonstrate the validity and flexibility of our approach.
