# Smorodov/Multitarget-tracker

Multiple Object Tracker, Based on  Hungarian algorithm + Kalman filter.

Repository: https://github.com/Smorodov/Multitarget-tracker
Canonical: https://ross.abutalabs.com/products/multitarget-tracker
Language: C++
License: Apache-2.0
License Family: permissive
Topics: multiple-object-tracking, kalman-filter, hungarian-algorithm, car-tracking, car-counting, people-tracking, abandoned-detector, face-tracking, mobilenet-ssd, yolo, kcf
Last push: 2026-07-15T05:27:33+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 22, longevity 100
- inputs: {"age_days": 4780, "days_push": 49, "days_rel": 306, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2415, forks 670 (observed 2026-08-28T04:06:50.264533+00:00)

## What it is
A C++ library for multiple object tracking that combines detectors (YOLO, D-FINE, RF-DETR, MobileNet-SSD) with tracking algorithms based on the Hungarian algorithm and Kalman filters. It supports vehicle and pedestrian tracking, counting, and runs detectors via ONNX and TensorRT.

## Use cases
- track cars in traffic video
- count vehicles crossing a line
- track people in surveillance footage
- run yolo detection with tracking in c++
- detect and track objects with tensorrt
- track faces across video frames
- detect abandoned objects in video

## When to choose
- you need a C++ multi-object tracker with modern YOLO/DETR detector support
- you want vehicle or pedestrian counting on CPU/GPU with TensorRT acceleration
- you need Hungarian/Kalman or ByteTrack tracking integrated with detectors

## When to avoid
- you want a Python-only tracking pipeline
- you need a turnkey end-user application rather than a library to integrate
- your project is not C++/OpenCV based

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, artificial-intelligence
- platform: cpp, windows, cross-platform
- tags: object-tracking, kalman-filter, hungarian-algorithm, multi-object-tracking, yolo, tensorrt, opencv, bytetrack, vehicle-counting, people-tracking, video, linux, macos

## Member repositories
- Smorodov/Multitarget-tracker (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.264533+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 2026-08-30T02:33:10.863985+00:00, confidence not recorded.
  - readme: https://github.com/Smorodov/Multitarget-tracker (fetched 2026-08-28T04:06:50.264533+00:00, sha fabf36fe48de)
- Data as of 2026-08-30T08:39:29.467469+00:00.