# hukaixuan19970627/yolov5_obb

yolov5 + csl_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于yolov5的旋转目标检测

Repository: https://github.com/hukaixuan19970627/yolov5_obb
Canonical: https://ross.abutalabs.com/products/yolov5_obb
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: yolov5, detection, dota, rotation, oriented, aerial-imagery, rotated-object
Last push: 2023-10-13T19:46:15+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": 1995, "days_push": 1055, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1947, forks 427 (observed 2026-08-28T04:05:57.896883+00:00)

## What it is
A PyTorch implementation of YOLOv5 extended for oriented (rotated) object detection using Circular Smooth Label (CSL) angle encoding. It provides training, validation, and inference for rotated bounding box detection, benchmarked on the DOTA aerial imagery dataset.

## Use cases
- detect rotated objects in aerial images
- train a yolov5 model for oriented bounding box detection
- run rotated object detection on the DOTA dataset
- detect ships or vehicles at arbitrary angles in satellite imagery
- reproduce OBB mAP results on DOTA v1.0/v1.5/v2.0
- convert a horizontal detection model to rotation-aware detection

## When to choose
- you need rotated/oriented bounding box detection built on the familiar YOLOv5 codebase
- you work with aerial or remote-sensing imagery like DOTA
- you want pretrained OBB checkpoints and DOTA evaluation tooling out of the box

## When to avoid
- you only need standard axis-aligned object detection (use upstream ultralytics yolov5)
- you need actively maintained code or the latest YOLO versions
- you require a license more permissive than GPL-3.0
- you need production support or frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: yolov5, oriented-object-detection, rotated-bbox, circular-smooth-label, dota-dataset, aerial-imagery, object-detection, gpu, linux

## Member repositories
- hukaixuan19970627/yolov5_obb (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:57.896883+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 2026-08-30T03:07:07.077786+00:00, confidence not recorded.
  - readme: https://github.com/hukaixuan19970627/yolov5_obb (fetched 2026-08-28T04:05:57.896883+00:00, sha db8167bff77b)
- Data as of 2026-08-30T08:39:29.467469+00:00.