This paper addresses the problem of background modeling for foreground object detection in complex environments. A Bayesian framework that incorporates spectral, spatial, and temporal features to characterize the background appearance is proposed. Under this framework, the background is represented by the most significant and frequent features, i.e., the principal features, at each pixel. A Bayes decision rule is derived for background and foreground classification based on the statistics of principal features. Principal feature representation for both the static and dynamic background pixels is investigated. A novel learning method is proposed to adapt to both gradual and sudden "once-off" background changes. The convergence of the learning process is analyzed and a formula to select a proper learning rate is derived. Under the proposed framework, a novel algorithm for detecting foreground objects from complex environments is then established. It consists of change detection, change classification, foreground segmentation, and background maintenance. Experiments were conducted on image sequences containing targets of interest in a variety of environments, e.g., offices, public buildings, subway stations, campuses, parking lots, airports, and sidewalks. Good results of foreground detection were obtained. Quantitative evaluation and comparison with the existing method show that the proposed method provides much improved results.

Summary Colorectal cancer is a leading cause of cancer-related deaths. Mutations in the innate immune sensor AIM2 are frequently identified in patients with colorectal cancer, but how AIM2 modulates colonic tumorigenesis is unknown. Here, we found that Aim2-deficient mice were hypersusceptible to colonic tumor development. Production of inflammasome-associated cytokines and other inflammatory mediators were largely intact in Aim2-deficient mice, however, intestinal stem cells were prone to uncontrolled proliferation. Aberrant Wnt signaling expanded a population of tumor-initiating stem cells in the absence of AIM2. Susceptibility of Aim2-deficient mice to colorectal tumorigenesis was enhanced by a dysbiotic gut microbiota, which was reduced by reciprocal exchange of gut microbiota with wild-type healthy mice. These findings uncover a synergy between a specific host genetic factor and gut microbiota in determining the susceptibility to colorectal cancer. Therapeutic modulation of AIM2 expression and microbiota has the potential to prevent colorectal cancer.

No abstract

No abstract

No abstract