Bounding overwatch

About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.

Estimating social distance in public places for COVID-19 protocol using region CNN

Abstract: The Coronavirus disease has spread throughout the world and its fear has made people to be more cautious in public places. Since precautionary measures are the only reliable protocol to defend ourselves, social distancing is the only best approach to defend against the pandemic situation. The reproduction number i.e. R0 factor of COVID-19, can be slowed down only through the physical distancing norms. This research proposes a deep learning approach for maintaining the social distance by tracking and detecting the people present indoor and outdoor scenarios. Surveillance video is taken as the input and applied into you only look once (YOLO) V3 algorithm. The persons in the video are identified based on the segmentation algorithm present within the framework and then using Euclidean distance the image is evaluated. The bounding box algorithm helps to segregate the humans based on the minimum distance threshold. The proposed method is evaluated for images with peoples in the market, availing essential commodities and students entry inside a campus. Our proposed region-based convolutional neural network (RCNN) algorithm gives a better accuracy over the traditional models and hence the service can be implemented in general for places where social distancing is mandatory.

A Deep Learning Framework for Grocery Product Detection and Recognition

Abstract: Object detection and recognition are the most important and challenging problems in computer vision. The remarkable advancements in deep learning techniques have significantly accelerated the momentum of object detection/recognition in recent years. Meanwhile, text detection/recognition is also a critical task in computer vision and has gotten more attention from many researchers due to its wide range of applications. This work focuses on detecting and recognizing multiple retail products stacked on the shelves and off the shelves in the grocery stores by identifying the label texts. In this paper, we proposed a new framework is composed of three modules: (a) retail product detection, (b) product-text detection, (c) product-text recognition. In the first module, on-the-shelf and off-the-shelf retail products are detected using the YOLOv5 object detection algorithm. In the second module, we improve the performance of the state-of-the-art text detection algorithm by replacing the backbone network with ResNet50 + FPN and by introducing a new post-processing technique, Width Height based Bounding Box Reconstruction, to mitigate the problem of inaccurate text detection. In the final module, we used a state-of-the-art text recognition model to recognize the retail product’s text information. The YOLOv5 algorithm accurately detects both on-the-shelf and off-the-shelf grocery products from the video frames and the static images. The experimental results show that the proposed post-processing approach improves the performance of the existing methods on both regular and irregular text. The robust text detection and text recognition methods greatly support our proposed framework to recognize the on-the-shelf retail products by extracting product information such as product name, brand name, price, and expiring date. The recognized text contexts around the retail products can be used as the identifier to distinguish the product.

Non Uniform Selection of Solutions for Upper Bounding the 3-SAT Threshold

Abstract: We give a new insight into the upper bounding of the 3-SAT threshold by the first moment method. The best criteria developed so far to select the solutions to be counted discriminate among neighboring solutions on the basis of uniform information about each individual free variable. What we mean by uniform information, is information which does not depend on the solution: e.g. the number of positive/negative occurrences of the considered variable. What is new in our approach is that we use non uniform information about variables. Thus we are able to make a more precise tuning, resulting in a slight improvement on upper bounding the 3-SAT threshold for various models of formulas defined by their distributions.

Scalable Capacity Bounding Models for Wireless Networks

Abstract: The framework of network equivalence theory developed by Koetter et al. introduces a notion of channel emulation to construct noiseless networks as upper (respectively, lower) bounding models, which can be used to calculate the outer (respectively, inner) bounds for the capacity region of the original noisy network. Based on the network equivalence framework, this paper presents scalable upper and lower bounding models for wireless networks with potentially many nodes. A channel decoupling method is proposed to decompose wireless networks into decoupled multiple-access channels and broadcast channels. The upper bounding model, consisting of only point-to-point bit pipes, is constructed by first extending the one-shot upper bounding models developed by Calmon et al. and then integrating them with network equivalence tools. The lower bounding model, consisting of both point-to-point and point-to-points bit pipes, is constructed based on a two-step update of the lower bounding models to incorporate the broadcast nature of wireless transmission. The main advantages of the proposed methods are their simplicity and the fact that they can be extended easily to large networks with a complexity that grows linearly with the number of nodes. It is demonstrated that the resulting upper and lower bounds can approach the capacity in some setups.