Mohamed Hussein

Application of Computer Vision to Diagnosis of Pedestrian Safety Issues

The potential for using computer vision techniques to solve several shortcomings associated with traditional road safety and behavior analysis is demonstrated. Surrogate data such as traffic conflicts provide invaluable information that can be used to understand collision-contributing factors and the collision failure mechanism better. Recent advances in computer vision techniques have encouraged the use of proactive safety surrogate measures such as detection of conflicts and violations. The objective of this study is to demonstrate the automated safety diagnosis of pedestrian crossing safety issues by using computer vision techniques. The automated safety diagnosis is applied at a major signalized intersection in downtown Vancouver, British Columbia, Canada, at which concerns had been raised regarding the high conflict rate between vehicles and pedestrians as well as the elevated number of traffic violations (i.e., jaywalking). This study is unique in its attempt to extract conflict indicators and detect violations from video sequences in a fully automated way. This line of research benefits safety experts because it provides a prompt and objective safety evaluation for intersections. The research also provides a permanent database for traffic information that can be beneficial for a sound safety diagnosis as well as for developing safety countermeasures.

Evaluation of Ureteral Stent Placement After Retroperitoneal Laparoscopic Ureterolithotomy for Upper Ureteral Stone: Randomized Controlled Study

PURPOSE To determine the necessity of ureteral stent placement after retroperitoneal laparoscopic ureterolithotomy (RLU) for upper ureteral stones more than 1 cm. PATIENTS AND METHODS Between May 2006 and May 2009, 104 RLUs were performed as primary management of large upper ureteral stones. The patients were randomly divided into two groups: In group 1 (52 patients), RLU was performed without stent placement afterward, and in group 2 (52 patients), the stent was placed after RLU. The mean stone size was 16.8 cm in group 1 and 18.2 cm in group 2. The stent in group 2 was placed cystoscopically. RESULTS All procedures were performed successfully. The mean operative time was 48 minutes in group 1 vs. 65 minutes in group 2. The mean drainage time was 4.1 days in group 1 vs. 2.3 days in group 2. All the patients were followed up for a period of 6 months with no recorded cases of residual stone or ureteral stricture. CONCLUSION RLU for large upper ureteral stones could be considered as a primary line for treatment as regards the economic status in developing countries. Laparoscopic ureterolithotomy (LU) without stent placement for upper ureteral stones is safe, cost effective, has less operative time, and needs no auxiliary procedures when compared with the use of stent placement after LU, which adds costs and discomfort for the patient.

A bi-directional agent-based pedestrian microscopic model

ABSTRACT This paper describes the development of a pedestrian microsimulation model that was developed based on the agent based modeling approach, which effectively accounts for the pedestrian intelligence and heterogeneity. The model focuses on producing accurate trajectories for pedestrian interactions. Behavior rules that control pedestrian interactions were extracted from a detailed pedestrian behavior study conducted in Vancouver, BC. The calibration of model parameters was performed using a Genetic algorithm, which aimed at minimizing the error between simulated trajectories and real trajectories obtained by means of computer vision. The validation of the results was conducted using two different data sets. The average errors between simulated and actual trajectories for the two data sets were 35 cm and 27 cm, respectively, while the average speed errors were 13.3% and 5.1%. Results also showed that the model was capable of predicting the correct collision avoidance strategy in 95% of the validation cases investigated.

Multi-mode reliability-based design of horizontal curves

Recently, reliability analysis has been advocated as an effective approach to account for uncertainty in the geometric design process and to evaluate the risk associated with a particular design. In this approach, a risk measure (e.g. probability of noncompliance) is calculated to represent the probability that a specific design would not meet standard requirements. The majority of previous applications of reliability analysis in geometric design focused on evaluating the probability of noncompliance for only one mode of noncompliance such as insufficient sight distance. However, in many design situations, more than one mode of noncompliance may be present (e.g. insufficient sight distance and vehicle skidding at horizontal curves). In these situations, utilizing a multi-mode reliability approach that considers more than one failure (noncompliance) mode is required. The main objective of this paper is to demonstrate the application of multi-mode (system) reliability analysis to the design of horizontal curves. The process is demonstrated by a case study of Sea-to-Sky Highway located between Vancouver and Whistler, in southern British Columbia, Canada. Two noncompliance modes were considered: insufficient sight distance and vehicle skidding. The results show the importance of accounting for several noncompliance modes in the reliability model. The system reliability concept could be used in future studies to calibrate the design of various design elements in order to achieve consistent safety levels based on all possible modes of noncompliance.

Validation of an Agent-Based Microscopic Pedestrian Simulation Model at a Scramble Phase Signalized Intersection

Recently, an agent-based pedestrian simulation model was developed at the University of British Columbia to model detailed pedestrian interactions. The model was originally calibrated and validated with video data, collected at a signalized intersection in Vancouver. However, it is important to investigate the applicability of the model in different walking environments. The main objective of this study was to assess the model performance in handling pedestrian interactions at a scramble phase signalized intersection in Oakland, California. The intersection had four conventional crosswalks in addition to two diagonal crosswalks, used during the scramble pedestrian phase. Model parameters were calibrated with a genetic algorithm, which aimed to minimize the location and speed error between simulated and actual trajectories, extracted from the video sequence through computer vision. Validation results showed that the model was capable of reproducing pedestrian trajectories with high accuracy in regard to average location and speed error. The average location error for 271 pedestrians considered in the validation was 0.49 m, while the average speed error was 0.04 m/s. Detailed analysis of crossing speed for both conventional and diagonal crossings was presented, and the ability of the model to produce the same speed distributions observed in actual data was confirmed. Furthermore, the ability of the model to reproduce five interactions that were frequently observed in the data was assessed. Results showed that the model was capable of reproducing the actual behavior taken by pedestrians during these interactions with high accuracy, from 80% to 100%.

Validation of an Agent-based Microscopic Pedestrian Simulation Model at the Pedestrian Walkway of Brooklyn Bridge

The objective of this study is to validate a recently developed agent-based pedestrian simulation model, using data collected at the pedestrian walkway of Brooklyn Bridge. Video data were collected at the walkway and the trajectories of 294 pedestrians were extracted using computer vision. A genetic algorithm was applied to identify the optimum model parameters that minimize the error between the simulated and the actual trajectories of the calibration dataset. The simulation model was then applied to reproduce the trajectories of 214 pedestrians, considered for validation. The validation results showed that the model was capable of producing pedestrian trajectories with high accuracy, as the average location error between actual and simulated trajectories was for 0.32 m, while the average speed error was 0.06 m/s. Macroscopic results of the model were assessed by comparing the density–speed relationship in both actual data and the simulation. Finally, the accuracy of the model in reproducing the actual behavior of pedestrians during different interactions was evaluated. Results showed that the model was capable of handling these interactions with high accuracy, ranged between 79% and 100%.

Analysis of Road User Behavior and Safety During New York City’s Summer Streets Program

Automated computer vision video analysis techniques were used to analyze video data during the operation of New York City’s Summer Streets Program at a major signalized intersection. The main objectives of this study were to diagnose pedestrian and cyclist safety issues during the shared space operation and to demonstrate the feasibility of the automatic extraction of road user data (e.g., pedestrian, runner, rollerblader, or cyclist) required for microscopic behavior analysis. Road users’ speeds and pedestrian gait parameters (step frequency and step length) were automatically extracted and analyzed. Results show that pedestrian walking speed was highest during the Summer Streets operation (1.49 ± 0.54 m/s) because pedestrians had more street space to use and slowest during normal operations (1.30 ± 0.22 m/s). Bike speeds were low during the Summer Streets event (3.62 ± 0.97 m/s), likely because of interaction with pedestrians, but these speeds increased during normal traffic operations. Pedestrians and cyclists moving in groups tended to be slower and confirmed results found in previous studies. The safety analysis was conducted with traffic conflict techniques. It was observed that the lowest rate of conflicts between pedestrians and cyclists and between cyclists was found to be during Summer Streets operations. In addition, an analysis of spatial violations showed that some road users were not observing traffic rules in the transition period after Summer Streets ceased to operate.