scispace - formally typeset
Search or ask a question
Author

Benjamin Coifman

Bio: Benjamin Coifman is an academic researcher from Ohio State University. The author has contributed to research in topics: Detector & Traffic flow. The author has an hindex of 34, co-authored 145 publications receiving 5081 citations. Previous affiliations of Benjamin Coifman include University of California, Berkeley.


Papers
More filters
Journal ArticleDOI
TL;DR: The issues associated with feature based tracking are described, the real-time implementation of a prototype system, and the performance of the system on a large data set are presented.
Abstract: Increasing congestion on freeways and problems associated with existing detectors have spawned an interest in new vehicle detection technologies such as video image processing. Existing commercial image processing systems work well in free-flowing traffic, but the systems have difficulties with congestion, shadows and lighting transitions. These problems stem from vehicles partially occluding one another and the fact that vehicles appear differently under various lighting conditions. We are developing a feature-based tracking system for detecting vehicles under these challenging conditions. Instead of tracking entire vehicles, vehicle features are tracked to make the system robust to partial occlusion. The system is fully functional under changing lighting conditions because the most salient features at the given moment are tracked. After the features exit the tracking region, they are grouped into discrete vehicles using a common motion constraint. The groups represent individual vehicle trajectories which can be used to measure traditional traffic parameters as well as new metrics suitable for improved automated surveillance. This paper describes the issues associated with feature based tracking, presents the real-time implementation of a prototype system, and the performance of the system on a large data set. ©

669 citations

Proceedings ArticleDOI
17 Jun 1997
TL;DR: This paper describes the feature-based tracking approach for the task of tracking vehicles under congestion, a real-time implementation using a network of DSP chips, and experiments of the system on approximately 44 lane hours of video data.
Abstract: For the problem of tracking vehicles on freeways using machine vision, existing systems work well in free-flowing traffic. Traffic engineers, however, are more interested in monitoring freeways when there is congestion, and current systems break down for congested traffic due to the problem of partial occlusion. We are developing a feature-based tracking approach for the task of tracking vehicles under congestion. Instead of tracking entire vehicles, vehicle sub-features are tracked to make the system robust to partial occlusion. In order to group together sub-features that come from the same vehicle, the constraint of common motion is used. In this paper we describe the system, a real-time implementation using a network of DSP chips, and experiments of the system on approximately 44 lane hours of video data.

545 citations

Journal ArticleDOI
TL;DR: This paper presents a method for estimating link travel time using data from an individual dual loop detector, without requiring any new hardware, that exploits basic traffic flow theory to extrapolate local conditions to an extended link.
Abstract: Recent research has investigated various means of measuring link travel times on freeways. This search has been motivated in part by the fact that travel time is considered to be more informative to users than local velocity measurements at a detector station. But direct travel time measurement requires the correlation of vehicle observations at multiple locations, which in turn requires new communications infrastructure and/or new detector hardware. This paper presents a method for estimating link travel time using data from an individual dual loop detector, without requiring any new hardware. The estimation technique exploits basic traffic flow theory to extrapolate local conditions to an extended link. In the process of estimating travel times, the algorithm also estimates vehicle trajectories. The work demonstrates that the travel time estimates are very good provided there are no sources of delay, such as an incident, within a link.

329 citations

Journal ArticleDOI
TL;DR: An approach is presented for estimating future travel times on a freeway using flow and occupancy data from single-loop detectors and historical travel-time information and linear regression, with the stepwise-variable-selection method and more advanced tree-based methods.
Abstract: An approach is presented for estimating future travel times on a freeway using flow and occupancy data from single-loop detectors and historical travel-time information. Linear regression, with the stepwise-variable-selection method and more advanced tree-based methods, is used. The analysis considers forecasts ranging from a few minutes into the future up to an hour ahead. Leave-a-day-out cross-validation was used to evaluate the prediction errors without underestimation. The current traffic state proved to be a good predictor for the near future, up to 20 min, whereas historical data are more informative for longer-range predictions. Tree-based methods and linear regression both performed satisfactorily, showing slightly different qualitative behaviors for each condition examined in this analysis. Unlike preceding works that rely on simulation, real traffic data were used. Although the current implementation uses measured travel times from probe vehicles, the ultimate goal is an autonomous system that r...

288 citations

Journal ArticleDOI
TL;DR: In this paper, an improved algorithm for estimating velocity from single loop detector data is presented, which is simple enough that it can be implemented using existing controller hardware, and the benefits of this work extend to automated tests of detector data quality at dual loop speed traps.
Abstract: This paper develops an improved algorithm for estimating velocity from single loop detector data. Unlike preceding works, the algorithm is simple enough that it can be implemented using existing controller hardware. The discussion shows how the benefits of this work extend to automated tests of detector data quality at dual loop speed traps. Finally, this paper refutes an earlier study that found conventional single loop velocity estimates are biased.

197 citations


Cited by
More filters
01 Jan 2016
TL;DR: The using multivariate statistics is universally compatible with any devices to read, allowing you to get the most less latency time to download any of the authors' books like this one.
Abstract: Thank you for downloading using multivariate statistics. As you may know, people have look hundreds times for their favorite novels like this using multivariate statistics, but end up in infectious downloads. Rather than reading a good book with a cup of tea in the afternoon, instead they juggled with some harmful bugs inside their laptop. using multivariate statistics is available in our digital library an online access to it is set as public so you can download it instantly. Our books collection saves in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Merely said, the using multivariate statistics is universally compatible with any devices to read.

14,604 citations

Journal ArticleDOI
TL;DR: This paper focuses on motion tracking and shows how one can use observed motion to learn patterns of activity in a site and create a hierarchical binary-tree classification of the representations within a sequence.
Abstract: Our goal is to develop a visual monitoring system that passively observes moving objects in a site and learns patterns of activity from those observations. For extended sites, the system will require multiple cameras. Thus, key elements of the system are motion tracking, camera coordination, activity classification, and event detection. In this paper, we focus on motion tracking and show how one can use observed motion to learn patterns of activity in a site. Motion segmentation is based on an adaptive background subtraction method that models each pixel as a mixture of Gaussians and uses an online approximation to update the model. The Gaussian distributions are then evaluated to determine which are most likely to result from a background process. This yields a stable, real-time outdoor tracker that reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes. While a tracking system is unaware of the identity of any object it tracks, the identity remains the same for the entire tracking sequence. Our system leverages this information by accumulating joint co-occurrences of the representations within a sequence. These joint co-occurrence statistics are then used to create a hierarchical binary-tree classification of the representations. This method is useful for classifying sequences, as well as individual instances of activities in a site.

3,631 citations

01 Jan 2002
TL;DR: This thesis will discuss how to represent many different kinds of models as DBNs, how to perform exact and approximate inference in Dbns, and how to learn DBN models from sequential data.
Abstract: Dynamic Bayesian Networks: Representation, Inference and Learning by Kevin Patrick Murphy Doctor of Philosophy in Computer Science University of California, Berkeley Professor Stuart Russell, Chair Modelling sequential data is important in many areas of science and engineering. Hidden Markov models (HMMs) and Kalman filter models (KFMs) are popular for this because they are simple and flexible. For example, HMMs have been used for speech recognition and bio-sequence analysis, and KFMs have been used for problems ranging from tracking planes and missiles to predicting the economy. However, HMMs and KFMs are limited in their “expressive power”. Dynamic Bayesian Networks (DBNs) generalize HMMs by allowing the state space to be represented in factored form, instead of as a single discrete random variable. DBNs generalize KFMs by allowing arbitrary probability distributions, not just (unimodal) linear-Gaussian. In this thesis, I will discuss how to represent many different kinds of models as DBNs, how to perform exact and approximate inference in DBNs, and how to learn DBN models from sequential data. In particular, the main novel technical contributions of this thesis are as follows: a way of representing Hierarchical HMMs as DBNs, which enables inference to be done in O(T ) time instead of O(T ), where T is the length of the sequence; an exact smoothing algorithm that takes O(log T ) space instead of O(T ); a simple way of using the junction tree algorithm for online inference in DBNs; new complexity bounds on exact online inference in DBNs; a new deterministic approximate inference algorithm called factored frontier; an analysis of the relationship between the BK algorithm and loopy belief propagation; a way of applying Rao-Blackwellised particle filtering to DBNs in general, and the SLAM (simultaneous localization and mapping) problem in particular; a way of extending the structural EM algorithm to DBNs; and a variety of different applications of DBNs. However, perhaps the main value of the thesis is its catholic presentation of the field of sequential data modelling.

2,757 citations

Journal ArticleDOI
01 Aug 2004
TL;DR: This paper reviews recent developments and general strategies of the processing framework of visual surveillance in dynamic scenes, and analyzes possible research directions, e.g., occlusion handling, a combination of two and three-dimensional tracking, and fusion of information from multiple sensors, and remote surveillance.
Abstract: Visual surveillance in dynamic scenes, especially for humans and vehicles, is currently one of the most active research topics in computer vision. It has a wide spectrum of promising applications, including access control in special areas, human identification at a distance, crowd flux statistics and congestion analysis, detection of anomalous behaviors, and interactive surveillance using multiple cameras, etc. In general, the processing framework of visual surveillance in dynamic scenes includes the following stages: modeling of environments, detection of motion, classification of moving objects, tracking, understanding and description of behaviors, human identification, and fusion of data from multiple cameras. We review recent developments and general strategies of all these stages. Finally, we analyze possible research directions, e.g., occlusion handling, a combination of twoand three-dimensional tracking, a combination of motion analysis and biometrics, anomaly detection and behavior prediction, content-based retrieval of surveillance videos, behavior understanding and natural language description, fusion of information from multiple sensors, and remote surveillance.

2,321 citations

Proceedings ArticleDOI
17 Jun 2006
TL;DR: A novel algorithm for tracking an object in a video sequence represented by multiple image fragments or patches, which is able to handle partial occlusions or pose change and overcomes several difficulties which cannot be handled by traditional histogram-based algorithms.
Abstract: We present a novel algorithm (which we call "Frag- Track") for tracking an object in a video sequence. The template object is represented by multiple image fragments or patches. The patches are arbitrary and are not based on an object model (in contrast with traditional use of modelbased parts e.g. limbs and torso in human tracking). Every patch votes on the possible positions and scales of the object in the current frame, by comparing its histogram with the corresponding image patch histogram. We then minimize a robust statistic in order to combine the vote maps of the multiple patches. A key tool enabling the application of our algorithm to tracking is the integral histogram data structure [18]. Its use allows to extract histograms of multiple rectangular regions in the image in a very efficient manner. Our algorithm overcomes several difficulties which cannot be handled by traditional histogram-based algorithms [8, 6]. First, by robustly combining multiple patch votes, we are able to handle partial occlusions or pose change. Second, the geometric relations between the template patches allow us to take into account the spatial distribution of the pixel intensities - information which is lost in traditional histogram-based algorithms. Third, as noted by [18], tracking large targets has the same computational cost as tracking small targets. We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (noncolor) information).

1,522 citations