Papanikolopoulos, Nikolaos P.

This report describes a real-time sensory system for monitoring safety in work zones by processing sequences of greyscale images from a stationary camera. The system uses the difference of high- and low-frequency elements to accomplish the goal of detecting the moving object. The output of detection phase, the tracked regions (or blobs) are passed to the classification level, and to the safety monitoring level. The classification level deals with the models of moving objects in the work-zone, and it depends on the results of the detection stage as the only source of input. Thus, researchers use processed images rather than raw images, which are highly sensitive to noise. In the safety monitoring stage, the system continuously detects situations, which potentially may cause accidents, and outputs warning messages if applicable; Designed to be robust, close to real-time, and easy to operate, the system was implemented on a Datacube Max Video 20 equipped with a Datacube Max 860 vector processor, and was converted later to new generation Datacube Max Video 200 with Max 860. Experimental results based on footage from several work-zone sites around the Twin Cities metro area have shown that the system is robust in different situations.

Sleep deprivation and sleep disorder continues to cause problems on the road. Reducing the number of accidents related to driver fatigue would save the society a significant amount of money and personal suffering. Monitoring the driver's symptoms can help determine driver fatigue early enough to prevent accidents due to lack of awareness. This report describes advances towards a non-intrusive approach for real-time detection of driver fatigue. It uses a video camera that points directly toward the driver's face and monitors the driver's eye to detect micro-sleeps, or short periods of sleep of about three-to-four seconds.

This report evaluates the Minnesota Department of Transportation's (Mn/DOT) Salt Solutions program over the past two years. The evaluation documents the components of the program, describes the technology, and provides a detailed cost-benefit analysis. Recognizing the potential to reduce the level of salt and sand use, the maintenance division began a reduction initiative in District 1 during the 1996-97 snow and ice season. The Salt Solutions program sought to develop a set of tools and a system that allowed operators to make better application rate decisions, support those tools and systems with ongoing training, develop controls and measurements to track the effectiveness of the tools and training, and recognize improved performance. The program expanded statewide in the 1997-98 winter season. Results of this evaluation show that the program is cost-effective means of reducing the amount of salt and sand applied to Minnesota roadways while still maintaining a safe operating environment. In its first year, the program saved an estimated $177,000.

This report presents a real-time system for pedestrian tracking in sequences of grayscale images acquired by a stationary CCD (charged-coupled devices) camera. The research objective involves integrating this system with a traffic control application, such as a pedestrian control scheme at intersections. The system outputs the spatiotemporal coordinates of each pedestrian during the period the pedestrian remains in the scene. The system processes at three levels: raw images, blobs, and pedestrians. It models blob tracking as a graph optimization problem and pedestrians as rectangular patches with a certain dynamic behavior. Kalman filtering is used to estimate pedestrian parameters. The system was implemented on a Datacube MaxVideo 20 equipped with a Datacube Max860 and on a Pentiumbased PC. The system achieved a peak performance of more than 20 frames per second. Experimental results based on indoor and outdoor scenes demonstrated the system's robustness under many difficult situations such as partial or full occlusions of pedestrians

This report describes a real-time system for tracking pedestrians in sequences of grayscale images acquired by a stationary camera. The system outputs the spatio-temporal coordinates of each pedestrian during the period when the pedestrian is visible. Implemented on a Datacube MaxVideo 20 equipped with a Datacube Max 860, the system achieved a peak performance of over 30 framers per second. Experimental results based on indoor and outdoor scenes have shown that the system is robust under many difficult traffic situations. The system uses the "figure/ground" framework to accomplish the goal of pedestrian detection. The detection phase outputs the tracked blobs (regions), which in turn pass to the final level, the pedestrian level. The pedestrian level deals with pedestrian models and depends on the tracked blobs as the only source of input. By doing this, researchers avoid trying to infer information about pedestrians directly from raw images, a process that is highly sensitive to noise. The pedestrian level makes use of Kalman filtering to predict and estimate pedestrian attributes. The filtered attributes constitute the output of this level, which is the output of the system. This system was designed to be robust to high levels of noise and particularly to deal with difficult situations, such as partial or full occlusions of pedestrians. The report compares vision sensors with other types of possible sensors for the pedestrian control task and evaluates the use of active deformable models as an effective pedestrian tracking module.

The use and creation of combined high-occupancy vehicle/high-occupancy toll (HOV/HOT Lanes) have become more common in urban areas since all types of road users can take advantage of the lane either as a high-occupancy vehicle or opting in to pay a congestion adjusted free. However; to maintain working integrity of the lanes for all users; stepped enforcement to discourage cheating has been needed as more lanes are added. This study evaluated the capability of a novel image sensor device to automate detection of in-vehicle occupants to flag law enforcement of HOV/HOT lane violators. The sensor device synchronously captures three co-registered images; one in the visible spectrum and two others in the infrared bands. The key idea is that the infrared bands can enhance correct occupancy detection through known phenomenological spectral properties of objects and humans residing inside the vehicle. Several experiments were conducted to determine this capability across varied conditions and scenarios to assess detection segmentation algorithms of vehicle passengers and drivers. Although occupancy detection through vehicle glass could be achieved in many cases; improvements must be made to such a detection system to increase robustness and reliability as a law enforcement tool. These improvements were guided by the experimental results; as well as suggested methods for deployment if this or similar technologies were to be deployed in the future.

The objective of the project is to analyze existing technologies used for the process of generating counts of bicycles and pedestrians in transportation facilities such as walk and bicycle bridges, urban bicycle routes, bicycle trails etc. The advantages and disadvantages of each existing technology which is being applied to counting has been analyzed and some commercially available products were listed. A technical description of different methods that were considered for vision based object recognition is also mentioned along with the reasons as to why such methods were overlooked for our problem. Support Vector Machines were used for classification based on a vocabulary of features built using interest point detectors. After finalizing the software and hardware, five sites were picked for filming and about 10 hours of video was acquired in all. A portion of the video data was used for training and the remainder was used for testing the algorithm's accuracy. Results of counts are provided and an interpretation of these results is provided in this report. Upon detailed analysis the reasons for false counts and undercounting in some cases have been identified and current work concerns dealing with these issues. Changes are being made to the system to improve the accuracy with the current level of training and make the system available for practitioners to perform counting.

This study evaluated the efficacy of active versus passive warnings at uncontrolled pedestrian (ped) crosswalks (Xwalks), by comparing how these two warnings types influenced behavior of drivers approaching such Xwalks. Vehicle-Xwalk interactions were observed at 18 sites with passive, continuously flashing, or ped-activated warnings, yielding 7,305 no ped present and 596 ped present interactions. Vehicle velocities and accelerations were averaged for each interaction. Findings show no significant effect of warning type on overall velocities for either interaction type. With peds present only, for average velocities at successive 5m distances from the Xwalk, a downward trend in velocities from 25 to 5m is observed for passive and active warning sites, but not for pedactivated warning sites. Various lines of evidence point to a number of sources of ambiguity regarding the salience of uncontrolled Xwalk warnings, resulting in behavioral uncertainty by drivers interacting with such warnings. Mixed findings on effects of warning type in this study point to the need for further analysis of this problem area.

We propose methods to distinguish between moving cast shadows and moving foreground objects in video sequences Shadow detection is an important part of any surveillance system as it makes object shape recovery possible, as well a improves accuracy of other statistics collection systems. As most such systems assume video frames without shadows, shadows must be dealt with beforehand. We propose a multi-level shadow identification scheme that is generally applicable without restrictions on the number of light sources, illumination conditions, surface orientations, and object sizes. In the first level, we use a background segmentation technique to identify foreground regions that include moving shadows. In the second step, pixel-based decisions are made by comparing the current frame with the background model to distinguish between shadows and actual foreground. In the third step, this result improved using blob-level reasoning that works on geometric constraints of identified shadow and foreground blobs. Results on various sequences under different illumination conditions show the success of the proposed approach. Second, we propose methods for physical placement of cameras in a site so as to make the most of the number of cameras available.

This report outlines a series of vision-based algorithms for data collection at traffic intersections. We have purposed an algorithm for obtaining sound spatial resolution, minimizing occlusions through an optimization-based camera-placement algorithm. A camera calibration algorithm, along with the camera calibration guided user interface tool, is introduced. Finally, a computationally simple data collection system using a multiple cue-based tracker is also presented. Extensive experimental analysis of the system was performed using three different traffic intersections. This report also presents solutions to the problem of reliable target detection and tracking in unconstrained outdoor environments as they pertain to vision-based data collection at traffic intersections.