ABSTRACT
This paper introduces the overall architecture of electronic perimeter system based-on the deep learning and its key technologies. The system adopts a microservice architecture, using deep learning algorithm services and Spring Cloud-based backend servers to implement the system architecture. Faster RCNN is used as the object detection algorithm and the processing mechanism of real-time video transmission and alarm information processing in the perimeter is introduced. Through the application of the system, the security of the perimeter is greatly improved, and to a certain extent, it has been applied to a certain extent.
- Cheng, BW; Wei, YC; (...); Huang, T. Revisiting RCNN: On Awakening the Classification Power of Faster RCNN. 2018, | COMPUTER VISION - ECCV 2018, PT 15 11219, pp.473-490.Google Scholar
- LeCun, Y; Bengio, Y and Hinton, G. Deep Learning. NATURE 521 (7553), pp.436-444, May 28, 2015.Google Scholar
- Raghunandan, A; Mohana; (...); Aradhya, HVR. Object Detection Algorithms for Video Surveillance Applications. 2018, PROCEEDINGS OF THE 2018 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), pp.563-568Google Scholar
- Mane, S and Mangale. SMoving object detection and tracking Using Convolutional Neural Networks. 2018, PROCEEDINGS OF THE 2018 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS), pp.1809-1813.Google Scholar
- Li, SS. Understanding Quality Attributes in Microservice Architecture. 2017, 24TH, ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE WORKSHOPS (APSECW), pp.9-10Google Scholar
- Hassan, S; Ali, N and Bahsoon, R. Microservice Ambients: An Architectural Meta-modelling Approach for Microservice Granularity. 2017 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE (ICSA 2017), pp.1-10, 2017.Google Scholar
Recommendations
Minimum-perimeter intersecting polygons
LATIN'10: Proceedings of the 9th Latin American conference on Theoretical InformaticsGiven a set ${\mathcal S}$ of segments in the plane, a polygon P is an intersecting polygon of ${\mathcal S}$ if every segment in ${\mathcal S}$ intersects the interior or the boundary of P. The problem MPIP of computing a minimum-perimeter intersecting ...
Conversational Recommender System Using Deep Reinforcement Learning
RecSys '22: Proceedings of the 16th ACM Conference on Recommender SystemsDeep Reinforcement Learning (DRL) uses the best of both Reinforcement Learning and Deep Learning for solving problems which cannot be addressed by them individually. Deep Reinforcement Learning has been used widely for games, robotics etc. Limited work ...
Comments