With the increasing demand of autonomous machines, pixel-wise semantic segmentation for visual scene understanding needs to be not only accurate but also efficient for any potential real-time applications. In this paper, we propose CABiNet (Context Aggregated Bi-lateral Network), a dual branch convolutional neural network (CNN), with significantly lower computational costs as compared to the state-of-the-art, while maintaining a competitive prediction accuracy. Building upon the existing multi-branch architectures for high-speed semantic segmentation, we design a cheap high resolution branch for effective spatial detailing and a context branch with light-weight versions of global aggregation and local distribution blocks, potent to capture both long-range and local contextual dependencies required for accurate semantic segmentation, with low computational overheads. Specifically, we achieve 76.6% and 75.9% mIOU on Cityscapes validation and test sets respectively, at 76 FPS on an NVIDIA RTX 2080Ti and 8 FPS on a Jetson Xavier NX.

Setting up a virtual machine (VM) in the cloud is a time-consuming task. Typically, VMs are created from so called VM images, a kind of blueprints used to configure and create a VM. However, to create a VM image manually might be very time-consuming, especially if the VM has to meet certain security benchmarks. In this paper, we present VM2 (Virtual Machine Vending Machine), a tool for creation of VM images and testing them wrt. security benchmarks as well as easy sharing the secure images. Our analysis demonstrated a significant reduction in security issues in hardened images created by VM2 in comparison with corresponding publicly available images. Moreover, our tool provided better results wrt. CIS benchmarks in comparison with the corresponding images commercially offered by CIS.

As one of the key problems in both remote sensing and computer vision, video semantic segmentation has been attracting increasing amounts of attention. Using video segmentation technique for Unmanned Aerial Vehicle (UAV) data processing is also a popular application. Previous methods extended single image segmentation approaches to multiple frames. The temporal dependencies are ignored in these methods. This paper proposes a novel segmentation method to solve this problem. Combining the fully convolutional networks (FCN) and the Convolution Long Short Term Memory (Conv-LSTM) together, we segment the sequence of the video frames instead of segmenting each individual frame separately. FCN serves as the frame-based segmentation method. Conv-LSTM makes use of the temporal information between consecutive frames. Experimental results show the superiority of this method especially in some classes compared to the single image segmentation model using video dataset from UAV.