Aniket Bera

We present a novel real-time algorithm to predict the path of pedestrians in cluttered environments. Our approach makes no assumption about pedestrian motion or crowd density, and is useful for short-term as well as long-term prediction. We interactively learn the characteristics of pedestrian motion and movement patterns from 2D trajectories using Bayesian inference. These include local movement patterns corresponding to the current and preferred velocities and global characteristics such as… Show more

We present a novel real-time algorithm to predict the path of pedestrians in cluttered environments. Our approach makes no assumption about pedestrian motion or crowd density, and is useful for short-term as well as long-term prediction. We interactively learn the characteristics of pedestrian motion and movement patterns from 2D trajectories using Bayesian inference. These include local movement patterns corresponding to the current and preferred velocities and global characteristics such as entry points and movement features. Our approach involves no precomputation and we demonstrate the real-time performance of our prediction algorithm on sparse and noisy trajectory data extracted from dense indoor and outdoor crowd videos. The combination of local and global movement patterns can improve the accuracy of long-term prediction by 12-18% over prior methods in high-density videos. Show less

We present an adaptive data-driven algorithm for interactive crowd simulation. Our approach combines realistic trajectory behaviors extracted from videos with synthetic multi-agent algorithms to generate plausible simulations. We use statistical techniques to compute the movement patterns and motion dynamics from noisy 2D trajectories extracted from crowd videos. These learned pedestrian dynamic characteristics are used to generate collision-free trajectories of virtual pedestrians in slightly… Show more

We present an adaptive data-driven algorithm for interactive crowd simulation. Our approach combines realistic trajectory behaviors extracted from videos with synthetic multi-agent algorithms to generate plausible simulations. We use statistical techniques to compute the movement patterns and motion dynamics from noisy 2D trajectories extracted from crowd videos. These learned pedestrian dynamic characteristics are used to generate collision-free trajectories of virtual pedestrians in slightly different environments or situations. The overall approach is robust and can generate perceptually realistic crowd movements at interactive rates in dynamic environments. We also present results from preliminary user studies that evaluate the trajectory behaviors generated by our algorithm.
Show less

We present an interactive approach for analyzing crowd videos and generating content for multimedia applications. Our formulation combines online tracking algorithms from computer vision, non-linear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute the trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to detect anomalous behaviors, perform crowd replication, augment crowd videos with… Show more

We present an interactive approach for analyzing crowd videos and generating content for multimedia applications. Our formulation combines online tracking algorithms from computer vision, non-linear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute the trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to detect anomalous behaviors, perform crowd replication, augment crowd videos with virtual agents, and segment the motion of pedestrians. We demonstrate the performance of
these tasks using indoor and outdoor crowd video benchmarks consisting of tens of human agents; moreover, our algorithm takes less than a tenth of a second per frame on a multi-core PC. The overall approach can handle dense and heterogeneous crowd behaviors and is useful for realtime crowd scene analysis applications. Show less

We present an online parameter learning algorithm for data-driven crowd simulation and crowd content generation. Our formulation is based on incrementally learning pedestrian motion models and behaviors from crowd videos. We combine the learned crowd-simulation model with an online tracker to compute accurate, smooth pedestrian trajectories. We refine the motion model using an optimization technique to estimate the agents׳ simulation parameters. We also use an adaptive-particle filtering scheme… Show more

We present an online parameter learning algorithm for data-driven crowd simulation and crowd content generation. Our formulation is based on incrementally learning pedestrian motion models and behaviors from crowd videos. We combine the learned crowd-simulation model with an online tracker to compute accurate, smooth pedestrian trajectories. We refine the motion model using an optimization technique to estimate the agents׳ simulation parameters. We also use an adaptive-particle filtering scheme for improved computational efficiency. We highlight the benefits of our approach for improved data-driven crowd simulation, including crowd replication, augmented crowds and merging the behavior of pedestrians from multiple videos. We highlight our algorithm׳s performance in various test scenarios containing tens of human-like agents and evaluate it using standard metrics. Show less

We present a novel, real-time algorithm to extract the trajectory of each pedestrian in moderately dense crowd videos. In order to improve the tracking accuracy, we use a hybrid motion model that combines discrete and continuous flow models. The discrete model is based on microscopic agent formulation and is used for local navigation, interaction, and collision avoidance. The continuum model accounts for macroscopic behaviors, including crowd orientation and flow. We use our hybrid model with… Show more

We present a novel, real-time algorithm to extract the trajectory of each pedestrian in moderately dense crowd videos. In order to improve the tracking accuracy, we use a hybrid motion model that combines discrete and continuous flow models. The discrete model is based on microscopic agent formulation and is used for local navigation, interaction, and collision avoidance. The continuum model accounts for macroscopic behaviors, including crowd orientation and flow. We use our hybrid model with particle filters to compute the trajectories at interactive rates. We demonstrate its performance in moderately-dense crowd videos with tens of pedestrians and highlight the improved accuracy on different datasets. Show less

We present a novel, realtime algorithm to compute the trajectory of each pedestrian in moderately dense crowd scenes. Our formulation is based on an adaptive particle filtering scheme that uses a multi-agent motion model based on velocity-obstacles, and takes into account local interactions as well as physical and personal constraints of each pedestrian. Our method dynamically changes the number of particles allocated to each pedestrian based on different confidence metrics. Additionally, we… Show more

We present a novel, realtime algorithm to compute the trajectory of each pedestrian in moderately dense crowd scenes. Our formulation is based on an adaptive particle filtering scheme that uses a multi-agent motion model based on velocity-obstacles, and takes into account local interactions as well as physical and personal constraints of each pedestrian. Our method dynamically changes the number of particles allocated to each pedestrian based on different confidence metrics. Additionally, we use a new high-definition crowd video dataset, which is used to evaluate the performance of different pedestrian tracking algorithms. This dataset consists of videos of indoor and outdoor scenes, recorded at different locations with 30-80 pedestrians. We highlight the performance benefits of our algorithm over prior techniques using this dataset. In practice, our algorithm can compute trajectories of tens of pedestrians on a multi-core desktop CPU at interactive rates (27-30 frames per second). To the best of our knowledge, our approach is 4-5 times faster than prior methods, which provide similar accuracy. Show less

We present a novel, realtime algorithm to compute the trajectory of each pedestrian in a crowded scene. Our formulation is based on an adaptive scheme that uses a combination of deterministic and probabilistic trackers to simultaneously achieve high accuracy and efficiency. Furthermore, we integrate it with a multi-agent motion model and local interaction scheme to accurately compute the trajectory of each pedestrian. We highlight the performance and benefits of our algorithm on well-known… Show more

We present a novel, realtime algorithm to compute the trajectory of each pedestrian in a crowded scene. Our formulation is based on an adaptive scheme that uses a combination of deterministic and probabilistic trackers to simultaneously achieve high accuracy and efficiency. Furthermore, we integrate it with a multi-agent motion model and local interaction scheme to accurately compute the trajectory of each pedestrian. We highlight the performance and benefits of our algorithm on well-known datasets with tens of pedestrians. Show less

In this paper a line based script identification using a hierarchical classification scheme is proposed to identify the Indian scripts includes Hindi, Gurumukhi and Bangla. We model the problem as topological, structural classification problem and examine the features inspired by human visual perception. Our basic algorithm uses different feature set at different level of classifier to optimize the tradeoff between accuracy and speed. The feature extraction is done on the subsets of image… Show more

In this paper a line based script identification using a hierarchical classification scheme is proposed to identify the Indian scripts includes Hindi, Gurumukhi and Bangla. We model the problem as topological, structural classification problem and examine the features inspired by human visual perception. Our basic algorithm uses different feature set at different level of classifier to optimize the tradeoff between accuracy and speed. The feature extraction is done on the subsets of image which in turn increases the performance of algorithm. The proposed system attains overall classification accuracy of 90% over the 2500+ text image data set. Show less

In this paper a new, faster approach which is different from all the other conventional image vectorization techniques. Using canny edge detection we are able to find the sharp edges in the image and the assigning shades to each identifiable segment using random colour extraction from the original image. Finally mapping the colour blobs with the SVG Schema and generating a scalable vector image. This technique is efficient for natural and well as non-It can be directly used in security cameras… Show more

In this paper a new, faster approach which is different from all the other conventional image vectorization techniques. Using canny edge detection we are able to find the sharp edges in the image and the assigning shades to each identifiable segment using random colour extraction from the original image. Finally mapping the colour blobs with the SVG Schema and generating a scalable vector image. This technique is efficient for natural and well as non-It can be directly used in security cameras for live image enhancement. Show less

There are various methods to estimate the scene flow. Most of the methods use motion estimation with stereo re-construction. This paper describes an interesting way to fuse the video from two camera's and create a 3D reconstruction. The proposed algorithm incorporates probabilistic distributions for optical flow and disparity. Multiple such re-created renderings can be put together to create re-timed movies of the event, with the resulting visual experience richer than that of a regular video… Show more

There are various methods to estimate the scene flow. Most of the methods use motion estimation with stereo re-construction. This paper describes an interesting way to fuse the video from two camera's and create a 3D reconstruction. The proposed algorithm incorporates probabilistic distributions for optical flow and disparity. Multiple such re-created renderings can be put together to create re-timed movies of the event, with the resulting visual experience richer than that of a regular video clip, or switching between images from multiple cameras, do a head tracking of the viewer and change the view angle accordingly or view it on a mobile device using the accelerometer for camera tilting for the 3D effect. Show less

We present a trajectory extraction and behavior-learning algorithm for data-driven crowd simulation. Our formulation is based on incrementally learning pedestrian motion models and behaviors from crowd videos. We combine this learned crowd-simulation model with an online tracker based on particle filtering to compute accurate, smooth pedestrian trajectories. We refine this motion model using an optimization technique to estimate the agents' simulation parameters. We highlight the benefits of… Show more

We present a trajectory extraction and behavior-learning algorithm for data-driven crowd simulation. Our formulation is based on incrementally learning pedestrian motion models and behaviors from crowd videos. We combine this learned crowd-simulation model with an online tracker based on particle filtering to compute accurate, smooth pedestrian trajectories. We refine this motion model using an optimization technique to estimate the agents' simulation parameters. We highlight the benefits of our approach for improved data-driven crowd simulation, including crowd replication from videos and merging the behavior of pedestrians from multiple videos. We highlight our algorithm's performance in various test scenarios containing tens of human-like agents. Show less