A framework for semantic people description in multi-camera surveillance systems

Zhou, Zhi; Wang, Yue; Teoh, Eam Khwang

doi:10.1016/j.imavis.2015.11.009

Cited by 6 publications

(3 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining several soft biometrics modalities, especially clothing, has proven important in improving subject recognition rates [3,14] and can be estimated for surveillance tracking and search [9,44].…”

Section: Pedestrian Re-identificationmentioning

confidence: 99%

“…Further approaches extract global and body soft biometrics from multi‐camera environments [35], depth images [36], or most recently, by applying state‐of‐the‐art convolutional neural networks to still images [15, 37]. Combining several soft biometrics modalities, especially clothing, has proven important in improving subject recognition rates [27, 38] and can be estimated for surveillance tracking and search [39, 40].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Analysing comparative soft biometrics from crowdsourced annotations

2016

View full text Add to dashboard Cite

Soft biometrics enable human description and identification from low quality surveillance footage. This paper premises the design, collection and analysis of a novel crowdsourced dataset of comparative soft biometric body annotations, obtained from a richly diverse set of human annotators. We annotate 100 subject images to provide a coherent, in-depth appraisal of the collected annotations and inferred relative labels. The dataset includes gender as a comparative trait and we find that comparative labels characteristically contain additional discriminative information over traditional categorical annotations. Using our pragmatic dataset, we perform semantic recognition by inferring relative biometric signatures using a RankSVM algorithm. This demonstrates a practical scenario, reproducing responses from a video surveillance operator searching for an individual. The approach can reliably return the correct match in the the top 7% of results with 10 comparisons, or top 13% of results using just 5 sets of subject comparisons.

show abstract

Section: Pedestrian Re-identificationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Analysing comparative soft biometrics from crowdsourced annotations

2016

View full text Add to dashboard Cite

show abstract

“…The primary driver to implement video surveillance systems is the increasing concern of safety [1][2][3]. To this end, these systems are endowed with corresponding functionalities, such as object tracking [4,5], face recognition [6][7][8], personal profiling [9], behavioral analysis [10,11], and accident analysis [1]. Video surveillance systems have become an indispensable part of modern safety management of public and private sectors and the installation of these systems shows no sign of stopping.…”

Section: Introductionmentioning

confidence: 99%

Can Video Surveillance Systems Promote the Perception of Safety? Evidence from Surveys on Residents in Beijing, China

et al. 2019

View full text Add to dashboard Cite

Ubiquitous utilization of video surveillance systems is supposed to promote safety, yet whether these systems improve the residents’ perception of safety is unknown. Moreover, the factors that affect the perception of safety are also unclear. We seek to fill these knowledge gaps via a survey-based study, which aims at evaluating the impact of video surveillance systems on perceived safety from crimes and accidents and on behavioral preferences, as well as the attitudes towards such systems. A total of 1080 residents in Beijing, China are validly surveyed, and the surveys returned are exploited for univariate analysis and regression analysis. The analysis results indicate that female respondents are more accustomed to adopt video surveillance systems, as they feel safer and more comfortable with the existence of surveillance systems. Higher levels of education, greater length of residency, and richer knowledge of surveillance systems tend to increase the perception of safety, while age and monthly income act negatively. The effects of these factors should be considered during the implementation of video surveillance systems and recommendations are given to facilitate the adoption of such systems.

show abstract