Learn More
— This work aims at addressing the many problems that have hindered the development of vision-based systems for automated road safety analysis. The approach relies on traffic conflicts used as surrogates for collision data. Traffic conflicts are identified by computing the collision probability for any two road users in an interaction. A complete system is(More)
Road collisions represent deplorable human and financial costs to society. Although some progress has been made, a renewed effort is necessary to tackle this growing worldwide issue. This paper advocates the development of proactive methods for road safety analysis that do not depend on the occurrence of collisions. In particular, collecting and analyzing(More)
1 Traditional road safety diagnosis is a reactive approach, based on historical collision data. This work aims at developing a proactive approach which avoids waiting for accidents to happen. There is a need for surrogate safety measures that can also provide complementary information and are easy to collect, e.g. requiring shorter observation periods. The(More)
We present a novel approach to background subtraction that is based on the local shape of small image regions. In our approach, an image region centered on a pixel is mod-eled using the local self-similarity descriptor. We aim at obtaining a reliable change detection based on local shape change in an image when foreground objects are moving. The method(More)
—In general, the problem of change detection is studied in color space. Most proposed methods aim at dynamically finding the best color thresholds to detect moving objects against a background model. Background models are often complex to handle noise affecting pixels. Because the pixels are considered individually, some changes cannot be detected because(More)
— The importance of reducing the social and economic costs associated with traffic collisions can not be overstated. The first goal of this research is to develop a method for automated road safety analysis using video sensors in order to address the problem of a dependency on the deteriorating collision data. The method will automate the extraction of(More)
We introduce MMTrack (max-margin tracker), a single-target tracker that linearly combines constant and adaptive appearance features. We frame offline single-camera tracking as a structured output prediction task where the goal is to find a sequence of locations of the target given a video. Following recent advances in machine learning, we discriminatively(More)