# tatsuyah/vehicle-detection

Vehicle detection using machine learning and computer vision techniques for Udacity's Self-Driving Car Engineer Nanodegree.

Repository: https://github.com/tatsuyah/vehicle-detection
Canonical: https://ross.abutalabs.com/products/vehicle-detection
Language: Jupyter Notebook
License Family: other
Topics: machine-learning, svm, svm-classifier, computer-vision, hog-features, sliding-windows, self-driving-car, udacity
Last push: 2017-10-31T03:49:56+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3233, "days_push": 3228, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1146, forks 173 (observed 2026-08-28T04:03:45.798615+00:00)

## What it is
A Jupyter Notebook project implementing vehicle detection with classical machine learning and computer vision techniques, built for Udacity's Self-Driving Car Engineer Nanodegree. It uses a linear SVM classifier with HOG features, color histograms, spatial binning, and sliding-window search over dashcam-style images.

## Use cases
- detect vehicles in images or video frames
- learn how HOG features and SVMs work for object detection
- complete a self-driving car nanodegree project
- understand sliding window object detection pipelines
- train a car classifier from GTI or KITTI image datasets
- study a worked example of classical computer vision before deep learning

## When to choose
- you want an educational walkthrough of classical (non-deep-learning) object detection
- you need a reference implementation of HOG + SVM vehicle detection
- you are working through Udacity's self-driving car curriculum

## When to avoid
- you need production-grade or modern deep-learning-based detection (use YOLO or similar)
- you need a maintained library with a license and active support
- you need real-time performance on embedded hardware

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, autonomous-vehicles, education
- platform: python, cross-platform
- tags: jupyter-notebook, svm, hog-features, sliding-windows, vehicle-detection, self-driving-car, udacity-nanodegree, object-detection

## Member repositories
- tatsuyah/vehicle-detection (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:45.798615+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:34:12.916950+00:00, confidence not recorded.
  - readme: https://github.com/tatsuyah/vehicle-detection (fetched 2026-08-28T04:03:45.798615+00:00, sha 75f44725a693)
- Data as of 2026-08-30T08:39:29.467469+00:00.