Abstract
With the development of the economy and society, the demand for social security and stability increases. However, traditional security systems rely too much on human resources and are affected by uncontrollable community security factors. An intelligent security monitoring system can overcome the limitations of traditional systems and save human resources, contributing to public security. To build this system, a RISC-V SoC is first designed in this paper and implemented on the Nexys-Video Artix-7 FPGA. Then, the Linux operating system is transplanted and successfully run. Meanwhile, the driver of related hardware devices is designed independently. After that, three OpenCV-based object detection models including YOLO (You Only Look Once), Haar (Haar-like features), and LBP (Local Binary Pattern) are compared, and the LBP model is chosen to design applications. Finally, the processing speed of 1.25 s per frame is realized to detect and track moving objects. To sum up, we build an intelligent security monitoring system with real-time detection, tracking, and identification functions through hardware and software collaborative design. This paper also proposes a video downsampling technique. Based on this technique, the BRAM resource usage on the hardware side is reduced by 50% and the amount of pixel data that needs to be processed on the software side is reduced by 75%. A video downsampling technology is also proposed in this paper to achieve better video display effects under limited hardware resources. It provides conditions for future function expansion and improves the models’ processing speed. Additionally, it reduces the run time of the application and improves the system performance.
Highlights
With the advent of the era of artificial intelligence, the applications of intelligent security systems [1,2,3] become more and more diverse
In order to use the advantages of RISC-V in power consumption and security and to enrich the ecological construction of RISC-V, this paper proposes an intelligent security monitoring system based on RISC-V SoC to broaden the application of RISC-V in the embedded domain
The three object detection models that are provided by OpenCV [30,31,32] are used in this paper, namely the YOLO model, the Haar model, and the LBP model
Summary
With the advent of the era of artificial intelligence, the applications of intelligent security systems [1,2,3] become more and more diverse. The object detection model [9] is exploited to record and analyze the video information, overcoming the limitation of the traditional security monitoring system with limited human resources. Among Digilent’s development board series, the Nexys-Video is an efficient tool specially designed for audio/video applications. It is equipped with a high-bandwidth external memory, three high-speed digital video ports, and a 24-bit audio codec design and has standard communications, users, and expansion peripherals. OpenCV provides a cascaded object detector for Haar models [35]. This detector is featured with high computational efficiency and fast detection speed. OpenCV provides an LBP detector that extracts the LBP feature in the picture and uses the statistical histogram of the LBP feature spectrum as a feature vector for classification and recognition
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
