Detecting and reading text from natural images is a hard computer vision task that is central to a variety of emerging applications. Related problems like document character recognition have been widely studied by computer vision and machine learning researchers and are virtually solved for practical applications like reading handwritten digits. Reliably recognizing characters in more complex scenes like photographs, however, is far more difficult: the best existing methods lag well behind human performance on the same tasks. In this paper we attack the problem of recognizing digits in a real application using unsupervised feature learning methods: reading house numbers from street level photos. To this end, we introduce a new benchmark dataset for research use containing over 600,000 labeled digits cropped from Street View images. We then demonstrate the difficulty of recognizing these digits when the problem is approached with hand-designed features. Finally, we employ variants of two recently proposed unsupervised feature learning methods and find that they are convincingly superior on our benchmarks.

/pdf/reading-digits-in-natural-images-with-unsupervised-feature-3ckuq1665o.pdf

Reading Digits in Natural Images with Unsupervised Feature Learning

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

IEEE Transactions on Pattern Analysis and Machine Intelligence

/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.

nuScenes: A multimodal dataset for autonomous driving

Temperature control is the key element during medicine storage. Pharmacies sell some medical products which are kept in fridges. The opening and closing of the fridge while taking some medicine makes the outside hot air enter the fridge, which will increase the inner fridge temperature. When the frequency of opening and closing of the fridge is increased, the temperature may go beyond the allowed storage temperature range. In this paper, we are proposing a model with the help of machine learning that will be used in multiple chambers fridges to keep indicating the time remaining for the inner temperature to go beyond the allowed range, and if the time is short, the system will propose to the pharmacist not to open that particular room and proposes a room that has enough time slots (time to reach the upper limit temperature). By using training data got from a thermoelectric cooler-based fridge, we constructed a multiple linear regression model that can predict the required time for a given room to reach the cut-off temperature in case that room is opened. The built model was evaluated using the coefficient of determination R2 and is found to be 77%, and then it can be used to develop a multiple room smart fridge for efficiently storing highly sensitive medical products.

/pdf/a-data-driven-predictive-machine-learning-model-for-3547ldlx0k.pdf

A Data-Driven Predictive Machine Learning Model for Efficiently Storing Temperature-Sensitive Medical Products, Such as Vaccines: Case Study: Pharmacies in Rwanda.

Traditional radio planning tools present a steep learning curve. We present BotRf, a Telegram Bot that facilitates the process by guiding non-experts in assessing the feasibility of radio links. Built on open source tools, BotRf can run on any smartphone or PC using Telegram. Running it on a smartphone has the added value that the Bot can leverage the internal GPS to capture the current coordinates. BotRf can be used in low bandwidth environments as the generated data traffic is very limited. We present an example of its use in Venezuela.

/pdf/radio-link-planning-made-easy-with-a-telegram-bot-4p83lfux0z.pdf

Radio Link Planning Made Easy with a Telegram Bot

http://users.ictp.it/~pub_off/preprints-sources/2007/IC2007062P.pdf

Rural wireless networking in developing countries: ictp contribution

Spectrum sensing’s inability to provide maximum protection to primary users operating in television white spaces summarizes the technical challenges associated with it. Building upon “WhiteNet”, a white space network management platform for campus connectivity, this paper proposes design principles that can be incorporated in a white space identification system based on a cooperative spectrum sensing model that both minimizes the probability of causing interference to primary users due to false negatives and reduces false positives thereby increasing the amount of white spaces identified. Real-world indoor measurements of a TV transmitter signal were used to evaluate the proposed principles. The results reveal the relevance of using these design principles in white space networking using the emerging White-Fi protocol.

https://riverpublishers.com/journal/journal_articles/RP_Journal_2245-800X_331.pdf

Improving Spectrum Sensing as a Method for White Space Identification through Design Principles

Low power wide area network (LPWAN) technologies are becoming prominent in the era of the Internet of Things. In this context, LoRa long range technology emerges as a good solution thanks to its property of providing long-range along with low power although with limited bandwidth. In this paper, we focus on the use of a LoRa network for time synchronization among various nodes, to support message transmission and critical data sharing in a correct real-time manner. When providing a reliable collaborative service, clock synchronization is required, for example to apply AI solutions in IoT. In this paper, we evaluate different methodologies based on LoRa network time synchronization using commodity low cost hardware so that our solution could be adopted even in low operating expenditures or rural contexts.

Marco Zennaro

Papers

A Data-Driven Predictive Machine Learning Model for Efficiently Storing Temperature-Sensitive Medical Products, Such as Vaccines: Case Study: Pharmacies in Rwanda.

Radio Link Planning Made Easy with a Telegram Bot

Rural wireless networking in developing countries: ictp contribution

Improving Spectrum Sensing as a Method for White Space Identification through Design Principles

On Time Synchronization of LoRaWAN Based IoT Devices for Enhanced Event Correlation