Guiding Visual Surveillance by Tracking Human Attention

By Ben Benfold, Ian David Reid. 2009

119 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “Most previous work on person recognition in images has focused either on face images [10] (mainly frontal head) or on the surveillance scenario [11, 12], where the full body is visible, usually in low resolution.”
Person Recognition in Personal Photo Collections (2015, background): “Data type The bulk of previous work on person recognition focus either on facial features [22] (only the head/face is visible), or on the surveillance scenario [3, 2] (full body is visible, usually in low resolution).”
Social interactions: A first-person perspective (2012, background): “There are previous work that estimate where people are looking in the scene [3, 14].”
Stable multi-target tracking in real-time surveillance video (2011, background): “The first group covers feed-forward systems which use only current and past observations to estimate the current state [7, 1, 2].”
Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective (2017, background): “Our case study considers the person recognition task in social media setup [5, 38, 27], as opposed to face recognition [9] (frontal faces, good lighting) or pedestrian re-identification [2, 1] (low resolution, fixed context).”
Ieee Transactions on Pattern Analysis an Machine Intelligence Structured Learning of Human Interactions in Tv Shows (background): “Visual attention of people usually corresponds to image regions of high interest, as was explored by Benfold and Reid [4] in the context of automatically guiding a surveillance system.”
Context-Based Pedestrian Path Prediction (2014, methodology): “For example, [5] used a HOG-based head detector to determine pedestrian attention for automated surveillance, and [3] combined contextual cues in a DBN to model influence of group interaction on VFOA.”
High Five: Recognising human interactions in TV shows (2010, background): “Optical flow is also discretised into five bins: no-motion, left, right, up and down.”