《物联网图像识别》由会员分享，可在线阅读，更多相关《物联网图像识别（30页珍藏版）》请在金锄头文库上搜索。
1、Mid Sweden University The Department of Information Technology and Media (ITM) Author: Patrik Rnnqvist E-mail address: paro0902student.miun.se Study programme: Computer Science, 180 hp Examiner: Ulf Jennehag, Ulf.Jennehagmiun.se Tutor: Stefan Forsstrm, Stefan.Forsstrommiun.se Scope: 4 870 words incl
2、usive of appendices Date: 2013-03-01 B.Sc. Thesis within Computer Science, 15 points Surveillance Applications Image Recognition on the Internet of Things Patrik Rnnqvist Surveillance Applications - Image Recognition on the Internet of Things Patrik Rnnqvist Abstract 2013-03-01 ii Abstract This is a
3、 B.Sc. thesis within the Computer Science programme at the Mid Sweden University. The purpose of this project has been to investigate the possibility of using image based surveillance in smart applications on the Internet-of-Things. The goals involved investigating relevant technologies and designin
4、g, implementing and evaluating an applica- tion that can perform image recognition. A number of image recognition techniques have been investigated and the use of color histograms has been chosen for its simplicity and low resource requirement. The main source of study material has been the Internet
5、. The solution has been developed in the Java programming language, for use on the Android operating system and using the MediaSense platform for communica- tion. It consists of a camera application that produces image data and a monitor application that performs image recognition and handles user i
6、nteraction. To evaluate the solution a number of tests have been per- formed and its pros and cons have been identified. The results show that the solution can differentiate between simple colored stick figures in a controlled environment. Variables such as lighting and the background are significan
7、t. The application can reliably send images from the cam- era to the monitor at a rate of one image every four seconds. The possi- bility of using streaming video instead of images has been investigated but found to be difficult under the given circumstances. It has been concluded that while the sol
8、ution cannot differentiate between actual people it has shown that image based surveillance is possible on the IoT and the goals of this project have been satisfied. The results were ex- pected and hold little newsworthiness. Suggested future work involves improvements to the MediaSense platform and
9、 infrastructure for pro- cessing and storing data. Surveillance Applications - Image Recognition on the Internet of Things Patrik Rnnqvist Table of Contents 2013-03-01 iii Table of Contents Abstract . ii Table of Contents . iii Terminology v 1 Introduction 1 1.1 Background and problem motivation 1 1
10、.2 Overall aim . 1 1.3 Concrete and verifiable goals 2 1.4 Scope . 2 1.5 Report overview 2 2 Theory 3 2.1 Image recognition 3 2.1.1 Edge detection . 3 2.1.2 Artificial Neural Networks . 4 2.1.3 Color histogram 5 2.2 Internet of Things 5 2.2.1 MediaSense 5 3 Methodology 6 3.1 Related technologies . 6
11、 3.2 Design and implementation . 6 3.3 Evaluation . 7 3.4 Streaming video . 7 4 Implementation . 8 4.1 Overview 8 4.2 Camera application . 9 4.3 Monitor application 9 4.4 Example interaction 10 4.5 Third party libraries 11 5 Results . 12 5.1 Functionality 12 5.1.1 Streaming video 13 5.2 Image recogn
12、ition 14 5.3 Network performance 15 5.4 Screenshots . 16 Surveillance Applications - Image Recognition on the Internet of Things Patrik Rnnqvist Table of Contents 2013-03-01 iv 6 Conclusions 18 6.1 Goals 18 6.1.1 Related technologies 18 6.1.2 Design and implementation 18 6.1.3 Evaluation 19 6.1.4 St
13、reaming video 19 6.2 Discussion . 20 6.2.1 Ethical considerations 20 6.3 Future work 21 References 22 Appendix A: Source code . 24 Appendix B: Reproduction of test results . 25 Surveillance Applications - Image Recognition on the Internet of Things Patrik Rnnqvist Terminology 2013-03-01 v Terminolog
14、y ANN Artificial Neural Network GNU GNUs Not Unix GPS Global Positioning System ID Identification IDE Integrated Development Environment IoT Internet-of-Things IP Internet Protocol kB Kilobyte (1000 bytes) RGB Red, Green, Blue SDK Software Development Kit UCI Universal Context Identifier Surveillanc
15、e Applications - Image Recognition on the Internet of Things Patrik Rnnqvist 1 Introduction 2013-03-01 1 1 Introduction This project is a B.Sc. thesis within the Computer Science programme at the Mid Sweden University. This section describes the background, purpose, scope and concrete goal of the pr
16、oject. 1.1 Background and problem motivation The introduction of smart mobile phones has given rise to a large mar- ket penetration of context-aware applications. Smart mobile phones carry many sensors and actuators that can be used in such programs. The Internet-of-Things (IoT) architecture refers to the idea that physical objects, such as smart mobile phones, can be uniquely identified and represented in an Internet-like structure, that applications can change their b
