Unsupervised camera localization in crowded spaces

Existing camera networks in public spaces such as train terminals or malls can help social robots to navigate crowded scenes. However, the localization of the cameras is required, i. e. , the positions and poses of all cameras in a unique reference. In this work, we estimate the relative location of any pair of cameras by solely using noisy trajectories observed from each camera. We propose a fully unsupervised learning technique using unlabelled pedestrians motion patterns captured in crowded scenes. We first estimate the pairwise camera parameters by optimally matching single-view pedestrian tracks using social awareness. Then, we show the impact of jointly estimating the network parameters. This is done by formulating a nonlinear least square optimization problem, leveraging a continuous approximation of the matching function. We evaluate our approach in real-world environments such as train terminals, where several hundreds of individuals need to be tracked across dozens of cameras every second.

Authors

• Alexandre Alahi
• Judson Wilson
• Li Fei-Fei 0001
• Silvio Savarese

Keywords

• Cameras
• Robot vision systems
• Tracking
• Optimization
• Navigation
• Camera Localization
• Public Spaces
• Nonlinear Programming
• Nonlinear Least Squares
• Social Awareness
• Social Robots
• Least-squares Optimization
• Pair Of Cameras
• Crowded Scenes
• Camera Network
• Least-squares
• Cost Function
• Markov Chain Monte Carlo
• Uncertainty Estimation
• Residual Function
• Real-world Datasets
• Motion Model
• Joint Optimization
• Levenberg-Marquardt Algorithm
• Relative Arrangement
• Camera Angle
• Bipartite Matching
• Distance Constraints
• Pairwise Estimates
• Greedy Approach
• Semidefinite Programming
• Nonlinear Flow
• Linear Flow
• Candidate Solutions
• Absolute Angle