Real-time people detection based on top-view TOF camera

Author(s):  
Hongjie Xiang ◽  
Wenbiao Zhou
2021 ◽  
Author(s):  
Daniele Berardini ◽  
Adriano Mancini ◽  
Primo Zingaretti ◽  
Sara Moccia

Abstract Nowadays, video surveillance has a crucial role. Analyzing surveillance videos is, however, a time consuming and tiresome procedure. In the last years, artificial intelligence paved the way for automatic and accurate surveillance-video analysis. In parallel to the development of artificial-intelligence methodologies, edge computing is becoming an active field of research with the final goal to provide cost-effective and real time deployment of the developed methodologies. In this work, we present an edge artificial intelligence application to video surveillance. Our approach relies on a set of four IP cameras, which acquire video frames that are processed on the edge using the NVIDIA® Jetson Nano. A state-of-the-art deep-learning model, called Single Shot multibox Detector (SSD) MobileNetV2 network, is used to perform object and people detection in real-time. The proposed infrastructure obtained an inference speed of ∼10.0 Frames per Second (FPS) for each parallel video stream. These results prompt the possibility of translating our work into a real word scenario. The integration of the presented application into a wider monitoring system with a central unit could bring benefits to the overall infrastructure. Indeed our application could send only video-related high-level information to the central unit, allowing it to combine information with data coming from other sensing devices without unuseful data overload. This would ensure a fast response in case of emergency or detected anomalies. We hope this work will contribute to stimulate the research in the field of edge artificial intelligence for video surveillance.


2020 ◽  
Vol 141 ◽  
pp. 112989 ◽  
Author(s):  
José A. Paredes ◽  
Fernando J. Álvarez ◽  
Teodoro Aguilera ◽  
Fernando J. Aranda

2020 ◽  
Vol 89 (1) ◽  
pp. 10303
Author(s):  
Mustafa Anutgan ◽  
Tamila Anutgan ◽  
Ismail Atilgan

An ordinary amorphous silicon nitride-based p-i-n diode was electroformed under optimized process conditions, which led to its instant transformation to a semiconductor device with two-in-one properties: a bright visible light emitting diode and a resistive memory switching device; i.e. light emitting memory (LEM). In the present work, for a thorough understanding of the changes that occur during electroforming, SEM images and EDX analyses were performed on both top-view and cross-section of both as-deposited and electroformed diodes. It was seen from the top-view images that while the diode surface of the as-deposited diode had a smooth and homogeneous ITO top electrode, the electroformed diode exhibited a rough ITO surface. EDX analyses showed that ITO was completely removed from many point-like regions on the diode surface. Cross-sectional SEM images showed no clue of any material diffusion through the diode structure during electroforming, which was one of the suspected situations about our model. EDX results also showed no considerable increase of any of the ingredients of the ITO alloy (In, Sn or O) across the semiconductor (p-i-n) layers of the electroformed diode. In contrast to the roughened surface of the electroformed diode, the silicon-based layers of the diode below the ITO electrode seemed to be well-preserved. Real-time optical microscopy showed that the light is emitted through the regions of the diode surface where the residual ITO top electrode is present.


Author(s):  
Alejandro Morfin-Santana ◽  
Filiberto Munoz Palacios ◽  
Sergio Salazar Cruz ◽  
Ivan Gonzalez-Hernandez ◽  
Eduardo S. Espinoza Quesada ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document