Locating People in Video from Semantic Descriptions: A New Database and Approach

Halstead, Michael; Denman, Simon; Sridharan, Sridha; Fookes, Clinton

doi:10.1109/icpr.2014.770

Cited by 27 publications

(21 citation statements)

References 17 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the limitations observed in systems such as [36,63] is that locations in the background can be well matched to the target. To overcome this, inspiration is taken from the notion of universal background models as used in biometrics.…”

Section: Particle Based Searchmentioning

confidence: 99%

“…Colour models are trained for each of the target colours and skin (i.e. twelve colours in total) using the colour patches provided by [63]. GMMs with up to twelve components (the number of components used is determined using the BIC) are trained in the CieLab colour space.…”

Section: Appearancementioning

confidence: 99%

“…GMMs with up to twelve components (the number of components used is determined using the BIC) are trained in the CieLab colour space. A confusion matrix is also computed using the test patches provided in [63], which is used when generating the expected colour of a region.…”

Section: Appearancementioning

confidence: 99%

“…Although classical biometrics such as facial recognition approaches can be used for subject identification, the need for enrollment and constraints on image conditions often make them Soft biometrics are able to provide information about physical (build), behavioural (gait) or adhered (clothing) human characteristics, and have been used in various computer vision research areas; including surveillance [63], fashion [153], content based image retrieval [73], clothing pattern recognition for the visually impaired [158], simplistic replication of human verbal descriptions of images in [79], and as an image labeling tool for surveillance with a deep neural network (DNN) [118]. Where an individual trait such as hair colour, clothing colour, height or gender may lack the permanence or distinctiveness to uniquely identify an individual, the grouping of traits is able to create a more unique soft-biometric signature.…”

Section: Introduction 11 Overviewmentioning

confidence: 99%

“…Semantic person search [40,50,63,144] is a novel method of searching from a supplied description, and one solution to this problem. The idea of these techniques is: based on a supplied textual or verbal target query, search for potential matches without any pre-enrollment or registration of the subject of interest.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Locating People in Video Surveillance from Semantic Descriptions

Halstead¹

View full text Add to dashboard Cite

AcknowledgmentsThe completion of my PhD research programme has been an enjoyable and at times difficult and complex journey that has involved a number of people that have assisted me in so many ways throughout the process. The people that I thank here is by no means a comprehensive list as there isn't enough paper for the names I have to mention.I would firstly like to thank my supervisory team, Clinton Fookes, Sridha Sridharan, and Simon Denman for providing valuable guidance throughout the course of my study. I would like to thank Clinton and Sridha for providing me with the opportunity to study my PhD, and also for providing the Vision and Signal Processing (VSP) laboratory environment that allowed me to research at a high level, and interact with other PhD students to assist with my PhD. I would like to make special mention of Simon for his day to day support and being consistently available to help me with my endless questions, and without his help, guidance, and encouragement I would not have made it to the end of my PhD. Another member of the of the VSP discipline that I would like to thank is David Dean, as a member of VSP he assisted me multiple times throughout the course of my PhD.I would also like to thank the other students and past and present staff within the VSP laboratory, thank you for the sharing of knowledge but mostly thank you all for the entertainment, and enjoyable moments that we shared throughout this time. AbstractIn surveillance and security situations it is often necessary to search and locate a subject of interest from a verbally or textually supplied subject description. At present, searches using these forms of queries are still predominantly performed manually and often ineffectively, via physical searching of a premises or personally watching countless hours of video footage, looking for the specific subject of interest. Surveillance networks are typically monitored by few people viewing several monitors displaying single and multiple camera feeds. In these situations, the ability to translate an externally supplied description into one of computer vision relevance would be of great assistance.To date, state-of-the-art soft biometric based search techniques primarily include some form of pre-enrollment component, where the target subject is enrolled from one camera and searched in other cameras for a match, or alternatively enrolled in an earlier instance of the same camera, and searched for in later footage. These re-identification techniques exclude however, instances where the subject has not previously been located and enrolled from the footage.Soft biometric based semantic search is one technique that provides a solution to this problem. The target query no longer requires scene interrogation and instead can be generated from a textually supplied query. While soft biometrics have obvious limitations, non-permanence and not individually identifiable, they are generally simplistic for a human operator to visually extract and relay to another human operator. They also have th...

show abstract

Section: Particle Based Searchmentioning

confidence: 99%

Section: Appearancementioning

confidence: 99%

Section: Appearancementioning

confidence: 99%