v0.1.0-beta

Functionality Overview

• Video Input Options: Utilize a live USB camera feed or upload a pre-recorded video for analysis.
• Frame Skipping: Define frame skip settings to optimize processing.
• Visual Feedback:
  • The status dropdown displays outputs from the computer vision models.
  • Resource usage is shown through bars located below the status dropdown.
• Analysis Tools:
  • Displays vehicle details such as plate number, sighting count, first and last sighting dates, and a calculated risk score.
  • Risk score calculation is based on the mean, median, and mode of total sightings across all observed plates.
  • Media logs for each vehicle can be accessed by selecting a plate on the Analysis page, featuring dropdowns for each sighting date and time, along with a cropped image of the vehicle and plate, and a video highlighting the vehicle in red labeled as "Target Vehicle".
• Data Management: Offers an option to clear all logs on the Analysis page for privacy and system performance.

Technical Specifications

• Vehicle Detection: Utilizes Ultralytics YOLOv9c, a state-of-the-art model for accurate vehicle detection.
• Plate Area Detection: Employs the License Plate Recognition LHQOW Dataset to locate license plates within the vehicle area detection. Pretrained on YOLOv8n using Ultralytics. See model metrics here.
• Alphanumeric Recognition: Implements EasyOCR english_g2 for extracting alphanumeric characters from license plates, enabling accurate plate string detection.