Perception & Robotics Lab

Vision that works on a dusty road at four in the afternoon.

  • Crop-disease detection
  • Infrastructure inspection
  • Edge inference
  • Data collection at scale

Lab lead

Dr. Zara Siddiqui

Assistant Professor · Head of the Perception & Robotics Lab

We build vision systems for conditions that benchmarks ignore: harsh light, low-cost cameras, intermittent connectivity and no possibility of a human in the loop. Field partners include cotton and wheat cooperatives in Punjab and a provincial roads authority.

The lab maintains one of the region’s largest labelled agricultural image sets and publishes the tooling used to collect and audit it.

Publications

  1. 2025
    Paper

    Automated Crack Segmentation for Bridge Inspection from Consumer Drones

    Zara Siddiqui, Ahmed Shah, Mariam Aziz · Automation in Construction

  2. 2025
    Paper

    Field-Robust Cotton Leaf Disease Detection on Sub-$50 Hardware

    Zara Siddiqui, Imran Khalid, Noor Fatima Baig · CVPR 2025 Workshop on Computer Vision for Agriculture