Horesh Ben Shitrit

Tracking multiple people under global appearance constraints

In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a convex global optimization problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being exploitable from frame to frame. We validate our approach on three multi-camera sport and pedestrian datasets that contain long and complex sequences. Our algorithm perseveres identities better than state-of-the-art algorithms while keeping similar MOTA scores.

Take your eyes off the ball: Improving ball-tracking by focusing on team play

Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating the tracking in terms of deciding which player, if any, is in possession of the ball at any given time. This is very different from standard approaches that first attempt to track the ball and only then to assign possession. We will show that our method substantially increases performance when applied to long basketball and soccer sequences.

Conditional Random Fields for multi-camera object detection

We formulate a model for multi-class object detection in a multi-camera environment. From our knowledge, this is the first time that this problem is addressed taken into account different object classes simultaneously. Given several images of the scene taken from different angles, our system estimates the ground plane location of the objects from the output of several object detectors applied at each viewpoint. We cast the problem as an energy minimization modeled with a Conditional Random Field (CRF). Instead of predicting the presence of an object at each image location independently, we simultaneously predict the labeling of the entire scene. Our CRF is able to take into account occlusions between objects and contextual constraints among them. We propose an effective iterative strategy that renders tractable the underlying optimization problem, and learn the parameters of the model with the max-margin paradigm. We evaluate the performance of our model on several challenging multi-camera pedestrian detection datasets namely PETS 2009 [5] and EPFL terrace sequence [9]. We also introduce a new dataset in which multiple classes of objects appear simultaneously in the scene. It is here where we show that our method effectively handles occlusions in the multi-class case.

Long term real trajectory reuse through region goal satisfaction

This paper is motivated by the objective of improving the realism of real-time simulated crowds by reducing short term collision avoidance through long term anticipation of pedestrian trajectories. For this aim, we choose to reuse outdoor pedestrian trajectories obtained with non-invasive means. This initial step is achieved by analyzing the recordings of multiple synchronized video cameras. In a second off-line stage, we fit as long as possible trajectory segments within predefined paths made of a succession of region goals. The concept of region goal is exploited to enforce the principle of “sufficient satisfaction”: it allows the pedestrians to relax the prescribed trajectory to the traversal of successive region goals. However, even if a fitted trajectory is modified due to collision avoidance, we are still able to make long-term trajectory anticipation and distribute the collision avoidance shift over a long distance.

Parsing human skeletons in an operating room

Multiple human pose estimation is an important yet challenging problem. In an operating room (OR) environment, the 3D body poses of surgeons and medical staff can provide important clues for surgical workflow analysis. For that purpose, we propose an algorithm for localizing and recovering body poses of multiple human in an OR environment under a multi-camera setup. Our model builds on 3D Pictorial Structures and 2D body part localization across all camera views, using convolutional neural networks (ConvNets). To evaluate our algorithm, we introduce a dataset captured in a real OR environment. Our dataset is unique, challenging and publicly available with annotated ground truths. Our proposed algorithm yields to promising pose estimation results on this dataset.

Analyzing Volleyball Match Data from the 2014 World Championships Using Machine Learning Techniques

This paper proposes a relational-learning based approach for discovering strategies in volleyball matches based on optical tracking data. In contrast to most existing methods, our approach permits discovering patterns that account for both spatial (that is, partial configurations of the players on the court) and temporal (that is, the order of events and positions) aspects of the game. We analyze both the mens and womens final match from the 2014 FIVB Volleyball World Championships, and are able to identify several interesting and relevant strategies from the matches.

Re-Identification for Improved People Tracking

Re-identification is usually defined as the problem of deciding whether a person currently in the field of view of a camera has been seen earlier either by that camera or another. However, a different version of the problem arises even when people are seen by multiple cameras with overlapping fields of view. Current tracking algorithms can easily get confused when people come close to each other and merge trajectory fragments into trajectories that include erroneous identity switches. Preventing this means re-identifying people across trajectory fragments. In this chapter, we show that this can be done very effectively by formulating the problem as a minimum-cost maximum-flow linear program. This version of the re-identification problem can be solved in real-time and produces trajectories without identity switches. We demonstrate the power of our approach both in single- and multicamera setups to track pedestrians, soccer players, and basketball players.