Evan Ribnick

Estimating pedestrian counts in groups

The goal of this work is to provide a system which can aid in monitoring crowded urban environments, which often contain tight groups of people. In this paper, we consider the problem of counting the number of people in the scene and also tracking them reliably. We propose a novel method for detecting and estimating the count of people in groups, dense or otherwise, as well as tracking them. Using prior knowledge obtained from the scene and accurate camera calibration, the system learns the parameters required for estimation. This information can then be used to estimate the count of people in the scene, in real-time. Groups are tracked in the same manner as individuals, using Kalman filtering techniques. Favorable results are shown for groups of various sizes moving in an unconstrained fashion.

Real-Time Detection of Camera Tampering

This paper presents a novel technique for camera tampering detection. It is implemented in real-time and was developed for use in surveillance and security applications. This method identifies camera tampering by detecting large differences between older frames of video and more recent frames. A buffer of incoming video frames is kept and three different measures of image dissimilarity are used to compare the frames. After normalization, a set of conditions is tested to decide if camera tampering has occurred. The effects of adjusting the internal parameters of the algorithm are examined. The performance of this method is shown to be extremely favorable in real-world settings.

Estimating 3D Positions and Velocities of Projectiles from Monocular Views

In this paper, we consider the problem of localizing a projectile in 3D based on its apparent motion in a stationary monocular view. A thorough theoretical analysis is developed, from which we establish the minimum conditions for the existence of a unique solution. The theoretical results obtained have important implications for applications involving projectile motion. A robust, nonlinear optimization-based formulation is proposed, and the use of a local optimization method is justified by detailed examination of the local convexity structure of the cost function. The potential of this approach is validated by experimental results.

3D Reconstruction of Periodic Motion from a Single View

Periodicity has been recognized as an important cue for tasks like activity recognition and gait analysis. However, most existing techniques analyze periodic motions only in image coordinates, making them very dependent on the viewing angle. In this paper we show that it is possible to reconstruct a periodic trajectory in 3D given only its appearance in image coordinates from a single camera view. We draw a strong analogy between this problem and that of reconstructing an object from multiple views, which allows us to rely on well-known theoretical results from the multi-view geometry domain and obtain significant guarantees regarding the solvability of the estimation problem. We present two different formulations of the problem, along with techniques for performing the reconstruction in both cases, and an algorithm for estimating the period of motion from its image-coordinate trajectory. Experimental results demonstrate the feasibility of the proposed techniques.

Detection of thrown objects in indoor and outdoor scenes

We present a novel technique for the detection of thrown objects and other free-flying bodies in video sequences. Our method runs in real-time and was designed to be used as a component in a deployed surveillance system. We detect regions of interesting motion that fit certain size, compactness and speed criteria, and use the expectation maximization algorithm to detect objects on parabolic trajectories over a short time window. The system was shown to successfully detect thrown objects of various sizes in a large test set of indoor and outdoor videos.

Estimating 3D Trajectories of Periodic Motions from Stationary Monocular Views

We present a method for estimating the 3D trajectory of an object undergoing periodic motion in world coordinates by observing its apparent trajectory in a video taken from a single stationary camera. Periodicity in 3D is used here as a physical constraint, from which accurate solutions can be obtained. A detailed analysis is performed, from which we gain significant insight regarding the nature of the problem and the information that is required to arrive at a unique solution. Subsequently, a robust, numerical approach is proposed, and it is demonstrated that the cost function exhibits strong local convexity which is amenable to local optimization methods. Experimental results indicate the effectiveness of the proposed method for reconstructing periodic trajectories in 3D.

View-invariant analysis of periodic motion

Periodicity has been recognized as an important cue for tasks like activity recognition and gait analysis. However, most existing techniques analyze periodic motions only in image coordinates, making them very dependent on the viewing angle. In this paper we propose a new technique for reconstructing periodic point trajectories in 3D given only their apparent trajectories in image coordinates from a single stationary camera. We show that this reconstruction is possible without performing a costly gradient descent-type optimization, and is based only on a single SVD. This new algorithm is shown to accurately reconstruct natural human motions, allowing them to be compared in 3D world coordinates, independent of the angle from which they were originally viewed.

Reconstructing and analyzing periodic human motion from stationary monocular views

We have shown previously that it is possible to accurately reconstruct periodic motions in 3D from a single camera view, using periodicity as a physical constraint from which to perform geometric inference. In this paper we explore the suitability of the reconstruction techniques for real human motion. We examine the degree of periodicity of human gait empirically, and develop algorithmic tools to address some of the challenges arising from this type of motion, including reconstructing motions that deviate from pure periodicity, properly handling the trajectories of multiple points on an articulated body, and proposing a distance function for measuring the difference between two reconstructions. Importantly, we illustrate the usefulness of these techniques by applying them to the tasks of view-invariant activity classification, clinical gait analysis and person identification.

Human motion patterns from single camera cues for medical applications

Physical constraints that underly the formation of periodic motions can be effectively used to accurately reconstruct the periodic motion from even single camera views. As shown in our earlier work, this reduces to a problem of geometric inference. In this paper, we focus on periodic motions exhibited by humans, which are generally not perfectly periodic, and explore the suitability of the reconstruction techniques in these scenarios. We examine the degree of periodicity of human gait empirically, including the applicability of our motion model. Importantly, we illustrate the usefulness of these techniques by applying them to the task of clinical gait analysis. A computational tool to analyze periodic human motion can prove to be invaluable in medical applications either in terms of assessing deviations from normal patterns or evaluating changes resulting from therapy or other clinical procedures.