Counting, Detecting and Tracking of People in Crowded Scenes
Prof. Mubarak Shah, Trustee Chair Professor of Computer Science, Director of the Center for Research in Computer Vision, University of Central Florida, USA.
In this talk, first I will present a new approach for counting people in extremely dense crowds. Our approach relies on multiple sources of information such as low confidence head detections, repetition of texture elements (using SIFT), and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region. In addition, we employ a global consistency constraint on counts using Markov Random Field. This caters for disparity in counts in local neighborhoods and across scales.
Next, I will discuss how we explore context for human detection in dense crowds in the form of locally-consistent scale prior which captures the similarity in scale in local neighborhoods and its smooth variation over the image. Using the scale and confidence of detections obtained from an underlying human detector, we infer scale and confidence priors using Markov Random Field. In an iterative mechanism, the confidences of detections are modified to reflect consistency with the inferred priors, and the priors are updated based on the new detections. The final set of detections obtained are then reasoned for occlusion using Binary Integer Programming where overlaps and relations between parts of individuals are encoded as linear constraints.
Finally, I will present a method for tracking in dense crowds using prominence and neighborhood motion concurrence. Our method begins with the automatic identification of prominent individuals from the crowd that are easy to track. Then, we use Neighborhood Motion Concurrence to model the behavior of individuals in a dense crowd, this predicts the position of an individual based on the motion of its neighbors.
Identity Preserving Multi-People Tracking through Linear Programming
Prof. Pascal Fua, Director of Computer Vision Lab, School of Computer and Communication Science, Ecole Polytechnique Fédérale de Lausanne, Switzerland.
In this talk, I will show that, given probabilities of presence of people at various locations in individual time frames, finding the most likely set of trajectories amounts to solving a linear program that depends on very few parameters.
This can be done without requiring appearance information and in real-time, by using the K-Shortest Paths algorithm (KSP). However, this can result in unwarranted identity switches in complex scenes. In such cases, sparse image information can be used within the Linear Programming framework to keep track of people’s identities, even when their paths come close to each other or intersect. By sparse, we mean that the appearance needs only be discriminative in a very limited number of frames, which makes our approach widely applicable. Furthermore, we can also model the interactions between people and moving objects in their environments. This lets us handle realistic scenarios in which humans are not the only things that move in the scene.
Turning Big Data into Rich data: Proactive Defensive Strategies in an Age of Modern Surveillance
Gennadiy Reznichenko, IT Security Manager EMEA, Honeywell, USA.
Modern video surveillance strategies go beyond camera deployments at critical points of your defence lines and operators continuously watching numerous screens. Number of security personnel should not restrict your camera plan. Can present day scenario of adding more eyes to observe first signs of anomalous behaviour be replaced by technology? Would software that turns huge amounts of video data into events and alerts that Security Operations Center staff can use to proactively monitor crowded environments be a step in a right direction?
During this presentation you will hear about a few examples demonstrating how security teams struggle to prioritize their limited resources during strikes, civil unrest, Olympic Games and other major sport events. With the use of analogies and examples, the audience will appreciate that CCTV monitoring, detecting abnormalities and managing security events is a resource consuming task. This presentation will provide researches with a few areas they should focus to enable security teams make right and fast decisions and adapt to the future changing needs of the organisation.