# dyh/unbox_yolov5_deepsort_counting

yolov5 deepsort 行人 车辆 跟踪 检测 计数

Repository: https://github.com/dyh/unbox_yolov5_deepsort_counting
Canonical: https://ross.abutalabs.com/products/unbox_yolov5_deepsort_counting
Language: Python
License Family: other
Last push: 2021-05-27T07:28:12+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2028, "days_push": 1924, "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 1091, forks 251 (observed 2026-08-28T04:03:33.106668+00:00)

## What it is
A Python application that combines YOLOv5 object detection with DeepSORT multi-object tracking to detect, track, and count pedestrians and vehicles in video. It supports directional in/out counting with configurable detection zones and classes.

## Use cases
- count pedestrians entering and exiting an area in video
- track and count vehicles passing a line in traffic footage
- detect people, cars, bikes, buses and trucks in a video
- build a traffic flow counting demo with yolov5 and deepsort
- analyze foot traffic direction from surveillance video

## When to choose
- you need a ready-made yolov5 + deepsort counting pipeline for pedestrians or vehicles
- you want directional in/out counting with adjustable polygon zones
- you want a simple educational reference for object tracking and counting

## When to avoid
- you need real-time streaming or production-grade deployment support
- you need a maintained project with a license, recent updates, or active support
- you need tracking classes beyond the default COCO categories without code changes

## Facets
- artifact type: application
- maturity: maintenance
- function: computer-vision, machine-learning, video-processing, object-storage
- domain: computer-vision, machine-learning
- platform: python, cross-platform
- tags: yolov5, deepsort, object-tracking, object-detection, counting, pedestrian-detection, vehicle-detection, video, linux

## Member repositories
- dyh/unbox_yolov5_deepsort_counting (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.106668+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 2026-08-30T06:49:07.551270+00:00, confidence not recorded.
  - readme: https://github.com/dyh/unbox_yolov5_deepsort_counting (fetched 2026-08-28T04:03:33.106668+00:00, sha b27fec7abe5d)
- Data as of 2026-08-30T08:39:29.467469+00:00.