scholarly journals Person Retrieval in Video Surveillance Using Deep Learning–Based Instance Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Chien-Hao Tseng ◽  
Chia-Chien Hsieh ◽  
Dah-Jing Jwo ◽  
Jyh-Horng Wu ◽  
Ruey-Kai Sheu ◽  
...  

Video surveillance systems are deployed at many places such as airports, train stations, and malls for security and monitoring purposes. However, it is laborious to search for and retrieve persons in multicamera surveillance systems, especially with cluttered backgrounds and appearance variations among multiple cameras. To solve these problems, this paper proposes a person retrieval method that extracts the attributes of a masked image using an instance segmentation module for each object of interest. It uses attributes such as color and type of clothes to describe a person. The proposed person retrieval system involves four steps: (1) using the YOLACT++ model to perform pixelwise person segmentation, (2) conducting appearance-based attribute feature extraction using a multiple convolutional neural network classifier, (3) employing a search engine with a fundamental attribute matching approach, and (4) implementing a video summarization technique to produce a temporal abstraction of retrieved objects. Experimental results show that the proposed retrieval system can achieve effective retrieval performance and provide a quick overview of retrieved content for multicamera surveillance systems.

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4419
Author(s):  
Hao Li ◽  
Tianhao Xiezhang ◽  
Cheng Yang ◽  
Lianbing Deng ◽  
Peng Yi

In the construction process of smart cities, more and more video surveillance systems have been deployed for traffic, office buildings, shopping malls, and families. Thus, the security of video surveillance systems has attracted more attention. At present, many researchers focus on how to select the region of interest (RoI) accurately and then realize privacy protection in videos by selective encryption. However, relatively few researchers focus on building a security framework by analyzing the security of a video surveillance system from the system and data life cycle. By analyzing the surveillance video protection and the attack surface of a video surveillance system in a smart city, we constructed a secure surveillance framework in this manuscript. In the secure framework, a secure video surveillance model is proposed, and a secure authentication protocol that can resist man-in-the-middle attacks (MITM) and replay attacks is implemented. For the management of the video encryption key, we introduced the Chinese remainder theorem (CRT) on the basis of group key management to provide an efficient and secure key update. In addition, we built a decryption suite based on transparent encryption to ensure the security of the decryption environment. The security analysis proved that our system can guarantee the forward and backward security of the key update. In the experiment environment, the average decryption speed of our system can reach 91.47 Mb/s, which can meet the real-time requirement of practical applications.


Author(s):  
Alex Kohn ◽  
François Bry ◽  
Alexander Manta

Studies agree that searchers are often not satisfied with the performance of current enterprise search engines. As a consequence, more scientists worldwide are actively investigating new avenues for searching to improve retrieval performance. This paper contributes to YASA (Your Adaptive Search Agent), a fully implemented and thoroughly evaluated ontology-based information retrieval system for the enterprise. A salient particularity of YASA is that large parts of the ontology are automatically filled with facts by recycling and transforming existing data. YASA offers context-based personalization, faceted navigation, as well as semantic search capabilities. YASA has been deployed and evaluated in the pharmaceutical research department of Roche, Penzberg, and results show that already semantically simple ontologies suffice to considerably improve search performance.


2021 ◽  
Author(s):  
Valentin Ion ◽  
Horia Andrei ◽  
Emil Diaconu ◽  
Mihaita Nicolae Ardeleanu ◽  
Andrei Cosmin Gheorghe

Author(s):  
Miguel Ángel CABELLOS ESPIÉRREZ

LABURPENA: Lan eremuan bideozaintzaren erabilerak ondorio garrantzitsuak dakartza funtsezko eskubideei dagokienez, esate baterako intimitateari eta datu pertsonalen babesari dagokienez. Hala eta guztiz ere, oraindik ez daukagu araudi zehatz eta espezifikorik kontrol-teknika hori lan eremuan erabiltzeari buruz. Horrek behartuta, errealitate horri araudi-esparru anitz eta generikoa aplikatzeko modua auzitegiek zehaztu behar dute, kontuan hartuta, gainera, Espainiako Konstituzioaren 18.4 artikulua alde horretatik lausoa dela. Konstituzio Auzitegiak, datuen babeserako funtsezko eskubidea aztertzean, datuen titularraren adostasuna eta titular horri eman beharreko informazioa eskubide horretan berebizikoak zirela ezarri zuen; hortik ondorioztatzen da titularraren adostasuna eta hari emandako informazioa mugatuz gero behar bezala justifikatu beharko dela. Hala ere, Konstituzio Auzitegiak, duela gutxiko jurisprudentzian, bere doktrina aldatu du. Aldaketa horrek, lan eremuan, argi eta garbi langileak informazioa jasotzeko duen eskubidea debaluatzea dakar, bere datuetatik zein lortzen ari diren jakiteari dagokionez. RESUMEN: La utilización de la videovigilancia en el ámbito laboral posee importantes implicaciones en relación con derechos fundamentales como los relativos a la intimidad y a la protección de datos personales. Pese a ello, carecemos aún de una normativa detallada y específica en relación con el uso de dicha técnica de control en el ámbito laboral, lo que obliga a que sean los tribunales los que vayan concretando la aplicación de un marco normativo plural y genérico a esa realidad, dada además la vaguedad del art. 18.4 CE. El TC, al analizar el derecho fundamental a la protección de datos, había establecido el carácter central en él del consentimiento del titular de los datos y de la información que debe dársele a éste, de donde se sigue que cualquier limitación del papel de ambos deberá estar debidamente justificada. Sin embargo, en su más reciente jurisprudencia el TC ha realizado un cambio de doctrina que supone, en el ámbito laboral, una clara devaluación del derecho a la información por parte del trabajador en relación con qué datos suyos se están obteniendo. ABSTRACT : T he use of video surveillance systems within the work sphere has major implications for fundamental rights such as privacy and data protection. Nonetheless, we still lack of a detailed and specific regulation regarding the use of that control technology within the work sphere, which obliges courts to define the application of a plural and generic normative framework to that issue, given the vagueness of art. 18.4 of the Constitution. The Constitutional Court, when analyzing the fundamental right to data protection, had settled the centralityof the consent of the data rightholder and of the information to be provided to the latter, and from this it followed that any restriction on the role of both rights should be duly justified. However, in its most recent case law the Constitutional Court has changed its doctrine which means, within the work sphere, a clear devaluation of the right of information by the employee regarding the obtained data of him/her.


Sign in / Sign up

Export Citation Format

Share Document