Smart environments are environments where digital devices are connected to each other over the Internet and operate in sync. Security is of paramount importance in such environments. This paper addresses aspects of authorized access and intruder detection for smart environments. Proposed is PiBase, an Internet of Things (IoT)-based app that aids in detecting intruders and providing security. The hardware for the application consists of a Raspberry Pi, a PIR motion sensor to detect motion from infrared radiation in the environment, an Android mobile phone and a camera. The software for the application is written in Java, Python and NodeJS. The PIR sensor and Pi camera module connected to the Raspberry Pi aid in detecting human intrusion. Machine learning algorithms, namely Haar-feature based cascade classifiers and Linear Binary Pattern Histograms (LBPH), are used for face detection and face recognition, respectively. The app lets the user create a list of non-intruders and anyone that is not on the list is identified as an intruder. The app alerts the user only in the event of an intrusion by using the Google Firebase Cloud Messaging service to trigger a notification to the app. The user may choose to add the detected intruder to the list of non-intruders through the app to avoid further detections as intruder. Face detection by the Haar Cascade algorithm yields a recall of 94.6%. Thus, the system is both highly effective and relatively low cost.
翻译:智能环境是数字设备在互联网上相互连接并同步运行的环境。 安全在这种环境中至关重要。 本文涉及授权访问和入侵探测智能环境中的智能环境。 提议采用PiBase, 一种基于事物的互联网应用程序, 帮助侦测入侵者和提供安全。 应用程序硬件包括一个“ 树莓皮” 、 一个用于探测环境中红外辐射运动的PIR运动传感器、 一个 Android移动电话和一个相机。 应用程序的软件以 Java、 Python 和 NodeJS 书写。 PIR 传感器和 Pi 相机模块, 与 Raspberry Pi 相连接, 帮助探测人类入侵。 机器学习算法, 即基于星际级分类的“ 速度” 分类器和线性双线性双线性平底图( LBPHPH), 分别用来检测和面部识别和面部识别。 应用程序允许用户创建一份非触摸底者名单, 被确认为“ 入侵者” 。 应用程序仅提醒用户在入侵时, 使用Goo Firb Cload Mess Mess Messimal 等 检测系统, 可以选择一个不甚高压的系统, 。 。 测试系统, 。 。 通过测试系统进一步检测成本。 。 。 。 。 。 将一个不测算取一个高额 。