Semi-supervised intelligent surveillance system for secure environments

Fookes, Clinton; Denman, Simon; Lakemond, Ruan; Ryan, David; Sridharan, Sridha; Piccardi, Massimo

doi:10.1109/isie.2010.5636922

Cited by 31 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many studies have been made towards the application of this system. For example, the development of home surveillance application and smart surveillance for generic purpose (Ali 2016;Antoniou & Angelov 2016), monitor displaced activity detection system (Babutain et al 2015) and smart surveillance system for secure environment from fight, riots of violence protests, panic behavior and excitement (Fookes et al 2010). However, the most challenging part in developing smart surveillance system is to develop the event detection capability so that the smart surveillance system can identify what is happening and take mitigation action accordingly.…”

Section: Literature Reviewmentioning

confidence: 99%

Suspicious Loitering Detection from Annotated CCTV Feed Using CEP Based Approach

Shahad¹,

Ibrahim²,

Xian³

et al. 2018

JKUKM

View full text Add to dashboard Cite

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Suspicious Loitering Detection from Annotated CCTV Feed Using CEP Based Approach

Shahad¹,

Ibrahim²,

Xian³

et al. 2018

JKUKM

View full text Add to dashboard Cite

show abstract

“…As the demand for public security progressively increases, so does the demand for more robust and ubiquitous automated surveillance systems [1]. There is a growing interest in being able to detect and identify individuals in unconstrained environments without direct interaction with the subjects.…”

Section: Introductionmentioning

confidence: 99%

Efficient real-time face detection for high resolution surveillance applications

Cheng

Lakemond

Fookes

et al. 2012

2012 6th International Conference on Signal Processing and Communication Systems

View full text Add to dashboard Cite

This paper presents an efficient face detection method suitable for real-time surveillance applications. Improved efficiency is achieved by constraining the search window of an AdaBoost face detector to pre-selected regions. Firstly, the proposed method takes a sparse grid of sample pixels from the image to reduce whole image scan time. A fusion of foreground segmentation and skin colour segmentation is then used to select candidate face regions. Finally, a classifier-based face detector is applied only to selected regions to verify the presence of a face (the Viola-Jones detector is used in this paper). The proposed system is evaluated using 640 × 480 pixels test images and compared with other relevant methods. Experimental results show that the proposed method reduces the detection time to 42 ms, where the Viola-Jones detector alone requires 565 ms (on a desktop processor). This improvement makes the face detector suitable for real-time applications. Furthermore, the proposed method requires 50% of the computation time of the best competing method, while reducing the false positive rate by 3.2% and maintaining the same hit rate.

show abstract

“…In surveillance environments cameras are almost invariably distributed very sparsely (wide baseline). Calibrating cameras for intelligent surveillance environments [7] therefore requires features that are highly robust to view change. A comprehensive review of local image feature extractors may be found in [8].…”

Section: Introductionmentioning

confidence: 99%

Hessian-Based Affine Adaptation of Salient Local Image Features

2011

View full text Add to dashboard Cite

Affine covariant local image features are a powerful tool for many applications, including matching and calibrating wide baseline images. Local feature extractors that use a saliency map to locate features require adaptation processes in order to extract affine covariant features. The most effective extractors make use of the second moment matrix (SMM) to iteratively estimate the affine shape of local image regions. This paper shows that the Hessian matrix can be used to estimate local affine shape in a similar fashion to the SMM. The Hessian matrix requires significantly less computation effort than the SMM, allowing more efficient affine adaptation. Experimental results indicate that using the Hessian matrix in conjunction with a feature extractor that selects features in regions with high second order gradients delivers equivalent quality correspondences in less than 17% of the processing time, compared to the same extractor using the SMM.

show abstract

Semi-supervised intelligent surveillance system for secure environments

Cited by 31 publications

References 28 publications

Suspicious Loitering Detection from Annotated CCTV Feed Using CEP Based Approach

Suspicious Loitering Detection from Annotated CCTV Feed Using CEP Based Approach

Efficient real-time face detection for high resolution surveillance applications

Hessian-Based Affine Adaptation of Salient Local Image Features

Contact Info

Product

Resources

About