EV Charger Detection

Industrial AI / Computer Vision

An end-to-end computer vision pipeline for collecting, filtering, labeling, and classifying EV charger imagery.

Human-in-the-loop annotation refinement for EV charger imagery.

Overview

The project combines web-collected EV charger imagery with automated labeling, embedding-based filtering, and model training.

The problem

Image collections can contain uncertain labels, near duplicates, and source-related leakage that undermine model evaluation.

My contribution

Built the pipeline around YOLO auto-labeling, ResNet50 embeddings, human review, and leakage-aware dataset splitting.

System or workflow

  1. 01Collect candidate imagery.
  2. 02Generate initial labels with YOLO.
  3. 03Filter candidates using pretrained embeddings and cosine similarity.
  4. 04Review uncertain samples and train the classifier on verified data.

Technical highlights

  1. 01Human-in-the-loop annotation refinement
  2. 02Cosine similarity filtering with pretrained embeddings
  3. 03Leakage-aware train and validation splitting by source URL
Next project04arTIcoIndustrial AI / Time-Series Machine Learning / Model Validation

Project image

Interactive demo