Screen road images for visible pavement defects using an AI-powered tool that runs in your web browser. No separate RoadVision Pro AI server, subscription or API key is required.
If the detector does not appear inside this panel, use “Open detector in a new tab”. The public demo is hosted and maintained by its author; availability and model downloads depend on that service.
ENGINEERING SAFEGUARDS & MODEL LIMITATIONS
AI output is a preliminary screening result, not an engineering measurement.
Detected damage must be checked by a human engineer.
The model was trained on Indian RDD2022 road images, not specifically on Bangladeshi roads.
Published held-out test mAP@0.5 is approximately 0.386; transverse-crack detection is particularly weak.
Do not convert image pixels into crack area, pothole depth or maintenance quantities without field measurement and calibration.
AI results do not automatically change RoadVision Pro's original pavement condition score.
Enter a documented cost and benefit value for each road. Benefit scores are supplied by the project team—not generated arbitrarily.
Optimization results will appear here after you provide road costs and benefit values.
PROJECT DELIVERABLES
Reports & Submission
⇧Raw Dataset (CSV)Original road pavement survey datasetOpen dataset →▣Project Notebook (PY)Python source file used for the project analysisOpen notebook →▤Presentation (PPT Slides)Project presentation slidesLink will be added▧Project Report (PDF)Complete project report documentLink will be added
THE PEOPLE BEHIND THE PROJECT
Project team
Foundation X · 4 student members
SERIAL 01 · 24205135
Rakibul Hasan
Group Leader · Developer
SERIAL 02 · 24205108
Niloy
Regular Member
SERIAL 03 · 24205106
Md. Mahedi Morshed
Regular Member
SERIAL 04 · 24205123
Rafiul Islam
Regular Member
Designed & Developed by Rakibul Hasan · Foundation X
ENGINEERING TRANSPARENCY
Project Methodology
Data-driven pavement assessment workflow
The proposed project follows a systematic, data-driven methodology to assess pavement conditions, classify road sections, and determine maintenance priorities.
01
Data Collection and Dataset Preparation
A structured dataset representing multiple road sections will be developed using pavement survey observations. The dataset will include key parameters such as:
Crack Percentage
Pothole Count or Area
Rut Depth
Roughness Indicator
Traffic Level
Drainage Condition
02
Data Validation and Preprocessing
The collected dataset will be processed to identify missing values, duplicate records, invalid entries, and inconsistent measurements. Data will be cleaned and standardized to ensure reliable analysis.
03
Weighted Pavement Condition Index (PCI)
A weighted condition-index approach will be developed to evaluate the overall pavement condition. Each distress parameter will be assigned a specific weight based on its engineering significance and impact on pavement performance. The weighted scores will be combined to calculate a condition index for each road section.
Based on the calculated condition index, road sections will be classified into different pavement condition categories, such as:
GoodFairPoorVery PoorCritical
05
Maintenance Priority Ranking
Road sections will be ranked according to their condition scores, distress severity, traffic importance, and drainage performance. This process will help identify which road sections require immediate maintenance and which can be scheduled for future intervention.
06
Python-Based Implementation
The system will use Python and its major libraries:
Lists and Tuples: Organizing road-section observations.
Dictionaries: Storing distress weights and classification thresholds.
Functions: Performing calculations, scoring, and classification.
Classes and Objects: Developing a PavementSection class to store road properties and calculated condition scores.
Pandas: Managing datasets and generating summary tables.
NumPy: Performing numerical and mathematical calculations.
Matplotlib: Creating bar charts and comparative visualizations.
File Handling: Saving and retrieving survey datasets and maintenance priority reports.
07
Data Visualization and Reporting
Analytical results will be presented through charts, graphs, and summary tables to provide a clear comparison of pavement conditions across different road sections. A final maintenance priority list will also be generated.
08
Testing and Validation
The proposed system will be tested using multiple road-condition scenarios to evaluate the accuracy, consistency, and reliability of its scoring, classification, and maintenance prioritization results.
EXPECTED OUTCOME
A Python-based pavement assessment system capable of identifying road conditions, classifying pavement performance, and supporting data-driven maintenance planning and investment decisions.
